From d0a3052f6faefffcb15e93853c06f56207c32743 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:33 -0800 Subject: perf metric: Compute and print threshold values Compute the threshold metric and use it to color the metric value as red or green. The threshold expression is used to generate the set of events as the threshold may require additional events. A later patch make this behavior optional with a --metric-no-threshold flag. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-37-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-shadow.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 806b32156459..a41f186c6ec8 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -777,6 +777,7 @@ static int prepare_metric(struct evsel **metric_events, static void generic_metric(struct perf_stat_config *config, const char *metric_expr, + const char *metric_threshold, struct evsel **metric_events, struct metric_ref *metric_refs, char *name, @@ -789,9 +790,10 @@ static void generic_metric(struct perf_stat_config *config, { print_metric_t print_metric = out->print_metric; struct expr_parse_ctx *pctx; - double ratio, scale; + double ratio, scale, threshold; int i; void *ctxp = out->ctx; + const char *color = NULL; pctx = expr__ctx_new(); if (!pctx) @@ -811,6 +813,12 @@ static void generic_metric(struct perf_stat_config *config, char *unit; char metric_bf[64]; + if (metric_threshold && + expr__parse(&threshold, pctx, metric_threshold) == 0) { + color = fpclassify(threshold) == FP_ZERO + ? PERF_COLOR_GREEN : PERF_COLOR_RED; + } + if (metric_unit && metric_name) { if (perf_pmu__convert_scale(metric_unit, &unit, &scale) >= 0) { @@ -823,22 +831,22 @@ static void generic_metric(struct perf_stat_config *config, scnprintf(metric_bf, sizeof(metric_bf), "%s %s", unit, metric_name); - print_metric(config, ctxp, NULL, "%8.1f", + print_metric(config, ctxp, color, "%8.1f", metric_bf, ratio); } else { - print_metric(config, ctxp, NULL, "%8.2f", + print_metric(config, ctxp, color, "%8.2f", metric_name ? metric_name : out->force_header ? name : "", ratio); } } else { - print_metric(config, ctxp, NULL, NULL, + print_metric(config, ctxp, color, /*unit=*/NULL, out->force_header ? (metric_name ? metric_name : name) : "", 0); } } else { - print_metric(config, ctxp, NULL, NULL, + print_metric(config, ctxp, color, /*unit=*/NULL, out->force_header ? (metric_name ? metric_name : name) : "", 0); } @@ -1214,9 +1222,9 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, list_for_each_entry (mexp, &me->head, nd) { if (num++ > 0) out->new_line(config, ctxp); - generic_metric(config, mexp->metric_expr, mexp->metric_events, - mexp->metric_refs, evsel->name, mexp->metric_name, - mexp->metric_unit, mexp->runtime, + generic_metric(config, mexp->metric_expr, mexp->metric_threshold, + mexp->metric_events, mexp->metric_refs, evsel->name, + mexp->metric_name, mexp->metric_unit, mexp->runtime, map_idx, out, st); } } -- cgit v1.2.3-70-g09d2 From 1fd09e299bdd434b259da3ffcfdcae2dfeac9b2e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:35 -0800 Subject: perf metric: Add --metric-no-threshold option Thresholds may need additional events, this can impact things like sharing groups of events to avoid multiplexing. Add a flag to make the threshold calculations optional. The threshold will still be computed if no additional events are necessary. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-39-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 4 +++ tools/perf/tests/expand-cgroup.c | 3 +- tools/perf/tests/parse-metric.c | 1 - tools/perf/tests/pmu-events.c | 4 +-- tools/perf/util/metricgroup.c | 62 +++++++++++++++++++++++++--------------- tools/perf/util/metricgroup.h | 3 +- tools/perf/util/stat-shadow.c | 3 +- tools/perf/util/stat.h | 1 + 8 files changed, 49 insertions(+), 32 deletions(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 5d18a5a6f662..5e13171a7bba 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1256,6 +1256,8 @@ 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, @@ -1852,6 +1854,7 @@ static int add_default_attributes(void) 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); @@ -2519,6 +2522,7 @@ 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); diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c index 672a27f37060..ec340880a848 100644 --- a/tools/perf/tests/expand-cgroup.c +++ b/tools/perf/tests/expand-cgroup.c @@ -187,8 +187,7 @@ static int expand_metric_events(void) rblist__init(&metric_events); pme_test = find_core_metrics_table("testarch", "testcpu"); - ret = metricgroup__parse_groups_test(evlist, pme_test, metric_str, - false, false, &metric_events); + ret = metricgroup__parse_groups_test(evlist, pme_test, metric_str, &metric_events); if (ret < 0) { pr_debug("failed to parse '%s' metric\n", metric_str); goto out; diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 9fec6040950c..132c9b945a42 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -98,7 +98,6 @@ static int __compute_metric(const char *name, struct value *vals, /* Parse the metric into metric_events list. */ pme_test = find_core_metrics_table("testarch", "testcpu"); err = metricgroup__parse_groups_test(evlist, pme_test, name, - false, false, &metric_events); if (err) goto out; diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index db2fed0c6993..50b99a0f8f59 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -846,9 +846,7 @@ static int test__parsing_callback(const struct pmu_metric *pm, perf_evlist__set_maps(&evlist->core, cpus, NULL); runtime_stat__init(&st); - err = metricgroup__parse_groups_test(evlist, table, pm->metric_name, - false, false, - &metric_events); + err = metricgroup__parse_groups_test(evlist, table, pm->metric_name, &metric_events); if (err) { if (!strcmp(pm->metric_name, "M1") || !strcmp(pm->metric_name, "M2") || !strcmp(pm->metric_name, "M3")) { diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index d83885697125..afb6f2fdc24e 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -771,6 +771,7 @@ struct metricgroup_add_iter_data { int *ret; bool *has_match; bool metric_no_group; + bool metric_no_threshold; const char *user_requested_cpu_list; bool system_wide; struct metric *root_metric; @@ -786,6 +787,7 @@ static int add_metric(struct list_head *metric_list, const struct pmu_metric *pm, const char *modifier, bool metric_no_group, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct metric *root_metric, @@ -813,6 +815,7 @@ static int add_metric(struct list_head *metric_list, static int resolve_metric(struct list_head *metric_list, const char *modifier, bool metric_no_group, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct metric *root_metric, @@ -861,8 +864,8 @@ static int resolve_metric(struct list_head *metric_list, */ for (i = 0; i < pending_cnt; i++) { ret = add_metric(metric_list, &pending[i].pm, modifier, metric_no_group, - user_requested_cpu_list, system_wide, root_metric, visited, - table); + metric_no_threshold, user_requested_cpu_list, system_wide, + root_metric, visited, table); if (ret) break; } @@ -879,6 +882,7 @@ static int resolve_metric(struct list_head *metric_list, * @metric_no_group: Should events written to events be grouped "{}" or * global. Grouping is the default but due to multiplexing the * user may override. + * @metric_no_threshold: Should threshold expressions be ignored? * @runtime: A special argument for the parser only known at runtime. * @user_requested_cpu_list: Command line specified CPUs to record on. * @system_wide: Are events for all processes recorded. @@ -894,6 +898,7 @@ static int __add_metric(struct list_head *metric_list, const struct pmu_metric *pm, const char *modifier, bool metric_no_group, + bool metric_no_threshold, int runtime, const char *user_requested_cpu_list, bool system_wide, @@ -974,10 +979,12 @@ static int __add_metric(struct list_head *metric_list, * Threshold expressions are built off the actual metric. Switch * to use that in case of additional necessary events. Change * the visited node name to avoid this being flagged as - * recursion. + * recursion. If the threshold events are disabled, just use the + * metric's name as a reference. This allows metric threshold + * computation if there are sufficient events. */ assert(strstr(pm->metric_threshold, pm->metric_name)); - expr = pm->metric_threshold; + expr = metric_no_threshold ? pm->metric_name : pm->metric_threshold; visited_node.name = "__threshold__"; } if (expr__find_ids(expr, NULL, root_metric->pctx) < 0) { @@ -987,8 +994,8 @@ static int __add_metric(struct list_head *metric_list, if (!ret) { /* Resolve referenced metrics. */ ret = resolve_metric(metric_list, modifier, metric_no_group, - user_requested_cpu_list, system_wide, - root_metric, &visited_node, table); + metric_no_threshold, user_requested_cpu_list, + system_wide, root_metric, &visited_node, table); } if (ret) { if (is_root) @@ -1035,6 +1042,7 @@ static int add_metric(struct list_head *metric_list, const struct pmu_metric *pm, const char *modifier, bool metric_no_group, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct metric *root_metric, @@ -1046,9 +1054,9 @@ static int add_metric(struct list_head *metric_list, pr_debug("metric expr %s for %s\n", pm->metric_expr, pm->metric_name); if (!strstr(pm->metric_expr, "?")) { - ret = __add_metric(metric_list, pm, modifier, metric_no_group, 0, - user_requested_cpu_list, system_wide, root_metric, - visited, table); + ret = __add_metric(metric_list, pm, modifier, metric_no_group, + metric_no_threshold, 0, user_requested_cpu_list, + system_wide, root_metric, visited, table); } else { int j, count; @@ -1060,9 +1068,9 @@ static int add_metric(struct list_head *metric_list, */ for (j = 0; j < count && !ret; j++) - ret = __add_metric(metric_list, pm, modifier, metric_no_group, j, - user_requested_cpu_list, system_wide, - root_metric, visited, table); + ret = __add_metric(metric_list, pm, modifier, metric_no_group, + metric_no_threshold, j, user_requested_cpu_list, + system_wide, root_metric, visited, table); } return ret; @@ -1079,8 +1087,8 @@ static int metricgroup__add_metric_sys_event_iter(const struct pmu_metric *pm, return 0; ret = add_metric(d->metric_list, pm, d->modifier, d->metric_no_group, - d->user_requested_cpu_list, d->system_wide, - d->root_metric, d->visited, d->table); + d->metric_no_threshold, d->user_requested_cpu_list, + d->system_wide, d->root_metric, d->visited, d->table); if (ret) goto out; @@ -1124,6 +1132,7 @@ struct metricgroup__add_metric_data { const char *modifier; const char *user_requested_cpu_list; bool metric_no_group; + bool metric_no_threshold; bool system_wide; bool has_match; }; @@ -1141,8 +1150,9 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, data->has_match = true; ret = add_metric(data->list, pm, data->modifier, data->metric_no_group, - data->user_requested_cpu_list, data->system_wide, - /*root_metric=*/NULL, /*visited_metrics=*/NULL, table); + data->metric_no_threshold, data->user_requested_cpu_list, + data->system_wide, /*root_metric=*/NULL, + /*visited_metrics=*/NULL, table); } return ret; } @@ -1163,7 +1173,7 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, * architecture perf is running upon. */ static int metricgroup__add_metric(const char *metric_name, const char *modifier, - bool metric_no_group, + bool metric_no_group, bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct list_head *metric_list, @@ -1179,6 +1189,7 @@ static int metricgroup__add_metric(const char *metric_name, const char *modifier .metric_name = metric_name, .modifier = modifier, .metric_no_group = metric_no_group, + .metric_no_threshold = metric_no_threshold, .user_requested_cpu_list = user_requested_cpu_list, .system_wide = system_wide, .has_match = false, @@ -1241,6 +1252,7 @@ out: * architecture perf is running upon. */ static int metricgroup__add_metric_list(const char *list, bool metric_no_group, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct list_head *metric_list, const struct pmu_metrics_table *table) @@ -1259,7 +1271,8 @@ static int metricgroup__add_metric_list(const char *list, bool metric_no_group, *modifier++ = '\0'; ret = metricgroup__add_metric(metric_name, modifier, - metric_no_group, user_requested_cpu_list, + metric_no_group, metric_no_threshold, + user_requested_cpu_list, system_wide, metric_list, table); if (ret == -EINVAL) pr_err("Cannot find metric or group `%s'\n", metric_name); @@ -1449,6 +1462,7 @@ err_out: static int parse_groups(struct evlist *perf_evlist, const char *str, bool metric_no_group, bool metric_no_merge, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct perf_pmu *fake_pmu, @@ -1463,7 +1477,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str, if (metric_events_list->nr_entries == 0) metricgroup__rblist_init(metric_events_list); - ret = metricgroup__add_metric_list(str, metric_no_group, + ret = metricgroup__add_metric_list(str, metric_no_group, metric_no_threshold, user_requested_cpu_list, system_wide, &metric_list, table); if (ret) @@ -1598,6 +1612,7 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, const char *str, bool metric_no_group, bool metric_no_merge, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct rblist *metric_events) @@ -1608,18 +1623,19 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, return -EINVAL; return parse_groups(perf_evlist, str, metric_no_group, metric_no_merge, - user_requested_cpu_list, system_wide, + metric_no_threshold, user_requested_cpu_list, system_wide, /*fake_pmu=*/NULL, metric_events, table); } int metricgroup__parse_groups_test(struct evlist *evlist, const struct pmu_metrics_table *table, const char *str, - bool metric_no_group, - bool metric_no_merge, struct rblist *metric_events) { - return parse_groups(evlist, str, metric_no_group, metric_no_merge, + return parse_groups(evlist, str, + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/false, /*user_requested_cpu_list=*/NULL, /*system_wide=*/false, &perf_pmu__fake, metric_events, table); diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 32eb3a5381fb..8d50052c5b4c 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -70,14 +70,13 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, const char *str, bool metric_no_group, bool metric_no_merge, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct rblist *metric_events); int metricgroup__parse_groups_test(struct evlist *evlist, const struct pmu_metrics_table *table, const char *str, - bool metric_no_group, - bool metric_no_merge, struct rblist *metric_events); void metricgroup__print(const struct print_callbacks *print_cb, void *print_state); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index a41f186c6ec8..77483eeda0d8 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -814,7 +814,8 @@ static void generic_metric(struct perf_stat_config *config, char metric_bf[64]; if (metric_threshold && - expr__parse(&threshold, pctx, metric_threshold) == 0) { + expr__parse(&threshold, pctx, metric_threshold) == 0 && + !isnan(threshold)) { color = fpclassify(threshold) == FP_ZERO ? PERF_COLOR_GREEN : PERF_COLOR_RED; } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index b1c29156c560..cf2d8aa445f3 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -159,6 +159,7 @@ struct perf_stat_config { bool no_csv_summary; bool metric_no_group; bool metric_no_merge; + bool metric_no_threshold; bool stop_read_counter; bool iostat_run; char *user_requested_cpu_list; -- cgit v1.2.3-70-g09d2 From 7b86475f02ac7d198fc52cfa780f8b93b17321ad Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:38 -0800 Subject: perf stat: Remove topdown event special handling Now the events are computed from json metrics, the hard coded logic can be removed. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-42-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-shadow.c | 346 ------------------------------------------ tools/perf/util/stat.c | 13 -- tools/perf/util/stat.h | 26 ---- 3 files changed, 385 deletions(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 77483eeda0d8..5189756bf16d 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -241,45 +241,6 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, update_runtime_stat(st, STAT_TRANSACTION, map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, ELISION_START)) update_runtime_stat(st, STAT_ELISION, map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS)) - update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED)) - update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED)) - update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES)) - update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES)) - update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING)) - update_runtime_stat(st, STAT_TOPDOWN_RETIRING, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC)) - update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND)) - update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND)) - update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_HEAVY_OPS)) - update_runtime_stat(st, STAT_TOPDOWN_HEAVY_OPS, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_BR_MISPREDICT)) - update_runtime_stat(st, STAT_TOPDOWN_BR_MISPREDICT, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_LAT)) - update_runtime_stat(st, STAT_TOPDOWN_FETCH_LAT, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_MEM_BOUND)) - update_runtime_stat(st, STAT_TOPDOWN_MEM_BOUND, - map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT, map_idx, count, &rsd); @@ -524,156 +485,6 @@ static void print_ll_cache_misses(struct perf_stat_config *config, out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache accesses", ratio); } -/* - * High level "TopDown" CPU core pipe line bottleneck break down. - * - * Basic concept following - * Yasin, A Top Down Method for Performance analysis and Counter architecture - * ISPASS14 - * - * The CPU pipeline is divided into 4 areas that can be bottlenecks: - * - * Frontend -> Backend -> Retiring - * BadSpeculation in addition means out of order execution that is thrown away - * (for example branch mispredictions) - * Frontend is instruction decoding. - * Backend is execution, like computation and accessing data in memory - * Retiring is good execution that is not directly bottlenecked - * - * The formulas are computed in slots. - * A slot is an entry in the pipeline each for the pipeline width - * (for example a 4-wide pipeline has 4 slots for each cycle) - * - * Formulas: - * BadSpeculation = ((SlotsIssued - SlotsRetired) + RecoveryBubbles) / - * TotalSlots - * Retiring = SlotsRetired / TotalSlots - * FrontendBound = FetchBubbles / TotalSlots - * BackendBound = 1.0 - BadSpeculation - Retiring - FrontendBound - * - * The kernel provides the mapping to the low level CPU events and any scaling - * needed for the CPU pipeline width, for example: - * - * TotalSlots = Cycles * 4 - * - * The scaling factor is communicated in the sysfs unit. - * - * In some cases the CPU may not be able to measure all the formulas due to - * missing events. In this case multiple formulas are combined, as possible. - * - * Full TopDown supports more levels to sub-divide each area: for example - * BackendBound into computing bound and memory bound. For now we only - * support Level 1 TopDown. - */ - -static double sanitize_val(double x) -{ - if (x < 0 && x >= -0.02) - return 0.0; - return x; -} - -static double td_total_slots(int map_idx, struct runtime_stat *st, - struct runtime_stat_data *rsd) -{ - return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, map_idx, rsd); -} - -static double td_bad_spec(int map_idx, struct runtime_stat *st, - struct runtime_stat_data *rsd) -{ - double bad_spec = 0; - double total_slots; - double total; - - total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, map_idx, rsd) - - runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, map_idx, rsd) + - runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, map_idx, rsd); - - total_slots = td_total_slots(map_idx, st, rsd); - if (total_slots) - bad_spec = total / total_slots; - return sanitize_val(bad_spec); -} - -static double td_retiring(int map_idx, struct runtime_stat *st, - struct runtime_stat_data *rsd) -{ - double retiring = 0; - double total_slots = td_total_slots(map_idx, st, rsd); - double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, - map_idx, rsd); - - if (total_slots) - retiring = ret_slots / total_slots; - return retiring; -} - -static double td_fe_bound(int map_idx, struct runtime_stat *st, - struct runtime_stat_data *rsd) -{ - double fe_bound = 0; - double total_slots = td_total_slots(map_idx, st, rsd); - double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES, - map_idx, rsd); - - if (total_slots) - fe_bound = fetch_bub / total_slots; - return fe_bound; -} - -static double td_be_bound(int map_idx, struct runtime_stat *st, - struct runtime_stat_data *rsd) -{ - double sum = (td_fe_bound(map_idx, st, rsd) + - td_bad_spec(map_idx, st, rsd) + - td_retiring(map_idx, st, rsd)); - if (sum == 0) - return 0; - return sanitize_val(1.0 - sum); -} - -/* - * Kernel reports metrics multiplied with slots. To get back - * the ratios we need to recreate the sum. - */ - -static double td_metric_ratio(int map_idx, enum stat_type type, - struct runtime_stat *stat, - struct runtime_stat_data *rsd) -{ - double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, map_idx, rsd) + - runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, map_idx, rsd) + - runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, map_idx, rsd) + - runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, map_idx, rsd); - double d = runtime_stat_avg(stat, type, map_idx, rsd); - - if (sum) - return d / sum; - return 0; -} - -/* - * ... but only if most of the values are actually available. - * We allow two missing. - */ - -static bool full_td(int map_idx, struct runtime_stat *stat, - struct runtime_stat_data *rsd) -{ - int c = 0; - - if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, map_idx, rsd) > 0) - c++; - if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, map_idx, rsd) > 0) - c++; - if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, map_idx, rsd) > 0) - c++; - if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, map_idx, rsd) > 0) - c++; - return c >= 2; -} - static void print_smi_cost(struct perf_stat_config *config, int map_idx, struct perf_stat_output_ctx *out, struct runtime_stat *st, @@ -885,7 +696,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, void *ctxp = out->ctx; print_metric_t print_metric = out->print_metric; double total, ratio = 0.0, total2; - const char *color = NULL; struct runtime_stat_data rsd = { .ctx = evsel_context(evsel), .cgrp = evsel->cgrp, @@ -1044,162 +854,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, avg / (ratio * evsel->scale)); else print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) { - double fe_bound = td_fe_bound(map_idx, st, &rsd); - - if (fe_bound > 0.2) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "frontend bound", - fe_bound * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) { - double retiring = td_retiring(map_idx, st, &rsd); - - if (retiring > 0.7) - color = PERF_COLOR_GREEN; - print_metric(config, ctxp, color, "%8.1f%%", "retiring", - retiring * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) { - double bad_spec = td_bad_spec(map_idx, st, &rsd); - - if (bad_spec > 0.1) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "bad speculation", - bad_spec * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) { - double be_bound = td_be_bound(map_idx, st, &rsd); - const char *name = "backend bound"; - static int have_recovery_bubbles = -1; - - /* In case the CPU does not support topdown-recovery-bubbles */ - if (have_recovery_bubbles < 0) - have_recovery_bubbles = pmu_have_event("cpu", - "topdown-recovery-bubbles"); - if (!have_recovery_bubbles) - name = "backend bound/bad spec"; - - if (be_bound > 0.2) - color = PERF_COLOR_RED; - if (td_total_slots(map_idx, st, &rsd) > 0) - print_metric(config, ctxp, color, "%8.1f%%", name, - be_bound * 100.); - else - print_metric(config, ctxp, NULL, NULL, name, 0); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) && - full_td(map_idx, st, &rsd)) { - double retiring = td_metric_ratio(map_idx, - STAT_TOPDOWN_RETIRING, st, - &rsd); - if (retiring > 0.7) - color = PERF_COLOR_GREEN; - print_metric(config, ctxp, color, "%8.1f%%", "Retiring", - retiring * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) && - full_td(map_idx, st, &rsd)) { - double fe_bound = td_metric_ratio(map_idx, - STAT_TOPDOWN_FE_BOUND, st, - &rsd); - if (fe_bound > 0.2) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "Frontend Bound", - fe_bound * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) && - full_td(map_idx, st, &rsd)) { - double be_bound = td_metric_ratio(map_idx, - STAT_TOPDOWN_BE_BOUND, st, - &rsd); - if (be_bound > 0.2) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "Backend Bound", - be_bound * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) && - full_td(map_idx, st, &rsd)) { - double bad_spec = td_metric_ratio(map_idx, - STAT_TOPDOWN_BAD_SPEC, st, - &rsd); - if (bad_spec > 0.1) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "Bad Speculation", - bad_spec * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) && - full_td(map_idx, st, &rsd) && (config->topdown_level > 1)) { - double retiring = td_metric_ratio(map_idx, - STAT_TOPDOWN_RETIRING, st, - &rsd); - double heavy_ops = td_metric_ratio(map_idx, - STAT_TOPDOWN_HEAVY_OPS, st, - &rsd); - double light_ops = retiring - heavy_ops; - - if (retiring > 0.7 && heavy_ops > 0.1) - color = PERF_COLOR_GREEN; - print_metric(config, ctxp, color, "%8.1f%%", "Heavy Operations", - heavy_ops * 100.); - if (retiring > 0.7 && light_ops > 0.6) - color = PERF_COLOR_GREEN; - else - color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "Light Operations", - light_ops * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) && - full_td(map_idx, st, &rsd) && (config->topdown_level > 1)) { - double bad_spec = td_metric_ratio(map_idx, - STAT_TOPDOWN_BAD_SPEC, st, - &rsd); - double br_mis = td_metric_ratio(map_idx, - STAT_TOPDOWN_BR_MISPREDICT, st, - &rsd); - double m_clears = bad_spec - br_mis; - - if (bad_spec > 0.1 && br_mis > 0.05) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "Branch Mispredict", - br_mis * 100.); - if (bad_spec > 0.1 && m_clears > 0.05) - color = PERF_COLOR_RED; - else - color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "Machine Clears", - m_clears * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) && - full_td(map_idx, st, &rsd) && (config->topdown_level > 1)) { - double fe_bound = td_metric_ratio(map_idx, - STAT_TOPDOWN_FE_BOUND, st, - &rsd); - double fetch_lat = td_metric_ratio(map_idx, - STAT_TOPDOWN_FETCH_LAT, st, - &rsd); - double fetch_bw = fe_bound - fetch_lat; - - if (fe_bound > 0.2 && fetch_lat > 0.15) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "Fetch Latency", - fetch_lat * 100.); - if (fe_bound > 0.2 && fetch_bw > 0.1) - color = PERF_COLOR_RED; - else - color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "Fetch Bandwidth", - fetch_bw * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) && - full_td(map_idx, st, &rsd) && (config->topdown_level > 1)) { - double be_bound = td_metric_ratio(map_idx, - STAT_TOPDOWN_BE_BOUND, st, - &rsd); - double mem_bound = td_metric_ratio(map_idx, - STAT_TOPDOWN_MEM_BOUND, st, - &rsd); - double core_bound = be_bound - mem_bound; - - if (be_bound > 0.2 && mem_bound > 0.2) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "Memory Bound", - mem_bound * 100.); - if (be_bound > 0.2 && core_bound > 0.1) - color = PERF_COLOR_RED; - else - color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "Core Bound", - core_bound * 100.); } else if (runtime_stat_n(st, STAT_NSECS, map_idx, &rsd) != 0) { char unit = ' '; char unit_buf[10] = "/sec"; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 534d36d26fc3..0b8c91ca13cd 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -91,19 +91,6 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { ID(TRANSACTION_START, cpu/tx-start/), ID(ELISION_START, cpu/el-start/), ID(CYCLES_IN_TX_CP, cpu/cycles-ct/), - ID(TOPDOWN_TOTAL_SLOTS, topdown-total-slots), - ID(TOPDOWN_SLOTS_ISSUED, topdown-slots-issued), - ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired), - ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles), - ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles), - ID(TOPDOWN_RETIRING, topdown-retiring), - ID(TOPDOWN_BAD_SPEC, topdown-bad-spec), - ID(TOPDOWN_FE_BOUND, topdown-fe-bound), - ID(TOPDOWN_BE_BOUND, topdown-be-bound), - ID(TOPDOWN_HEAVY_OPS, topdown-heavy-ops), - ID(TOPDOWN_BR_MISPREDICT, topdown-br-mispredict), - ID(TOPDOWN_FETCH_LAT, topdown-fetch-lat), - ID(TOPDOWN_MEM_BOUND, topdown-mem-bound), ID(SMI_NUM, msr/smi/), ID(APERF, msr/aperf/), }; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index cf2d8aa445f3..42af350a96d9 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -25,19 +25,6 @@ enum perf_stat_evsel_id { PERF_STAT_EVSEL_ID__TRANSACTION_START, PERF_STAT_EVSEL_ID__ELISION_START, PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP, - PERF_STAT_EVSEL_ID__TOPDOWN_TOTAL_SLOTS, - PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_ISSUED, - PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED, - PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES, - PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES, - PERF_STAT_EVSEL_ID__TOPDOWN_RETIRING, - PERF_STAT_EVSEL_ID__TOPDOWN_BAD_SPEC, - PERF_STAT_EVSEL_ID__TOPDOWN_FE_BOUND, - PERF_STAT_EVSEL_ID__TOPDOWN_BE_BOUND, - PERF_STAT_EVSEL_ID__TOPDOWN_HEAVY_OPS, - PERF_STAT_EVSEL_ID__TOPDOWN_BR_MISPREDICT, - PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_LAT, - PERF_STAT_EVSEL_ID__TOPDOWN_MEM_BOUND, PERF_STAT_EVSEL_ID__SMI_NUM, PERF_STAT_EVSEL_ID__APERF, PERF_STAT_EVSEL_ID__MAX, @@ -108,19 +95,6 @@ enum stat_type { STAT_CYCLES_IN_TX, STAT_TRANSACTION, STAT_ELISION, - STAT_TOPDOWN_TOTAL_SLOTS, - STAT_TOPDOWN_SLOTS_ISSUED, - STAT_TOPDOWN_SLOTS_RETIRED, - STAT_TOPDOWN_FETCH_BUBBLES, - STAT_TOPDOWN_RECOVERY_BUBBLES, - STAT_TOPDOWN_RETIRING, - STAT_TOPDOWN_BAD_SPEC, - STAT_TOPDOWN_FE_BOUND, - STAT_TOPDOWN_BE_BOUND, - STAT_TOPDOWN_HEAVY_OPS, - STAT_TOPDOWN_BR_MISPREDICT, - STAT_TOPDOWN_FETCH_LAT, - STAT_TOPDOWN_MEM_BOUND, STAT_SMI_NUM, STAT_APERF, STAT_MAX -- cgit v1.2.3-70-g09d2 From d6964c5b1f76518e425f9aef05670a0933903207 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:40 -0800 Subject: perf stat: Remove hard coded transaction events The metric group "transaction" is now present for Intel architectures so the legacy hard coded approach won't be used. Remove the associated logic. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-44-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 59 ++++++++----------------------------------- tools/perf/util/stat-shadow.c | 48 +---------------------------------- tools/perf/util/stat.c | 4 --- tools/perf/util/stat.h | 7 ----- 4 files changed, 11 insertions(+), 107 deletions(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index bdb1ef4fc6ad..e6b60b058257 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -100,30 +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 *smi_cost_attrs = { "{" "msr/aperf/," @@ -1811,37 +1787,22 @@ 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.metric_no_threshold, - 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) { diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 5189756bf16d..3cfe4b4eb3de 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -235,12 +235,6 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, update_runtime_stat(st, STAT_NSECS, map_idx, count_ns, &rsd); else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) update_runtime_stat(st, STAT_CYCLES, map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, CYCLES_IN_TX)) - update_runtime_stat(st, STAT_CYCLES_IN_TX, map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TRANSACTION_START)) - update_runtime_stat(st, STAT_TRANSACTION, map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, ELISION_START)) - update_runtime_stat(st, STAT_ELISION, map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT, map_idx, count, &rsd); @@ -695,7 +689,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, { void *ctxp = out->ctx; print_metric_t print_metric = out->print_metric; - double total, ratio = 0.0, total2; + double total, ratio = 0.0; struct runtime_stat_data rsd = { .ctx = evsel_context(evsel), .cgrp = evsel->cgrp, @@ -808,46 +802,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, } else { print_metric(config, ctxp, NULL, NULL, "Ghz", 0); } - } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) { - total = runtime_stat_avg(st, STAT_CYCLES, map_idx, &rsd); - - if (total) - print_metric(config, ctxp, NULL, - "%7.2f%%", "transactional cycles", - 100.0 * (avg / total)); - else - print_metric(config, ctxp, NULL, NULL, "transactional cycles", - 0); - } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) { - total = runtime_stat_avg(st, STAT_CYCLES, map_idx, &rsd); - total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, map_idx, &rsd); - - if (total2 < avg) - total2 = avg; - if (total) - print_metric(config, ctxp, NULL, "%7.2f%%", "aborted cycles", - 100.0 * ((total2-avg) / total)); - else - print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0); - } else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) { - total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, map_idx, &rsd); - - if (avg) - ratio = total / avg; - - if (runtime_stat_n(st, STAT_CYCLES_IN_TX, map_idx, &rsd) != 0) - print_metric(config, ctxp, NULL, "%8.0f", - "cycles / transaction", ratio); - else - print_metric(config, ctxp, NULL, NULL, "cycles / transaction", - 0); - } else if (perf_stat_evsel__is(evsel, ELISION_START)) { - total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, map_idx, &rsd); - - if (avg) - ratio = total / avg; - - print_metric(config, ctxp, NULL, "%8.0f", "cycles / elision", ratio); } else if (evsel__is_clock(evsel)) { if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0) print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized", diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 0b8c91ca13cd..b5b18d457254 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -87,10 +87,6 @@ bool __perf_stat_evsel__is(struct evsel *evsel, enum perf_stat_evsel_id id) #define ID(id, name) [PERF_STAT_EVSEL_ID__##id] = #name static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { ID(NONE, x), - ID(CYCLES_IN_TX, cpu/cycles-t/), - ID(TRANSACTION_START, cpu/tx-start/), - ID(ELISION_START, cpu/el-start/), - ID(CYCLES_IN_TX_CP, cpu/cycles-ct/), ID(SMI_NUM, msr/smi/), ID(APERF, msr/aperf/), }; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 42af350a96d9..c5fe847dd344 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -21,10 +21,6 @@ struct stats { enum perf_stat_evsel_id { PERF_STAT_EVSEL_ID__NONE = 0, - PERF_STAT_EVSEL_ID__CYCLES_IN_TX, - PERF_STAT_EVSEL_ID__TRANSACTION_START, - PERF_STAT_EVSEL_ID__ELISION_START, - PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP, PERF_STAT_EVSEL_ID__SMI_NUM, PERF_STAT_EVSEL_ID__APERF, PERF_STAT_EVSEL_ID__MAX, @@ -92,9 +88,6 @@ enum stat_type { STAT_LL_CACHE, STAT_ITLB_CACHE, STAT_DTLB_CACHE, - STAT_CYCLES_IN_TX, - STAT_TRANSACTION, - STAT_ELISION, STAT_SMI_NUM, STAT_APERF, STAT_MAX -- cgit v1.2.3-70-g09d2 From c23f5cc06ac5dc556fccd2c9ac648fa84fb876fd Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:41 -0800 Subject: perf stat: Use metrics for --smi-cost Rather than parsing events for --smi-cost, use the json metric group 'smi'. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-45-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 34 +++++++++++----------------------- tools/perf/util/stat-shadow.c | 30 ------------------------------ tools/perf/util/stat.c | 2 -- tools/perf/util/stat.h | 4 ---- 4 files changed, 11 insertions(+), 59 deletions(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index e6b60b058257..9c1fbf154ee3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -100,14 +100,6 @@ static void print_counters(struct timespec *ts, int argc, const char **argv); -static const char *smi_cost_attrs = { - "{" - "msr/aperf/," - "msr/smi/," - "cycles" - "}" -}; - static struct evlist *evsel_list; static bool all_counters_use_bpf = true; @@ -1666,7 +1658,6 @@ 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 }, @@ -1806,11 +1797,10 @@ static int add_default_attributes(void) } 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; } @@ -1822,23 +1812,21 @@ 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) { diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 3cfe4b4eb3de..d14fa531ee27 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -255,10 +255,6 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, update_runtime_stat(st, STAT_DTLB_CACHE, map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) update_runtime_stat(st, STAT_ITLB_CACHE, map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, SMI_NUM)) - update_runtime_stat(st, STAT_SMI_NUM, map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, APERF)) - update_runtime_stat(st, STAT_APERF, map_idx, count, &rsd); if (counter->collect_stat) { v = saved_value_lookup(counter, map_idx, true, STAT_NONE, 0, st, @@ -479,30 +475,6 @@ static void print_ll_cache_misses(struct perf_stat_config *config, out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache accesses", ratio); } -static void print_smi_cost(struct perf_stat_config *config, int map_idx, - struct perf_stat_output_ctx *out, - struct runtime_stat *st, - struct runtime_stat_data *rsd) -{ - double smi_num, aperf, cycles, cost = 0.0; - const char *color = NULL; - - smi_num = runtime_stat_avg(st, STAT_SMI_NUM, map_idx, rsd); - aperf = runtime_stat_avg(st, STAT_APERF, map_idx, rsd); - cycles = runtime_stat_avg(st, STAT_CYCLES, map_idx, rsd); - - if ((cycles == 0) || (aperf == 0)) - return; - - if (smi_num) - cost = (aperf - cycles) / aperf * 100.00; - - if (cost > 10) - color = PERF_COLOR_RED; - out->print_metric(config, out->ctx, color, "%8.1f%%", "SMI cycles%", cost); - out->print_metric(config, out->ctx, NULL, "%4.0f", "SMI#", smi_num); -} - static int prepare_metric(struct evsel **metric_events, struct metric_ref *metric_refs, struct expr_parse_ctx *pctx, @@ -819,8 +791,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (unit != ' ') snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio); - } else if (perf_stat_evsel__is(evsel, SMI_NUM)) { - print_smi_cost(config, map_idx, out, st, &rsd); } else { num = 0; } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index b5b18d457254..d51d7457f12d 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -87,8 +87,6 @@ bool __perf_stat_evsel__is(struct evsel *evsel, enum perf_stat_evsel_id id) #define ID(id, name) [PERF_STAT_EVSEL_ID__##id] = #name static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { ID(NONE, x), - ID(SMI_NUM, msr/smi/), - ID(APERF, msr/aperf/), }; #undef ID diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index c5fe847dd344..9af4af3bc3f2 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -21,8 +21,6 @@ struct stats { enum perf_stat_evsel_id { PERF_STAT_EVSEL_ID__NONE = 0, - PERF_STAT_EVSEL_ID__SMI_NUM, - PERF_STAT_EVSEL_ID__APERF, PERF_STAT_EVSEL_ID__MAX, }; @@ -88,8 +86,6 @@ enum stat_type { STAT_LL_CACHE, STAT_ITLB_CACHE, STAT_DTLB_CACHE, - STAT_SMI_NUM, - STAT_APERF, STAT_MAX }; -- cgit v1.2.3-70-g09d2 From 758bc8e626b76b53ac643dae4128d6f617e24467 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:43 -0800 Subject: perf stat: Move enums from header The enums are only used in stat-shadow.c, so narrow their scope by moving to the C file. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-47-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-shadow.c | 25 +++++++++++++++++++++++++ tools/perf/util/stat.h | 27 --------------------------- 2 files changed, 25 insertions(+), 27 deletions(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index d14fa531ee27..fc948a7e83b7 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -29,6 +29,31 @@ struct runtime_stat rt_stat; struct stats walltime_nsecs_stats; struct rusage_stats ru_stats; +enum { + CTX_BIT_USER = 1 << 0, + CTX_BIT_KERNEL = 1 << 1, + CTX_BIT_HV = 1 << 2, + CTX_BIT_HOST = 1 << 3, + CTX_BIT_IDLE = 1 << 4, + CTX_BIT_MAX = 1 << 5, +}; + +enum stat_type { + STAT_NONE = 0, + STAT_NSECS, + STAT_CYCLES, + STAT_STALLED_CYCLES_FRONT, + STAT_STALLED_CYCLES_BACK, + STAT_BRANCHES, + STAT_CACHEREFS, + STAT_L1_DCACHE, + STAT_L1_ICACHE, + STAT_LL_CACHE, + STAT_ITLB_CACHE, + STAT_DTLB_CACHE, + STAT_MAX +}; + struct saved_value { struct rb_node rb_node; struct evsel *evsel; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index df6068a3f7bb..215c0f5c4db7 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -55,33 +55,6 @@ enum aggr_mode { AGGR_MAX }; -enum { - CTX_BIT_USER = 1 << 0, - CTX_BIT_KERNEL = 1 << 1, - CTX_BIT_HV = 1 << 2, - CTX_BIT_HOST = 1 << 3, - CTX_BIT_IDLE = 1 << 4, - CTX_BIT_MAX = 1 << 5, -}; - -#define NUM_CTX CTX_BIT_MAX - -enum stat_type { - STAT_NONE = 0, - STAT_NSECS, - STAT_CYCLES, - STAT_STALLED_CYCLES_FRONT, - STAT_STALLED_CYCLES_BACK, - STAT_BRANCHES, - STAT_CACHEREFS, - STAT_L1_DCACHE, - STAT_L1_ICACHE, - STAT_LL_CACHE, - STAT_ITLB_CACHE, - STAT_DTLB_CACHE, - STAT_MAX -}; - struct runtime_stat { struct rblist value_list; }; -- cgit v1.2.3-70-g09d2 From cc26ffaa01f04cbe5c958df5532f3c23599e7a04 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:44 -0800 Subject: perf stat: Hide runtime_stat runtime_stat is only shared for the sake of tests that don't care about its value. Move the definition into stat-shadow.c and have the tests also use the global version. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-48-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 6 +- tools/perf/builtin-stat.c | 4 +- tools/perf/tests/parse-metric.c | 19 ++--- tools/perf/tests/pmu-events.c | 8 +- tools/perf/util/stat-display.c | 5 +- tools/perf/util/stat-shadow.c | 165 +++++++++++++++++----------------------- tools/perf/util/stat.c | 2 +- tools/perf/util/stat.h | 17 +---- 8 files changed, 90 insertions(+), 136 deletions(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index a792214d1af8..e9b5387161df 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2074,8 +2074,7 @@ static void perf_sample__fprint_metric(struct perf_script *script, val = sample->period * evsel->scale; perf_stat__update_shadow_stats(evsel, val, - sample->cpu, - &rt_stat); + sample->cpu); evsel_script(evsel)->val = val; if (evsel_script(leader)->gnum == leader->core.nr_members) { for_each_group_member (ev2, leader) { @@ -2083,8 +2082,7 @@ static void perf_sample__fprint_metric(struct perf_script *script, evsel_script(ev2)->val, sample->cpu, &ctx, - NULL, - &rt_stat); + NULL); } evsel_script(leader)->gnum = 0; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 9c1fbf154ee3..619387459914 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -434,7 +434,7 @@ static void process_interval(void) clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); - perf_stat__reset_shadow_per_stat(&rt_stat); + perf_stat__reset_shadow_per_stat(); evlist__reset_aggr_stats(evsel_list); if (read_counters(&rs) == 0) @@ -910,7 +910,7 @@ 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); + perf_stat__reset_shadow_per_stat(); } else { update_stats(&walltime_nsecs_stats, t1 - t0); update_rusage_stats(&ru_stats, &stat_config.ru_data); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 132c9b945a42..37e3371d978e 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -30,8 +30,7 @@ static u64 find_value(const char *name, struct value *values) return 0; } -static void load_runtime_stat(struct runtime_stat *st, struct evlist *evlist, - struct value *vals) +static void load_runtime_stat(struct evlist *evlist, struct value *vals) { struct evsel *evsel; u64 count; @@ -39,14 +38,14 @@ static void load_runtime_stat(struct runtime_stat *st, struct evlist *evlist, perf_stat__reset_shadow_stats(); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); - perf_stat__update_shadow_stats(evsel, count, 0, st); + perf_stat__update_shadow_stats(evsel, count, 0); if (!strcmp(evsel->name, "duration_time")) update_stats(&walltime_nsecs_stats, count); } } static double compute_single(struct rblist *metric_events, struct evlist *evlist, - struct runtime_stat *st, const char *name) + const char *name) { struct metric_expr *mexp; struct metric_event *me; @@ -58,7 +57,7 @@ static double compute_single(struct rblist *metric_events, struct evlist *evlist list_for_each_entry (mexp, &me->head, nd) { if (strcmp(mexp->metric_name, name)) continue; - return test_generic_metric(mexp, 0, st); + return test_generic_metric(mexp, 0); } } } @@ -74,7 +73,6 @@ static int __compute_metric(const char *name, struct value *vals, }; const struct pmu_metrics_table *pme_test; struct perf_cpu_map *cpus; - struct runtime_stat st; struct evlist *evlist; int err; @@ -93,7 +91,6 @@ static int __compute_metric(const char *name, struct value *vals, } perf_evlist__set_maps(&evlist->core, cpus, NULL); - runtime_stat__init(&st); /* Parse the metric into metric_events list. */ pme_test = find_core_metrics_table("testarch", "testcpu"); @@ -107,18 +104,17 @@ static int __compute_metric(const char *name, struct value *vals, goto out; /* Load the runtime stats with given numbers for events. */ - load_runtime_stat(&st, evlist, vals); + load_runtime_stat(evlist, vals); /* And execute the metric */ if (name1 && ratio1) - *ratio1 = compute_single(&metric_events, evlist, &st, name1); + *ratio1 = compute_single(&metric_events, evlist, name1); if (name2 && ratio2) - *ratio2 = compute_single(&metric_events, evlist, &st, name2); + *ratio2 = compute_single(&metric_events, evlist, name2); out: /* ... cleanup. */ metricgroup__rblist_exit(&metric_events); - runtime_stat__exit(&st); evlist__free_stats(evlist); perf_cpu_map__put(cpus); evlist__delete(evlist); @@ -300,6 +296,7 @@ static int test_metric_group(void) static int test__parse_metric(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { + perf_stat__init_shadow_stats(); TEST_ASSERT_VAL("IPC failed", test_ipc() == 0); TEST_ASSERT_VAL("frontend failed", test_frontend() == 0); TEST_ASSERT_VAL("DCache_L2 failed", test_dcache_l2() == 0); diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 50b99a0f8f59..122e74c282a7 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -816,7 +816,6 @@ static int test__parsing_callback(const struct pmu_metric *pm, int k; struct evlist *evlist; struct perf_cpu_map *cpus; - struct runtime_stat st; struct evsel *evsel; struct rblist metric_events = { .nr_entries = 0, @@ -844,7 +843,6 @@ static int test__parsing_callback(const struct pmu_metric *pm, } perf_evlist__set_maps(&evlist->core, cpus, NULL); - runtime_stat__init(&st); err = metricgroup__parse_groups_test(evlist, table, pm->metric_name, &metric_events); if (err) { @@ -867,7 +865,7 @@ static int test__parsing_callback(const struct pmu_metric *pm, k = 1; perf_stat__reset_shadow_stats(); evlist__for_each_entry(evlist, evsel) { - perf_stat__update_shadow_stats(evsel, k, 0, &st); + perf_stat__update_shadow_stats(evsel, k, 0); if (!strcmp(evsel->name, "duration_time")) update_stats(&walltime_nsecs_stats, k); k++; @@ -881,7 +879,7 @@ static int test__parsing_callback(const struct pmu_metric *pm, list_for_each_entry (mexp, &me->head, nd) { if (strcmp(mexp->metric_name, pm->metric_name)) continue; - pr_debug("Result %f\n", test_generic_metric(mexp, 0, &st)); + pr_debug("Result %f\n", test_generic_metric(mexp, 0)); err = 0; (*failures)--; goto out_err; @@ -896,7 +894,6 @@ out_err: /* ... cleanup. */ metricgroup__rblist_exit(&metric_events); - runtime_stat__exit(&st); evlist__free_stats(evlist); perf_cpu_map__put(cpus); evlist__delete(evlist); @@ -908,6 +905,7 @@ static int test__parsing(struct test_suite *test __maybe_unused, { int failures = 0; + perf_stat__init_shadow_stats(); pmu_for_each_core_metric(test__parsing_callback, &failures); pmu_for_each_sys_metric(test__parsing_callback, &failures); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 1b5cb20efd23..6c065d0624c3 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -729,7 +729,7 @@ static void printout(struct perf_stat_config *config, struct outstate *os, if (ok) { perf_stat__print_shadow_stats(config, counter, uval, map_idx, - &out, &config->metric_events, &rt_stat); + &out, &config->metric_events); } else { pm(config, os, /*color=*/NULL, /*format=*/NULL, /*unit=*/"", /*val=*/0); } @@ -1089,8 +1089,7 @@ static void print_metric_headers(struct perf_stat_config *config, perf_stat__print_shadow_stats(config, counter, 0, 0, &out, - &config->metric_events, - &rt_stat); + &config->metric_events); } if (!config->json_output) diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index fc948a7e83b7..f80be6abac90 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -25,10 +25,13 @@ * AGGR_THREAD: Not supported? */ -struct runtime_stat rt_stat; struct stats walltime_nsecs_stats; struct rusage_stats ru_stats; +static struct runtime_stat { + struct rblist value_list; +} rt_stat; + enum { CTX_BIT_USER = 1 << 0, CTX_BIT_KERNEL = 1 << 1, @@ -125,7 +128,6 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel, bool create, enum stat_type type, int ctx, - struct runtime_stat *st, struct cgroup *cgrp) { struct rblist *rblist; @@ -138,7 +140,7 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel, .cgrp = cgrp, }; - rblist = &st->value_list; + rblist = &rt_stat.value_list; /* don't use context info for clock events */ if (type == STAT_NSECS) @@ -156,9 +158,9 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel, return NULL; } -void runtime_stat__init(struct runtime_stat *st) +void perf_stat__init_shadow_stats(void) { - struct rblist *rblist = &st->value_list; + struct rblist *rblist = &rt_stat.value_list; rblist__init(rblist); rblist->node_cmp = saved_value_cmp; @@ -166,16 +168,6 @@ void runtime_stat__init(struct runtime_stat *st) rblist->node_delete = saved_value_delete; } -void runtime_stat__exit(struct runtime_stat *st) -{ - rblist__exit(&st->value_list); -} - -void perf_stat__init_shadow_stats(void) -{ - runtime_stat__init(&rt_stat); -} - static int evsel_context(struct evsel *evsel) { int ctx = 0; @@ -194,12 +186,12 @@ static int evsel_context(struct evsel *evsel) return ctx; } -static void reset_stat(struct runtime_stat *st) +void perf_stat__reset_shadow_per_stat(void) { struct rblist *rblist; struct rb_node *pos, *next; - rblist = &st->value_list; + rblist = &rt_stat.value_list; next = rb_first_cached(&rblist->entries); while (next) { pos = next; @@ -212,28 +204,22 @@ static void reset_stat(struct runtime_stat *st) void perf_stat__reset_shadow_stats(void) { - reset_stat(&rt_stat); + perf_stat__reset_shadow_per_stat(); memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats)); memset(&ru_stats, 0, sizeof(ru_stats)); } -void perf_stat__reset_shadow_per_stat(struct runtime_stat *st) -{ - reset_stat(st); -} - struct runtime_stat_data { int ctx; struct cgroup *cgrp; }; -static void update_runtime_stat(struct runtime_stat *st, - enum stat_type type, +static void update_runtime_stat(enum stat_type type, int map_idx, u64 count, struct runtime_stat_data *rsd) { struct saved_value *v = saved_value_lookup(NULL, map_idx, true, type, - rsd->ctx, st, rsd->cgrp); + rsd->ctx, rsd->cgrp); if (v) update_stats(&v->stats, count); @@ -245,7 +231,7 @@ static void update_runtime_stat(struct runtime_stat *st, * instruction rates, etc: */ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, - int map_idx, struct runtime_stat *st) + int map_idx) { u64 count_ns = count; struct saved_value *v; @@ -253,43 +239,42 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, .ctx = evsel_context(counter), .cgrp = counter->cgrp, }; - count *= counter->scale; if (evsel__is_clock(counter)) - update_runtime_stat(st, STAT_NSECS, map_idx, count_ns, &rsd); + update_runtime_stat(STAT_NSECS, map_idx, count_ns, &rsd); else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) - update_runtime_stat(st, STAT_CYCLES, map_idx, count, &rsd); + update_runtime_stat(STAT_CYCLES, map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) - update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT, + update_runtime_stat(STAT_STALLED_CYCLES_FRONT, map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) - update_runtime_stat(st, STAT_STALLED_CYCLES_BACK, + update_runtime_stat(STAT_STALLED_CYCLES_BACK, map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) - update_runtime_stat(st, STAT_BRANCHES, map_idx, count, &rsd); + update_runtime_stat(STAT_BRANCHES, map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_runtime_stat(st, STAT_CACHEREFS, map_idx, count, &rsd); + update_runtime_stat(STAT_CACHEREFS, map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) - update_runtime_stat(st, STAT_L1_DCACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_L1_DCACHE, map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) - update_runtime_stat(st, STAT_L1_ICACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_L1_ICACHE, map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL)) - update_runtime_stat(st, STAT_LL_CACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_LL_CACHE, map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB)) - update_runtime_stat(st, STAT_DTLB_CACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_DTLB_CACHE, map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) - update_runtime_stat(st, STAT_ITLB_CACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_ITLB_CACHE, map_idx, count, &rsd); if (counter->collect_stat) { - v = saved_value_lookup(counter, map_idx, true, STAT_NONE, 0, st, + v = saved_value_lookup(counter, map_idx, true, STAT_NONE, 0, rsd.cgrp); update_stats(&v->stats, count); if (counter->metric_leader) v->metric_total += count; } else if (counter->metric_leader && !counter->merged_stat) { v = saved_value_lookup(counter->metric_leader, - map_idx, true, STAT_NONE, 0, st, rsd.cgrp); + map_idx, true, STAT_NONE, 0, rsd.cgrp); v->metric_total += count; v->metric_other++; } @@ -322,26 +307,24 @@ static const char *get_ratio_color(enum grc_type type, double ratio) return color; } -static double runtime_stat_avg(struct runtime_stat *st, - enum stat_type type, int map_idx, +static double runtime_stat_avg(enum stat_type type, int map_idx, struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, map_idx, false, type, rsd->ctx, st, rsd->cgrp); + v = saved_value_lookup(NULL, map_idx, false, type, rsd->ctx, rsd->cgrp); if (!v) return 0.0; return avg_stats(&v->stats); } -static double runtime_stat_n(struct runtime_stat *st, - enum stat_type type, int map_idx, +static double runtime_stat_n(enum stat_type type, int map_idx, struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, map_idx, false, type, rsd->ctx, st, rsd->cgrp); + v = saved_value_lookup(NULL, map_idx, false, type, rsd->ctx, rsd->cgrp); if (!v) return 0.0; @@ -351,13 +334,12 @@ static double runtime_stat_n(struct runtime_stat *st, static void print_stalled_cycles_frontend(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_CYCLES, map_idx, rsd); + total = runtime_stat_avg(STAT_CYCLES, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -374,13 +356,12 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config, static void print_stalled_cycles_backend(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_CYCLES, map_idx, rsd); + total = runtime_stat_avg(STAT_CYCLES, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -393,13 +374,12 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config, static void print_branch_misses(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_BRANCHES, map_idx, rsd); + total = runtime_stat_avg(STAT_BRANCHES, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -412,13 +392,12 @@ static void print_branch_misses(struct perf_stat_config *config, static void print_l1_dcache_misses(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_L1_DCACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_L1_DCACHE, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -431,13 +410,12 @@ static void print_l1_dcache_misses(struct perf_stat_config *config, static void print_l1_icache_misses(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_L1_ICACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_L1_ICACHE, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -449,13 +427,12 @@ static void print_l1_icache_misses(struct perf_stat_config *config, static void print_dtlb_cache_misses(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_DTLB_CACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_DTLB_CACHE, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -467,13 +444,12 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config, static void print_itlb_cache_misses(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_ITLB_CACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_ITLB_CACHE, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -485,13 +461,12 @@ static void print_itlb_cache_misses(struct perf_stat_config *config, static void print_ll_cache_misses(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_LL_CACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_LL_CACHE, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -503,8 +478,7 @@ static void print_ll_cache_misses(struct perf_stat_config *config, static int prepare_metric(struct evsel **metric_events, struct metric_ref *metric_refs, struct expr_parse_ctx *pctx, - int map_idx, - struct runtime_stat *st) + int map_idx) { double scale; char *n; @@ -543,7 +517,7 @@ static int prepare_metric(struct evsel **metric_events, } } else { v = saved_value_lookup(metric_events[i], map_idx, false, - STAT_NONE, 0, st, + STAT_NONE, 0, metric_events[i]->cgrp); if (!v) break; @@ -587,8 +561,7 @@ static void generic_metric(struct perf_stat_config *config, const char *metric_unit, int runtime, int map_idx, - struct perf_stat_output_ctx *out, - struct runtime_stat *st) + struct perf_stat_output_ctx *out) { print_metric_t print_metric = out->print_metric; struct expr_parse_ctx *pctx; @@ -605,7 +578,7 @@ static void generic_metric(struct perf_stat_config *config, pctx->sctx.user_requested_cpu_list = strdup(config->user_requested_cpu_list); pctx->sctx.runtime = runtime; pctx->sctx.system_wide = config->system_wide; - i = prepare_metric(metric_events, metric_refs, pctx, map_idx, st); + i = prepare_metric(metric_events, metric_refs, pctx, map_idx); if (i < 0) { expr__ctx_free(pctx); return; @@ -657,7 +630,7 @@ static void generic_metric(struct perf_stat_config *config, expr__ctx_free(pctx); } -double test_generic_metric(struct metric_expr *mexp, int map_idx, struct runtime_stat *st) +double test_generic_metric(struct metric_expr *mexp, int map_idx) { struct expr_parse_ctx *pctx; double ratio = 0.0; @@ -666,7 +639,7 @@ double test_generic_metric(struct metric_expr *mexp, int map_idx, struct runtime if (!pctx) return NAN; - if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, map_idx, st) < 0) + if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, map_idx) < 0) goto out; if (expr__parse(&ratio, pctx, mexp->metric_expr)) @@ -681,8 +654,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct evsel *evsel, double avg, int map_idx, struct perf_stat_output_ctx *out, - struct rblist *metric_events, - struct runtime_stat *st) + struct rblist *metric_events) { void *ctxp = out->ctx; print_metric_t print_metric = out->print_metric; @@ -697,7 +669,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (config->iostat_run) { iostat_print_metric(config, evsel, out); } else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { - total = runtime_stat_avg(st, STAT_CYCLES, map_idx, &rsd); + total = runtime_stat_avg(STAT_CYCLES, map_idx, &rsd); if (total) { ratio = avg / total; @@ -707,10 +679,9 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0); } - total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, map_idx, &rsd); + total = runtime_stat_avg(STAT_STALLED_CYCLES_FRONT, map_idx, &rsd); - total = max(total, runtime_stat_avg(st, - STAT_STALLED_CYCLES_BACK, + total = max(total, runtime_stat_avg(STAT_STALLED_CYCLES_BACK, map_idx, &rsd)); if (total && avg) { @@ -721,8 +692,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ratio); } } else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { - if (runtime_stat_n(st, STAT_BRANCHES, map_idx, &rsd) != 0) - print_branch_misses(config, map_idx, avg, out, st, &rsd); + if (runtime_stat_n(STAT_BRANCHES, map_idx, &rsd) != 0) + print_branch_misses(config, map_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all branches", 0); } else if ( @@ -731,8 +702,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_L1_DCACHE, map_idx, &rsd) != 0) - print_l1_dcache_misses(config, map_idx, avg, out, st, &rsd); + if (runtime_stat_n(STAT_L1_DCACHE, map_idx, &rsd) != 0) + print_l1_dcache_misses(config, map_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0); } else if ( @@ -741,8 +712,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_L1_ICACHE, map_idx, &rsd) != 0) - print_l1_icache_misses(config, map_idx, avg, out, st, &rsd); + if (runtime_stat_n(STAT_L1_ICACHE, map_idx, &rsd) != 0) + print_l1_icache_misses(config, map_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0); } else if ( @@ -751,8 +722,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_DTLB_CACHE, map_idx, &rsd) != 0) - print_dtlb_cache_misses(config, map_idx, avg, out, st, &rsd); + if (runtime_stat_n(STAT_DTLB_CACHE, map_idx, &rsd) != 0) + print_dtlb_cache_misses(config, map_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0); } else if ( @@ -761,8 +732,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_ITLB_CACHE, map_idx, &rsd) != 0) - print_itlb_cache_misses(config, map_idx, avg, out, st, &rsd); + if (runtime_stat_n(STAT_ITLB_CACHE, map_idx, &rsd) != 0) + print_itlb_cache_misses(config, map_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0); } else if ( @@ -771,27 +742,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_LL_CACHE, map_idx, &rsd) != 0) - print_ll_cache_misses(config, map_idx, avg, out, st, &rsd); + if (runtime_stat_n(STAT_LL_CACHE, map_idx, &rsd) != 0) + print_ll_cache_misses(config, map_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0); } else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) { - total = runtime_stat_avg(st, STAT_CACHEREFS, map_idx, &rsd); + total = runtime_stat_avg(STAT_CACHEREFS, map_idx, &rsd); if (total) ratio = avg * 100 / total; - if (runtime_stat_n(st, STAT_CACHEREFS, map_idx, &rsd) != 0) + if (runtime_stat_n(STAT_CACHEREFS, map_idx, &rsd) != 0) print_metric(config, ctxp, NULL, "%8.3f %%", "of all cache refs", ratio); else print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) { - print_stalled_cycles_frontend(config, map_idx, avg, out, st, &rsd); + print_stalled_cycles_frontend(config, map_idx, avg, out, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) { - print_stalled_cycles_backend(config, map_idx, avg, out, st, &rsd); + print_stalled_cycles_backend(config, map_idx, avg, out, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { - total = runtime_stat_avg(st, STAT_NSECS, map_idx, &rsd); + total = runtime_stat_avg(STAT_NSECS, map_idx, &rsd); if (total) { ratio = avg / total; @@ -805,11 +776,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, avg / (ratio * evsel->scale)); else print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); - } else if (runtime_stat_n(st, STAT_NSECS, map_idx, &rsd) != 0) { + } else if (runtime_stat_n(STAT_NSECS, map_idx, &rsd) != 0) { char unit = ' '; char unit_buf[10] = "/sec"; - total = runtime_stat_avg(st, STAT_NSECS, map_idx, &rsd); + total = runtime_stat_avg(STAT_NSECS, map_idx, &rsd); if (total) ratio = convert_unit_double(1000000000.0 * avg / total, &unit); @@ -829,7 +800,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, generic_metric(config, mexp->metric_expr, mexp->metric_threshold, mexp->metric_events, mexp->metric_refs, evsel->name, mexp->metric_name, mexp->metric_unit, mexp->runtime, - map_idx, out, st); + map_idx, out); } } if (num == 0) diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 8d83d2f4a082..0d7538670d67 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -659,7 +659,7 @@ static void evsel__update_shadow_stats(struct evsel *evsel) for (i = 0; i < ps->nr_aggr; i++) { struct perf_counts_values *aggr_counts = &ps->aggr[i].counts; - perf_stat__update_shadow_stats(evsel, aggr_counts->val, i, &rt_stat); + perf_stat__update_shadow_stats(evsel, aggr_counts->val, i); } } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 215c0f5c4db7..09975e098bd0 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -55,10 +55,6 @@ enum aggr_mode { AGGR_MAX }; -struct runtime_stat { - struct rblist value_list; -}; - struct rusage_stats { struct stats ru_utime_usec_stat; struct stats ru_stime_usec_stat; @@ -153,7 +149,6 @@ static inline void update_rusage_stats(struct rusage_stats *ru_stats, struct rus struct evsel; struct evlist; -extern struct runtime_stat rt_stat; extern struct stats walltime_nsecs_stats; extern struct rusage_stats ru_stats; @@ -162,13 +157,10 @@ typedef void (*print_metric_t)(struct perf_stat_config *config, const char *fmt, double val); typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx); -void runtime_stat__init(struct runtime_stat *st); -void runtime_stat__exit(struct runtime_stat *st); void perf_stat__init_shadow_stats(void); void perf_stat__reset_shadow_stats(void); -void perf_stat__reset_shadow_per_stat(struct runtime_stat *st); -void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, - int map_idx, struct runtime_stat *st); +void perf_stat__reset_shadow_per_stat(void); +void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int map_idx); struct perf_stat_output_ctx { void *ctx; print_metric_t print_metric; @@ -180,8 +172,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct evsel *evsel, double avg, int map_idx, struct perf_stat_output_ctx *out, - struct rblist *metric_events, - struct runtime_stat *st); + struct rblist *metric_events); int evlist__alloc_stats(struct perf_stat_config *config, struct evlist *evlist, bool alloc_raw); @@ -220,5 +211,5 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf struct target *_target, struct timespec *ts, int argc, const char **argv); struct metric_expr; -double test_generic_metric(struct metric_expr *mexp, int map_idx, struct runtime_stat *st); +double test_generic_metric(struct metric_expr *mexp, int map_idx); #endif -- cgit v1.2.3-70-g09d2 From 8945bef30684b5ffb6778de1e979a7fcef6a760b Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:45 -0800 Subject: perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cpumap.h | 3 + tools/perf/util/stat-display.c | 112 +++++++++++++++++++----------------- tools/perf/util/stat-shadow.c | 128 ++++++++++++++++++++--------------------- tools/perf/util/stat.c | 8 +-- tools/perf/util/stat.h | 6 +- 5 files changed, 132 insertions(+), 125 deletions(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index c2f5824a3a22..e3426541e0aa 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -35,6 +35,9 @@ struct cpu_aggr_map { struct aggr_cpu_id map[]; }; +#define cpu_aggr_map__for_each_idx(idx, aggr_map) \ + for ((idx) = 0; (idx) < aggr_map->nr; (idx)++) + struct perf_record_cpu_map_data; bool perf_record_cpu_map_data__test_bit(int i, const struct perf_record_cpu_map_data *data); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 6c065d0624c3..e6035ecbeee8 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -183,7 +183,7 @@ static void print_cgroup(struct perf_stat_config *config, struct cgroup *cgrp) } static void print_aggr_id_std(struct perf_stat_config *config, - struct evsel *evsel, struct aggr_cpu_id id, int nr) + struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr) { FILE *output = config->output; int idx = config->aggr_mode; @@ -225,11 +225,11 @@ static void print_aggr_id_std(struct perf_stat_config *config, return; } - fprintf(output, "%-*s %*d ", aggr_header_lens[idx], buf, 4, nr); + fprintf(output, "%-*s %*d ", aggr_header_lens[idx], buf, 4, aggr_nr); } static void print_aggr_id_csv(struct perf_stat_config *config, - struct evsel *evsel, struct aggr_cpu_id id, int nr) + struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr) { FILE *output = config->output; const char *sep = config->csv_sep; @@ -237,19 +237,19 @@ static void print_aggr_id_csv(struct perf_stat_config *config, switch (config->aggr_mode) { case AGGR_CORE: fprintf(output, "S%d-D%d-C%d%s%d%s", - id.socket, id.die, id.core, sep, nr, sep); + id.socket, id.die, id.core, sep, aggr_nr, sep); break; case AGGR_DIE: fprintf(output, "S%d-D%d%s%d%s", - id.socket, id.die, sep, nr, sep); + id.socket, id.die, sep, aggr_nr, sep); break; case AGGR_SOCKET: fprintf(output, "S%d%s%d%s", - id.socket, sep, nr, sep); + id.socket, sep, aggr_nr, sep); break; case AGGR_NODE: fprintf(output, "N%d%s%d%s", - id.node, sep, nr, sep); + id.node, sep, aggr_nr, sep); break; case AGGR_NONE: if (evsel->percore && !config->percore_show_thread) { @@ -275,26 +275,26 @@ static void print_aggr_id_csv(struct perf_stat_config *config, } static void print_aggr_id_json(struct perf_stat_config *config, - struct evsel *evsel, struct aggr_cpu_id id, int nr) + struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr) { FILE *output = config->output; switch (config->aggr_mode) { case AGGR_CORE: fprintf(output, "\"core\" : \"S%d-D%d-C%d\", \"aggregate-number\" : %d, ", - id.socket, id.die, id.core, nr); + id.socket, id.die, id.core, aggr_nr); break; case AGGR_DIE: fprintf(output, "\"die\" : \"S%d-D%d\", \"aggregate-number\" : %d, ", - id.socket, id.die, nr); + id.socket, id.die, aggr_nr); break; case AGGR_SOCKET: fprintf(output, "\"socket\" : \"S%d\", \"aggregate-number\" : %d, ", - id.socket, nr); + id.socket, aggr_nr); break; case AGGR_NODE: fprintf(output, "\"node\" : \"N%d\", \"aggregate-number\" : %d, ", - id.node, nr); + id.node, aggr_nr); break; case AGGR_NONE: if (evsel->percore && !config->percore_show_thread) { @@ -319,14 +319,14 @@ static void print_aggr_id_json(struct perf_stat_config *config, } static void aggr_printout(struct perf_stat_config *config, - struct evsel *evsel, struct aggr_cpu_id id, int nr) + struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr) { if (config->json_output) - print_aggr_id_json(config, evsel, id, nr); + print_aggr_id_json(config, evsel, id, aggr_nr); else if (config->csv_output) - print_aggr_id_csv(config, evsel, id, nr); + print_aggr_id_csv(config, evsel, id, aggr_nr); else - print_aggr_id_std(config, evsel, id, nr); + print_aggr_id_std(config, evsel, id, aggr_nr); } struct outstate { @@ -335,7 +335,7 @@ struct outstate { bool first; const char *prefix; int nfields; - int nr; + int aggr_nr; struct aggr_cpu_id id; struct evsel *evsel; struct cgroup *cgrp; @@ -355,7 +355,7 @@ static void do_new_line_std(struct perf_stat_config *config, fputc('\n', os->fh); if (os->prefix) fputs(os->prefix, os->fh); - aggr_printout(config, os->evsel, os->id, os->nr); + aggr_printout(config, os->evsel, os->id, os->aggr_nr); if (config->aggr_mode == AGGR_NONE) fprintf(os->fh, " "); fprintf(os->fh, " "); @@ -396,7 +396,7 @@ static void new_line_csv(struct perf_stat_config *config, void *ctx) fputc('\n', os->fh); if (os->prefix) fprintf(os->fh, "%s", os->prefix); - aggr_printout(config, os->evsel, os->id, os->nr); + aggr_printout(config, os->evsel, os->id, os->aggr_nr); for (i = 0; i < os->nfields; i++) fputs(config->csv_sep, os->fh); } @@ -444,7 +444,7 @@ static void new_line_json(struct perf_stat_config *config, void *ctx) fputs("\n{", os->fh); if (os->prefix) fprintf(os->fh, "%s", os->prefix); - aggr_printout(config, os->evsel, os->id, os->nr); + aggr_printout(config, os->evsel, os->id, os->aggr_nr); } /* Filter out some columns that don't work well in metrics only mode */ @@ -645,10 +645,10 @@ static void print_counter_value(struct perf_stat_config *config, } static void abs_printout(struct perf_stat_config *config, - struct aggr_cpu_id id, int nr, + struct aggr_cpu_id id, int aggr_nr, struct evsel *evsel, double avg, bool ok) { - aggr_printout(config, evsel, id, nr); + aggr_printout(config, evsel, id, aggr_nr); print_counter_value(config, evsel, avg, ok); print_cgroup(config, evsel->cgrp); } @@ -678,7 +678,7 @@ static bool is_mixed_hw_group(struct evsel *counter) } static void printout(struct perf_stat_config *config, struct outstate *os, - double uval, u64 run, u64 ena, double noise, int map_idx) + double uval, u64 run, u64 ena, double noise, int aggr_idx) { struct perf_stat_output_ctx out; print_metric_t pm; @@ -721,14 +721,14 @@ static void printout(struct perf_stat_config *config, struct outstate *os, out.force_header = false; if (!config->metric_only) { - abs_printout(config, os->id, os->nr, counter, uval, ok); + abs_printout(config, os->id, os->aggr_nr, counter, uval, ok); print_noise(config, counter, noise, /*before_metric=*/true); print_running(config, run, ena, /*before_metric=*/true); } if (ok) { - perf_stat__print_shadow_stats(config, counter, uval, map_idx, + perf_stat__print_shadow_stats(config, counter, uval, aggr_idx, &out, &config->metric_events); } else { pm(config, os, /*color=*/NULL, /*format=*/NULL, /*unit=*/"", /*val=*/0); @@ -833,20 +833,20 @@ static bool should_skip_zero_counter(struct perf_stat_config *config, } static void print_counter_aggrdata(struct perf_stat_config *config, - struct evsel *counter, int s, + struct evsel *counter, int aggr_idx, struct outstate *os) { FILE *output = config->output; u64 ena, run, val; double uval; struct perf_stat_evsel *ps = counter->stats; - struct perf_stat_aggr *aggr = &ps->aggr[s]; - struct aggr_cpu_id id = config->aggr_map->map[s]; + struct perf_stat_aggr *aggr = &ps->aggr[aggr_idx]; + struct aggr_cpu_id id = config->aggr_map->map[aggr_idx]; double avg = aggr->counts.val; bool metric_only = config->metric_only; os->id = id; - os->nr = aggr->nr; + os->aggr_nr = aggr->nr; os->evsel = counter; /* Skip already merged uncore/hybrid events */ @@ -874,7 +874,7 @@ static void print_counter_aggrdata(struct perf_stat_config *config, uval = val * counter->scale; - printout(config, os, uval, run, ena, avg, s); + printout(config, os, uval, run, ena, avg, aggr_idx); if (!metric_only) fputc('\n', output); @@ -925,7 +925,7 @@ static void print_aggr(struct perf_stat_config *config, struct outstate *os) { struct evsel *counter; - int s; + int aggr_idx; if (!config->aggr_map || !config->aggr_get_id) return; @@ -934,11 +934,11 @@ static void print_aggr(struct perf_stat_config *config, * With metric_only everything is on a single line. * Without each counter has its own line. */ - for (s = 0; s < config->aggr_map->nr; s++) { - print_metric_begin(config, evlist, os, s); + cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) { + print_metric_begin(config, evlist, os, aggr_idx); evlist__for_each_entry(evlist, counter) { - print_counter_aggrdata(config, counter, s, os); + print_counter_aggrdata(config, counter, aggr_idx, os); } print_metric_end(config, os); } @@ -949,7 +949,7 @@ static void print_aggr_cgroup(struct perf_stat_config *config, struct outstate *os) { struct evsel *counter, *evsel; - int s; + int aggr_idx; if (!config->aggr_map || !config->aggr_get_id) return; @@ -960,14 +960,14 @@ static void print_aggr_cgroup(struct perf_stat_config *config, os->cgrp = evsel->cgrp; - for (s = 0; s < config->aggr_map->nr; s++) { - print_metric_begin(config, evlist, os, s); + cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) { + print_metric_begin(config, evlist, os, aggr_idx); evlist__for_each_entry(evlist, counter) { if (counter->cgrp != os->cgrp) continue; - print_counter_aggrdata(config, counter, s, os); + print_counter_aggrdata(config, counter, aggr_idx, os); } print_metric_end(config, os); } @@ -977,14 +977,14 @@ static void print_aggr_cgroup(struct perf_stat_config *config, static void print_counter(struct perf_stat_config *config, struct evsel *counter, struct outstate *os) { - int s; + int aggr_idx; /* AGGR_THREAD doesn't have config->aggr_get_id */ if (!config->aggr_map) return; - for (s = 0; s < config->aggr_map->nr; s++) { - print_counter_aggrdata(config, counter, s, os); + cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) { + print_counter_aggrdata(config, counter, aggr_idx, os); } } @@ -1003,23 +1003,23 @@ static void print_no_aggr_metric(struct perf_stat_config *config, u64 ena, run, val; double uval; struct perf_stat_evsel *ps = counter->stats; - int counter_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu); + int aggr_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu); - if (counter_idx < 0) + if (aggr_idx < 0) continue; os->evsel = counter; os->id = aggr_cpu_id__cpu(cpu, /*data=*/NULL); if (first) { - print_metric_begin(config, evlist, os, counter_idx); + print_metric_begin(config, evlist, os, aggr_idx); first = false; } - val = ps->aggr[counter_idx].counts.val; - ena = ps->aggr[counter_idx].counts.ena; - run = ps->aggr[counter_idx].counts.run; + val = ps->aggr[aggr_idx].counts.val; + ena = ps->aggr[aggr_idx].counts.ena; + run = ps->aggr[aggr_idx].counts.run; uval = val * counter->scale; - printout(config, os, uval, run, ena, 1.0, counter_idx); + printout(config, os, uval, run, ena, 1.0, aggr_idx); } if (!first) print_metric_end(config, os); @@ -1338,7 +1338,7 @@ static void print_percore(struct perf_stat_config *config, bool metric_only = config->metric_only; FILE *output = config->output; struct cpu_aggr_map *core_map; - int s, c, i; + int aggr_idx, core_map_len = 0; if (!config->aggr_map || !config->aggr_get_id) return; @@ -1346,18 +1346,22 @@ static void print_percore(struct perf_stat_config *config, if (config->percore_show_thread) return print_counter(config, counter, os); + /* + * core_map will hold the aggr_cpu_id for the cores that have been + * printed so that each core is printed just once. + */ core_map = cpu_aggr_map__empty_new(config->aggr_map->nr); if (core_map == NULL) { fprintf(output, "Cannot allocate per-core aggr map for display\n"); return; } - for (s = 0, c = 0; s < config->aggr_map->nr; s++) { - struct perf_cpu curr_cpu = config->aggr_map->map[s].cpu; + cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) { + struct perf_cpu curr_cpu = config->aggr_map->map[aggr_idx].cpu; struct aggr_cpu_id core_id = aggr_cpu_id__core(curr_cpu, NULL); bool found = false; - for (i = 0; i < c; i++) { + for (int i = 0; i < core_map_len; i++) { if (aggr_cpu_id__equal(&core_map->map[i], &core_id)) { found = true; break; @@ -1366,9 +1370,9 @@ static void print_percore(struct perf_stat_config *config, if (found) continue; - print_counter_aggrdata(config, counter, s, os); + print_counter_aggrdata(config, counter, aggr_idx, os); - core_map->map[c++] = core_id; + core_map->map[core_map_len++] = core_id; } free(core_map); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index f80be6abac90..7b48e2bd3ba1 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -231,7 +231,7 @@ static void update_runtime_stat(enum stat_type type, * instruction rates, etc: */ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, - int map_idx) + int aggr_idx) { u64 count_ns = count; struct saved_value *v; @@ -242,39 +242,39 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, count *= counter->scale; if (evsel__is_clock(counter)) - update_runtime_stat(STAT_NSECS, map_idx, count_ns, &rsd); + update_runtime_stat(STAT_NSECS, aggr_idx, count_ns, &rsd); else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) - update_runtime_stat(STAT_CYCLES, map_idx, count, &rsd); + update_runtime_stat(STAT_CYCLES, aggr_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) update_runtime_stat(STAT_STALLED_CYCLES_FRONT, - map_idx, count, &rsd); + aggr_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) update_runtime_stat(STAT_STALLED_CYCLES_BACK, - map_idx, count, &rsd); + aggr_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) - update_runtime_stat(STAT_BRANCHES, map_idx, count, &rsd); + update_runtime_stat(STAT_BRANCHES, aggr_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_runtime_stat(STAT_CACHEREFS, map_idx, count, &rsd); + update_runtime_stat(STAT_CACHEREFS, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) - update_runtime_stat(STAT_L1_DCACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_L1_DCACHE, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) - update_runtime_stat(STAT_L1_ICACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_L1_ICACHE, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL)) - update_runtime_stat(STAT_LL_CACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_LL_CACHE, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB)) - update_runtime_stat(STAT_DTLB_CACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_DTLB_CACHE, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) - update_runtime_stat(STAT_ITLB_CACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_ITLB_CACHE, aggr_idx, count, &rsd); if (counter->collect_stat) { - v = saved_value_lookup(counter, map_idx, true, STAT_NONE, 0, + v = saved_value_lookup(counter, aggr_idx, true, STAT_NONE, 0, rsd.cgrp); update_stats(&v->stats, count); if (counter->metric_leader) v->metric_total += count; } else if (counter->metric_leader && !counter->merged_stat) { v = saved_value_lookup(counter->metric_leader, - map_idx, true, STAT_NONE, 0, rsd.cgrp); + aggr_idx, true, STAT_NONE, 0, rsd.cgrp); v->metric_total += count; v->metric_other++; } @@ -307,24 +307,24 @@ static const char *get_ratio_color(enum grc_type type, double ratio) return color; } -static double runtime_stat_avg(enum stat_type type, int map_idx, +static double runtime_stat_avg(enum stat_type type, int aggr_idx, struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, map_idx, false, type, rsd->ctx, rsd->cgrp); + v = saved_value_lookup(NULL, aggr_idx, false, type, rsd->ctx, rsd->cgrp); if (!v) return 0.0; return avg_stats(&v->stats); } -static double runtime_stat_n(enum stat_type type, int map_idx, +static double runtime_stat_n(enum stat_type type, int aggr_idx, struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, map_idx, false, type, rsd->ctx, rsd->cgrp); + v = saved_value_lookup(NULL, aggr_idx, false, type, rsd->ctx, rsd->cgrp); if (!v) return 0.0; @@ -332,14 +332,14 @@ static double runtime_stat_n(enum stat_type type, int map_idx, } static void print_stalled_cycles_frontend(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_CYCLES, map_idx, rsd); + total = runtime_stat_avg(STAT_CYCLES, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -354,14 +354,14 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config, } static void print_stalled_cycles_backend(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_CYCLES, map_idx, rsd); + total = runtime_stat_avg(STAT_CYCLES, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -372,14 +372,14 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config, } static void print_branch_misses(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_BRANCHES, map_idx, rsd); + total = runtime_stat_avg(STAT_BRANCHES, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -390,14 +390,14 @@ static void print_branch_misses(struct perf_stat_config *config, } static void print_l1_dcache_misses(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_L1_DCACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_L1_DCACHE, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -408,14 +408,14 @@ static void print_l1_dcache_misses(struct perf_stat_config *config, } static void print_l1_icache_misses(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_L1_ICACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_L1_ICACHE, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -425,14 +425,14 @@ static void print_l1_icache_misses(struct perf_stat_config *config, } static void print_dtlb_cache_misses(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_DTLB_CACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_DTLB_CACHE, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -442,14 +442,14 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config, } static void print_itlb_cache_misses(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_ITLB_CACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_ITLB_CACHE, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -459,14 +459,14 @@ static void print_itlb_cache_misses(struct perf_stat_config *config, } static void print_ll_cache_misses(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_LL_CACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_LL_CACHE, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -478,7 +478,7 @@ static void print_ll_cache_misses(struct perf_stat_config *config, static int prepare_metric(struct evsel **metric_events, struct metric_ref *metric_refs, struct expr_parse_ctx *pctx, - int map_idx) + int aggr_idx) { double scale; char *n; @@ -516,7 +516,7 @@ static int prepare_metric(struct evsel **metric_events, abort(); } } else { - v = saved_value_lookup(metric_events[i], map_idx, false, + v = saved_value_lookup(metric_events[i], aggr_idx, false, STAT_NONE, 0, metric_events[i]->cgrp); if (!v) @@ -560,7 +560,7 @@ static void generic_metric(struct perf_stat_config *config, const char *metric_name, const char *metric_unit, int runtime, - int map_idx, + int aggr_idx, struct perf_stat_output_ctx *out) { print_metric_t print_metric = out->print_metric; @@ -578,7 +578,7 @@ static void generic_metric(struct perf_stat_config *config, pctx->sctx.user_requested_cpu_list = strdup(config->user_requested_cpu_list); pctx->sctx.runtime = runtime; pctx->sctx.system_wide = config->system_wide; - i = prepare_metric(metric_events, metric_refs, pctx, map_idx); + i = prepare_metric(metric_events, metric_refs, pctx, aggr_idx); if (i < 0) { expr__ctx_free(pctx); return; @@ -630,7 +630,7 @@ static void generic_metric(struct perf_stat_config *config, expr__ctx_free(pctx); } -double test_generic_metric(struct metric_expr *mexp, int map_idx) +double test_generic_metric(struct metric_expr *mexp, int aggr_idx) { struct expr_parse_ctx *pctx; double ratio = 0.0; @@ -639,7 +639,7 @@ double test_generic_metric(struct metric_expr *mexp, int map_idx) if (!pctx) return NAN; - if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, map_idx) < 0) + if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, aggr_idx) < 0) goto out; if (expr__parse(&ratio, pctx, mexp->metric_expr)) @@ -652,7 +652,7 @@ out: void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct evsel *evsel, - double avg, int map_idx, + double avg, int aggr_idx, struct perf_stat_output_ctx *out, struct rblist *metric_events) { @@ -669,7 +669,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (config->iostat_run) { iostat_print_metric(config, evsel, out); } else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { - total = runtime_stat_avg(STAT_CYCLES, map_idx, &rsd); + total = runtime_stat_avg(STAT_CYCLES, aggr_idx, &rsd); if (total) { ratio = avg / total; @@ -679,10 +679,10 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0); } - total = runtime_stat_avg(STAT_STALLED_CYCLES_FRONT, map_idx, &rsd); + total = runtime_stat_avg(STAT_STALLED_CYCLES_FRONT, aggr_idx, &rsd); total = max(total, runtime_stat_avg(STAT_STALLED_CYCLES_BACK, - map_idx, &rsd)); + aggr_idx, &rsd)); if (total && avg) { out->new_line(config, ctxp); @@ -692,8 +692,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ratio); } } else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { - if (runtime_stat_n(STAT_BRANCHES, map_idx, &rsd) != 0) - print_branch_misses(config, map_idx, avg, out, &rsd); + if (runtime_stat_n(STAT_BRANCHES, aggr_idx, &rsd) != 0) + print_branch_misses(config, aggr_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all branches", 0); } else if ( @@ -702,8 +702,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(STAT_L1_DCACHE, map_idx, &rsd) != 0) - print_l1_dcache_misses(config, map_idx, avg, out, &rsd); + if (runtime_stat_n(STAT_L1_DCACHE, aggr_idx, &rsd) != 0) + print_l1_dcache_misses(config, aggr_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0); } else if ( @@ -712,8 +712,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(STAT_L1_ICACHE, map_idx, &rsd) != 0) - print_l1_icache_misses(config, map_idx, avg, out, &rsd); + if (runtime_stat_n(STAT_L1_ICACHE, aggr_idx, &rsd) != 0) + print_l1_icache_misses(config, aggr_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0); } else if ( @@ -722,8 +722,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(STAT_DTLB_CACHE, map_idx, &rsd) != 0) - print_dtlb_cache_misses(config, map_idx, avg, out, &rsd); + if (runtime_stat_n(STAT_DTLB_CACHE, aggr_idx, &rsd) != 0) + print_dtlb_cache_misses(config, aggr_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0); } else if ( @@ -732,8 +732,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(STAT_ITLB_CACHE, map_idx, &rsd) != 0) - print_itlb_cache_misses(config, map_idx, avg, out, &rsd); + if (runtime_stat_n(STAT_ITLB_CACHE, aggr_idx, &rsd) != 0) + print_itlb_cache_misses(config, aggr_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0); } else if ( @@ -742,27 +742,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(STAT_LL_CACHE, map_idx, &rsd) != 0) - print_ll_cache_misses(config, map_idx, avg, out, &rsd); + if (runtime_stat_n(STAT_LL_CACHE, aggr_idx, &rsd) != 0) + print_ll_cache_misses(config, aggr_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0); } else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) { - total = runtime_stat_avg(STAT_CACHEREFS, map_idx, &rsd); + total = runtime_stat_avg(STAT_CACHEREFS, aggr_idx, &rsd); if (total) ratio = avg * 100 / total; - if (runtime_stat_n(STAT_CACHEREFS, map_idx, &rsd) != 0) + if (runtime_stat_n(STAT_CACHEREFS, aggr_idx, &rsd) != 0) print_metric(config, ctxp, NULL, "%8.3f %%", "of all cache refs", ratio); else print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) { - print_stalled_cycles_frontend(config, map_idx, avg, out, &rsd); + print_stalled_cycles_frontend(config, aggr_idx, avg, out, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) { - print_stalled_cycles_backend(config, map_idx, avg, out, &rsd); + print_stalled_cycles_backend(config, aggr_idx, avg, out, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { - total = runtime_stat_avg(STAT_NSECS, map_idx, &rsd); + total = runtime_stat_avg(STAT_NSECS, aggr_idx, &rsd); if (total) { ratio = avg / total; @@ -776,11 +776,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, avg / (ratio * evsel->scale)); else print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); - } else if (runtime_stat_n(STAT_NSECS, map_idx, &rsd) != 0) { + } else if (runtime_stat_n(STAT_NSECS, aggr_idx, &rsd) != 0) { char unit = ' '; char unit_buf[10] = "/sec"; - total = runtime_stat_avg(STAT_NSECS, map_idx, &rsd); + total = runtime_stat_avg(STAT_NSECS, aggr_idx, &rsd); if (total) ratio = convert_unit_double(1000000000.0 * avg / total, &unit); @@ -800,7 +800,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, generic_metric(config, mexp->metric_expr, mexp->metric_threshold, mexp->metric_events, mexp->metric_refs, evsel->name, mexp->metric_name, mexp->metric_unit, mexp->runtime, - map_idx, out); + aggr_idx, out); } } if (num == 0) diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 0d7538670d67..83dc4c1f4b12 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -651,15 +651,15 @@ void perf_stat_process_percore(struct perf_stat_config *config, struct evlist *e static void evsel__update_shadow_stats(struct evsel *evsel) { struct perf_stat_evsel *ps = evsel->stats; - int i; + int aggr_idx; if (ps->aggr == NULL) return; - for (i = 0; i < ps->nr_aggr; i++) { - struct perf_counts_values *aggr_counts = &ps->aggr[i].counts; + for (aggr_idx = 0; aggr_idx < ps->nr_aggr; aggr_idx++) { + struct perf_counts_values *aggr_counts = &ps->aggr[aggr_idx].counts; - perf_stat__update_shadow_stats(evsel, aggr_counts->val, i); + perf_stat__update_shadow_stats(evsel, aggr_counts->val, aggr_idx); } } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 09975e098bd0..b01c828c3799 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -160,7 +160,7 @@ typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx); void perf_stat__init_shadow_stats(void); void perf_stat__reset_shadow_stats(void); void perf_stat__reset_shadow_per_stat(void); -void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int map_idx); +void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int aggr_idx); struct perf_stat_output_ctx { void *ctx; print_metric_t print_metric; @@ -170,7 +170,7 @@ struct perf_stat_output_ctx { void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct evsel *evsel, - double avg, int map_idx, + double avg, int aggr_idx, struct perf_stat_output_ctx *out, struct rblist *metric_events); @@ -211,5 +211,5 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf struct target *_target, struct timespec *ts, int argc, const char **argv); struct metric_expr; -double test_generic_metric(struct metric_expr *mexp, int map_idx); +double test_generic_metric(struct metric_expr *mexp, int aggr_idx); #endif -- cgit v1.2.3-70-g09d2 From 37cc8ad77cf81f3ffd226856c367b0e15333a738 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:46 -0800 Subject: perf metric: Directly use counts rather than saved_value Bugs with double aggregation have been introduced because of aggregation of counters and again with saved_value. Remove the generic metric use-case. Update parse-metric and pmu-events tests to update aggregate rather than saved_value counts. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-50-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/parse-metric.c | 4 +-- tools/perf/tests/pmu-events.c | 4 +-- tools/perf/util/stat-shadow.c | 56 ++++++++++++++--------------------------- 3 files changed, 23 insertions(+), 41 deletions(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 37e3371d978e..b9b8a48289c4 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -35,10 +35,10 @@ static void load_runtime_stat(struct evlist *evlist, struct value *vals) struct evsel *evsel; u64 count; - perf_stat__reset_shadow_stats(); + evlist__alloc_aggr_stats(evlist, 1); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); - perf_stat__update_shadow_stats(evsel, count, 0); + evsel->stats->aggr->counts.val = count; if (!strcmp(evsel->name, "duration_time")) update_stats(&walltime_nsecs_stats, count); } diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 122e74c282a7..4ec2a4ca1a82 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -863,9 +863,9 @@ static int test__parsing_callback(const struct pmu_metric *pm, * zero when subtracted and so try to make them unique. */ k = 1; - perf_stat__reset_shadow_stats(); + evlist__alloc_aggr_stats(evlist, 1); evlist__for_each_entry(evlist, evsel) { - perf_stat__update_shadow_stats(evsel, k, 0); + evsel->stats->aggr->counts.val = k; if (!strcmp(evsel->name, "duration_time")) update_stats(&walltime_nsecs_stats, k); k++; diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 7b48e2bd3ba1..eba98520cea2 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -234,7 +234,6 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int aggr_idx) { u64 count_ns = count; - struct saved_value *v; struct runtime_stat_data rsd = { .ctx = evsel_context(counter), .cgrp = counter->cgrp, @@ -265,19 +264,6 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, update_runtime_stat(STAT_DTLB_CACHE, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) update_runtime_stat(STAT_ITLB_CACHE, aggr_idx, count, &rsd); - - if (counter->collect_stat) { - v = saved_value_lookup(counter, aggr_idx, true, STAT_NONE, 0, - rsd.cgrp); - update_stats(&v->stats, count); - if (counter->metric_leader) - v->metric_total += count; - } else if (counter->metric_leader && !counter->merged_stat) { - v = saved_value_lookup(counter->metric_leader, - aggr_idx, true, STAT_NONE, 0, rsd.cgrp); - v->metric_total += count; - v->metric_other++; - } } /* used for get_ratio_color() */ @@ -480,18 +466,17 @@ static int prepare_metric(struct evsel **metric_events, struct expr_parse_ctx *pctx, int aggr_idx) { - double scale; - char *n; - int i, j, ret; + int i; for (i = 0; metric_events[i]; i++) { - struct saved_value *v; - struct stats *stats; - u64 metric_total = 0; - int source_count; + char *n; + double val; + int source_count = 0; if (evsel__is_tool(metric_events[i])) { - source_count = 1; + struct stats *stats; + double scale; + switch (metric_events[i]->tool_event) { case PERF_TOOL_DURATION_TIME: stats = &walltime_nsecs_stats; @@ -515,35 +500,32 @@ static int prepare_metric(struct evsel **metric_events, pr_err("Unknown tool event '%s'", evsel__name(metric_events[i])); abort(); } + val = avg_stats(stats) * scale; + source_count = 1; } else { - v = saved_value_lookup(metric_events[i], aggr_idx, false, - STAT_NONE, 0, - metric_events[i]->cgrp); - if (!v) + struct perf_stat_evsel *ps = metric_events[i]->stats; + struct perf_stat_aggr *aggr = &ps->aggr[aggr_idx]; + + if (!aggr) break; - stats = &v->stats; + /* * If an event was scaled during stat gathering, reverse * the scale before computing the metric. */ - scale = 1.0 / metric_events[i]->scale; - + val = aggr->counts.val * (1.0 / metric_events[i]->scale); source_count = evsel__source_count(metric_events[i]); - - if (v->metric_other) - metric_total = v->metric_total * scale; } n = strdup(evsel__metric_id(metric_events[i])); if (!n) return -ENOMEM; - expr__add_id_val_source_count(pctx, n, - metric_total ? : avg_stats(stats) * scale, - source_count); + expr__add_id_val_source_count(pctx, n, val, source_count); } - for (j = 0; metric_refs && metric_refs[j].metric_name; j++) { - ret = expr__add_ref(pctx, &metric_refs[j]); + for (int j = 0; metric_refs && metric_refs[j].metric_name; j++) { + int ret = expr__add_ref(pctx, &metric_refs[j]); + if (ret) return ret; } -- cgit v1.2.3-70-g09d2 From 0a57b910807ad16381d39578ffc51a7055e4dfd6 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:47 -0800 Subject: perf stat: Use counts rather than saved_value Switch the hard coded metrics to use the aggregate value rather than from saved_value. When computing a metric like IPC the aggregate count comes from instructions then cycles is looked up and if present IPC computed. Rather than lookup from the saved_value rbtree, search the counter's evlist for the desired counter. A new helper evsel__stat_type is used to both quickly find a metric function and to identify when a counter is the one being sought. So that both total and miss counts can be sought, the stat_type enum is expanded. The ratio functions are rewritten to share a common helper with the ratios being directly passed rather than computed from an enum value. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-51-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.h | 2 +- tools/perf/util/stat-shadow.c | 534 +++++++++++++++++++++--------------------- 2 files changed, 270 insertions(+), 266 deletions(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 24cb807ef6ce..814a49ebb7e3 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -436,7 +436,7 @@ static inline bool evsel__is_bpf_output(struct evsel *evsel) return evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT); } -static inline bool evsel__is_clock(struct evsel *evsel) +static inline bool evsel__is_clock(const struct evsel *evsel) { return evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) || evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index eba98520cea2..9d22cde09dc9 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -45,15 +45,23 @@ enum stat_type { STAT_NONE = 0, STAT_NSECS, STAT_CYCLES, + STAT_INSTRUCTIONS, STAT_STALLED_CYCLES_FRONT, STAT_STALLED_CYCLES_BACK, STAT_BRANCHES, - STAT_CACHEREFS, + STAT_BRANCH_MISS, + STAT_CACHE_REFS, + STAT_CACHE_MISSES, STAT_L1_DCACHE, STAT_L1_ICACHE, STAT_LL_CACHE, STAT_ITLB_CACHE, STAT_DTLB_CACHE, + STAT_L1D_MISS, + STAT_L1I_MISS, + STAT_LL_MISS, + STAT_DTLB_MISS, + STAT_ITLB_MISS, STAT_MAX }; @@ -168,7 +176,7 @@ void perf_stat__init_shadow_stats(void) rblist->node_delete = saved_value_delete; } -static int evsel_context(struct evsel *evsel) +static int evsel_context(const struct evsel *evsel) { int ctx = 0; @@ -253,7 +261,7 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) update_runtime_stat(STAT_BRANCHES, aggr_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_runtime_stat(STAT_CACHEREFS, aggr_idx, count, &rsd); + update_runtime_stat(STAT_CACHE_REFS, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) update_runtime_stat(STAT_L1_DCACHE, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) @@ -266,199 +274,283 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, update_runtime_stat(STAT_ITLB_CACHE, aggr_idx, count, &rsd); } -/* used for get_ratio_color() */ -enum grc_type { - GRC_STALLED_CYCLES_FE, - GRC_STALLED_CYCLES_BE, - GRC_CACHE_MISSES, - GRC_MAX_NR -}; +static enum stat_type evsel__stat_type(const struct evsel *evsel) +{ + /* Fake perf_hw_cache_op_id values for use with evsel__match. */ + u64 PERF_COUNT_hw_cache_l1d_miss = PERF_COUNT_HW_CACHE_L1D | + ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); + u64 PERF_COUNT_hw_cache_l1i_miss = PERF_COUNT_HW_CACHE_L1I | + ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); + u64 PERF_COUNT_hw_cache_ll_miss = PERF_COUNT_HW_CACHE_LL | + ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); + u64 PERF_COUNT_hw_cache_dtlb_miss = PERF_COUNT_HW_CACHE_DTLB | + ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); + u64 PERF_COUNT_hw_cache_itlb_miss = PERF_COUNT_HW_CACHE_ITLB | + ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); + + if (evsel__is_clock(evsel)) + return STAT_NSECS; + else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) + return STAT_CYCLES; + else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) + return STAT_INSTRUCTIONS; + else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) + return STAT_STALLED_CYCLES_FRONT; + else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) + return STAT_STALLED_CYCLES_BACK; + else if (evsel__match(evsel, HARDWARE, HW_BRANCH_INSTRUCTIONS)) + return STAT_BRANCHES; + else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) + return STAT_BRANCH_MISS; + else if (evsel__match(evsel, HARDWARE, HW_CACHE_REFERENCES)) + return STAT_CACHE_REFS; + else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) + return STAT_CACHE_MISSES; + else if (evsel__match(evsel, HW_CACHE, HW_CACHE_L1D)) + return STAT_L1_DCACHE; + else if (evsel__match(evsel, HW_CACHE, HW_CACHE_L1I)) + return STAT_L1_ICACHE; + else if (evsel__match(evsel, HW_CACHE, HW_CACHE_LL)) + return STAT_LL_CACHE; + else if (evsel__match(evsel, HW_CACHE, HW_CACHE_DTLB)) + return STAT_DTLB_CACHE; + else if (evsel__match(evsel, HW_CACHE, HW_CACHE_ITLB)) + return STAT_ITLB_CACHE; + else if (evsel__match(evsel, HW_CACHE, hw_cache_l1d_miss)) + return STAT_L1D_MISS; + else if (evsel__match(evsel, HW_CACHE, hw_cache_l1i_miss)) + return STAT_L1I_MISS; + else if (evsel__match(evsel, HW_CACHE, hw_cache_ll_miss)) + return STAT_LL_MISS; + else if (evsel__match(evsel, HW_CACHE, hw_cache_dtlb_miss)) + return STAT_DTLB_MISS; + else if (evsel__match(evsel, HW_CACHE, hw_cache_itlb_miss)) + return STAT_ITLB_MISS; + return STAT_NONE; +} -static const char *get_ratio_color(enum grc_type type, double ratio) +static const char *get_ratio_color(const double ratios[3], double val) { - static const double grc_table[GRC_MAX_NR][3] = { - [GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 }, - [GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 }, - [GRC_CACHE_MISSES] = { 20.0, 10.0, 5.0 }, - }; const char *color = PERF_COLOR_NORMAL; - if (ratio > grc_table[type][0]) + if (val > ratios[0]) color = PERF_COLOR_RED; - else if (ratio > grc_table[type][1]) + else if (val > ratios[1]) color = PERF_COLOR_MAGENTA; - else if (ratio > grc_table[type][2]) + else if (val > ratios[2]) color = PERF_COLOR_YELLOW; return color; } -static double runtime_stat_avg(enum stat_type type, int aggr_idx, - struct runtime_stat_data *rsd) +static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type type) { - struct saved_value *v; - - v = saved_value_lookup(NULL, aggr_idx, false, type, rsd->ctx, rsd->cgrp); - if (!v) - return 0.0; - - return avg_stats(&v->stats); + const struct evsel *cur; + int evsel_ctx = evsel_context(evsel); + + evlist__for_each_entry(evsel->evlist, cur) { + struct perf_stat_aggr *aggr; + + /* Ignore the evsel that is being searched from. */ + if (evsel == cur) + continue; + + /* Ignore evsels that are part of different groups. */ + if (evsel->core.leader->nr_members && + evsel->core.leader != cur->core.leader) + continue; + /* Ignore evsels with mismatched modifiers. */ + if (evsel_ctx != evsel_context(cur)) + continue; + /* Ignore if not the cgroup we're looking for. */ + if (evsel->cgrp != cur->cgrp) + continue; + /* Ignore if not the stat we're looking for. */ + if (type != evsel__stat_type(cur)) + continue; + + aggr = &cur->stats->aggr[aggr_idx]; + if (type == STAT_NSECS) + return aggr->counts.val; + return aggr->counts.val * cur->scale; + } + return 0.0; } -static double runtime_stat_n(enum stat_type type, int aggr_idx, - struct runtime_stat_data *rsd) +static void print_ratio(struct perf_stat_config *config, + const struct evsel *evsel, int aggr_idx, + double numerator, struct perf_stat_output_ctx *out, + enum stat_type denominator_type, + const double color_ratios[3], const char *unit) { - struct saved_value *v; + double denominator = find_stat(evsel, aggr_idx, denominator_type); - v = saved_value_lookup(NULL, aggr_idx, false, type, rsd->ctx, rsd->cgrp); - if (!v) - return 0.0; + if (numerator && denominator) { + double ratio = numerator / denominator * 100.0; + const char *color = get_ratio_color(color_ratios, ratio); - return v->stats.n; + out->print_metric(config, out->ctx, color, "%7.2f%%", unit, ratio); + } else + out->print_metric(config, out->ctx, NULL, NULL, unit, 0); } -static void print_stalled_cycles_frontend(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_stalled_cycles_front(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double stalled, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; - - total = runtime_stat_avg(STAT_CYCLES, aggr_idx, rsd); - - if (total) - ratio = avg / total * 100.0; + static const double color_ratios[3] = {50.0, 30.0, 10.0}; - color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio); - - if (ratio) - out->print_metric(config, out->ctx, color, "%7.2f%%", "frontend cycles idle", - ratio); - else - out->print_metric(config, out->ctx, NULL, NULL, "frontend cycles idle", 0); + print_ratio(config, evsel, aggr_idx, stalled, out, STAT_CYCLES, color_ratios, + "frontend cycles idle"); } -static void print_stalled_cycles_backend(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_stalled_cycles_back(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double stalled, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; - - total = runtime_stat_avg(STAT_CYCLES, aggr_idx, rsd); - - if (total) - ratio = avg / total * 100.0; + static const double color_ratios[3] = {75.0, 50.0, 20.0}; - color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio); - - out->print_metric(config, out->ctx, color, "%7.2f%%", "backend cycles idle", ratio); + print_ratio(config, evsel, aggr_idx, stalled, out, STAT_CYCLES, color_ratios, + "backend cycles idle"); } -static void print_branch_misses(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_branch_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; - - total = runtime_stat_avg(STAT_BRANCHES, aggr_idx, rsd); - - if (total) - ratio = avg / total * 100.0; + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - color = get_ratio_color(GRC_CACHE_MISSES, ratio); - - out->print_metric(config, out->ctx, color, "%7.2f%%", "of all branches", ratio); + print_ratio(config, evsel, aggr_idx, misses, out, STAT_BRANCHES, color_ratios, + "of all branches"); } -static void print_l1_dcache_misses(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_l1d_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; - - total = runtime_stat_avg(STAT_L1_DCACHE, aggr_idx, rsd); + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - if (total) - ratio = avg / total * 100.0; + print_ratio(config, evsel, aggr_idx, misses, out, STAT_L1_DCACHE, color_ratios, + "of all L1-dcache accesses"); +} - color = get_ratio_color(GRC_CACHE_MISSES, ratio); +static void print_l1i_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) +{ + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache accesses", ratio); + print_ratio(config, evsel, aggr_idx, misses, out, STAT_L1_ICACHE, color_ratios, + "of all L1-icache accesses"); } -static void print_l1_icache_misses(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_ll_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - total = runtime_stat_avg(STAT_L1_ICACHE, aggr_idx, rsd); + print_ratio(config, evsel, aggr_idx, misses, out, STAT_LL_CACHE, color_ratios, + "of all L1-icache accesses"); +} - if (total) - ratio = avg / total * 100.0; +static void print_dtlb_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) +{ + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache accesses", ratio); + print_ratio(config, evsel, aggr_idx, misses, out, STAT_DTLB_CACHE, color_ratios, + "of all dTLB cache accesses"); } -static void print_dtlb_cache_misses(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_itlb_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - total = runtime_stat_avg(STAT_DTLB_CACHE, aggr_idx, rsd); + print_ratio(config, evsel, aggr_idx, misses, out, STAT_ITLB_CACHE, color_ratios, + "of all iTLB cache accesses"); +} - if (total) - ratio = avg / total * 100.0; +static void print_cache_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) +{ + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache accesses", ratio); + print_ratio(config, evsel, aggr_idx, misses, out, STAT_CACHE_REFS, color_ratios, + "of all cache refs"); } -static void print_itlb_cache_misses(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_instructions(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double instructions, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; + print_metric_t print_metric = out->print_metric; + void *ctxp = out->ctx; + double cycles = find_stat(evsel, aggr_idx, STAT_CYCLES); + double max_stalled = max(find_stat(evsel, aggr_idx, STAT_STALLED_CYCLES_FRONT), + find_stat(evsel, aggr_idx, STAT_STALLED_CYCLES_BACK)); + + if (cycles) { + print_metric(config, ctxp, NULL, "%7.2f ", "insn per cycle", + instructions / cycles); + } else + print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0); + + if (max_stalled && instructions) { + out->new_line(config, ctxp); + print_metric(config, ctxp, NULL, "%7.2f ", "stalled cycles per insn", + max_stalled / instructions); + } +} - total = runtime_stat_avg(STAT_ITLB_CACHE, aggr_idx, rsd); +static void print_cycles(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double cycles, + struct perf_stat_output_ctx *out) +{ + double nsecs = find_stat(evsel, aggr_idx, STAT_NSECS); - if (total) - ratio = avg / total * 100.0; + if (cycles && nsecs) { + double ratio = cycles / nsecs; - color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache accesses", ratio); + out->print_metric(config, out->ctx, NULL, "%8.3f", "GHz", ratio); + } else + out->print_metric(config, out->ctx, NULL, NULL, "GHz", 0); } -static void print_ll_cache_misses(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_nsecs(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx __maybe_unused, double nsecs, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; - - total = runtime_stat_avg(STAT_LL_CACHE, aggr_idx, rsd); - - if (total) - ratio = avg / total * 100.0; + print_metric_t print_metric = out->print_metric; + void *ctxp = out->ctx; + double wall_time = avg_stats(&walltime_nsecs_stats); - color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache accesses", ratio); + if (wall_time) { + print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized", + nsecs / (wall_time * evsel->scale)); + } else + print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); } static int prepare_metric(struct evsel **metric_events, @@ -638,139 +730,51 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct perf_stat_output_ctx *out, struct rblist *metric_events) { - void *ctxp = out->ctx; - print_metric_t print_metric = out->print_metric; - double total, ratio = 0.0; - struct runtime_stat_data rsd = { - .ctx = evsel_context(evsel), - .cgrp = evsel->cgrp, + typedef void (*stat_print_function_t)(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out); + static const stat_print_function_t stat_print_function[STAT_MAX] = { + [STAT_INSTRUCTIONS] = print_instructions, + [STAT_BRANCH_MISS] = print_branch_miss, + [STAT_L1D_MISS] = print_l1d_miss, + [STAT_L1I_MISS] = print_l1i_miss, + [STAT_DTLB_MISS] = print_dtlb_miss, + [STAT_ITLB_MISS] = print_itlb_miss, + [STAT_LL_MISS] = print_ll_miss, + [STAT_CACHE_MISSES] = print_cache_miss, + [STAT_STALLED_CYCLES_FRONT] = print_stalled_cycles_front, + [STAT_STALLED_CYCLES_BACK] = print_stalled_cycles_back, + [STAT_CYCLES] = print_cycles, + [STAT_NSECS] = print_nsecs, }; + print_metric_t print_metric = out->print_metric; + void *ctxp = out->ctx; struct metric_event *me; int num = 1; if (config->iostat_run) { iostat_print_metric(config, evsel, out); - } else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { - total = runtime_stat_avg(STAT_CYCLES, aggr_idx, &rsd); - - if (total) { - ratio = avg / total; - print_metric(config, ctxp, NULL, "%7.2f ", - "insn per cycle", ratio); - } else { - print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0); - } - - total = runtime_stat_avg(STAT_STALLED_CYCLES_FRONT, aggr_idx, &rsd); - - total = max(total, runtime_stat_avg(STAT_STALLED_CYCLES_BACK, - aggr_idx, &rsd)); - - if (total && avg) { - out->new_line(config, ctxp); - ratio = total / avg; - print_metric(config, ctxp, NULL, "%7.2f ", - "stalled cycles per insn", - ratio); - } - } else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { - if (runtime_stat_n(STAT_BRANCHES, aggr_idx, &rsd) != 0) - print_branch_misses(config, aggr_idx, avg, out, &rsd); - else - print_metric(config, ctxp, NULL, NULL, "of all branches", 0); - } else if ( - evsel->core.attr.type == PERF_TYPE_HW_CACHE && - evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_L1D | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - - if (runtime_stat_n(STAT_L1_DCACHE, aggr_idx, &rsd) != 0) - print_l1_dcache_misses(config, aggr_idx, avg, out, &rsd); - else - print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0); - } else if ( - evsel->core.attr.type == PERF_TYPE_HW_CACHE && - evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_L1I | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - - if (runtime_stat_n(STAT_L1_ICACHE, aggr_idx, &rsd) != 0) - print_l1_icache_misses(config, aggr_idx, avg, out, &rsd); - else - print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0); - } else if ( - evsel->core.attr.type == PERF_TYPE_HW_CACHE && - evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_DTLB | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - - if (runtime_stat_n(STAT_DTLB_CACHE, aggr_idx, &rsd) != 0) - print_dtlb_cache_misses(config, aggr_idx, avg, out, &rsd); - else - print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0); - } else if ( - evsel->core.attr.type == PERF_TYPE_HW_CACHE && - evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_ITLB | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - - if (runtime_stat_n(STAT_ITLB_CACHE, aggr_idx, &rsd) != 0) - print_itlb_cache_misses(config, aggr_idx, avg, out, &rsd); - else - print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0); - } else if ( - evsel->core.attr.type == PERF_TYPE_HW_CACHE && - evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_LL | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - - if (runtime_stat_n(STAT_LL_CACHE, aggr_idx, &rsd) != 0) - print_ll_cache_misses(config, aggr_idx, avg, out, &rsd); - else - print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0); - } else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) { - total = runtime_stat_avg(STAT_CACHEREFS, aggr_idx, &rsd); - - if (total) - ratio = avg * 100 / total; - - if (runtime_stat_n(STAT_CACHEREFS, aggr_idx, &rsd) != 0) - print_metric(config, ctxp, NULL, "%8.3f %%", - "of all cache refs", ratio); - else - print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0); - } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) { - print_stalled_cycles_frontend(config, aggr_idx, avg, out, &rsd); - } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) { - print_stalled_cycles_backend(config, aggr_idx, avg, out, &rsd); - } else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { - total = runtime_stat_avg(STAT_NSECS, aggr_idx, &rsd); - - if (total) { - ratio = avg / total; - print_metric(config, ctxp, NULL, "%8.3f", "GHz", ratio); - } else { - print_metric(config, ctxp, NULL, NULL, "Ghz", 0); - } - } else if (evsel__is_clock(evsel)) { - if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0) - print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized", - avg / (ratio * evsel->scale)); - else - print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); - } else if (runtime_stat_n(STAT_NSECS, aggr_idx, &rsd) != 0) { - char unit = ' '; - char unit_buf[10] = "/sec"; - - total = runtime_stat_avg(STAT_NSECS, aggr_idx, &rsd); - if (total) - ratio = convert_unit_double(1000000000.0 * avg / total, &unit); - - if (unit != ' ') - snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); - print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio); } else { - num = 0; + stat_print_function_t fn = stat_print_function[evsel__stat_type(evsel)]; + + if (fn) + fn(config, evsel, aggr_idx, avg, out); + else { + double nsecs = find_stat(evsel, aggr_idx, STAT_NSECS); + + if (nsecs) { + char unit = ' '; + char unit_buf[10] = "/sec"; + double ratio = convert_unit_double(1000000000.0 * avg / nsecs, + &unit); + + if (unit != ' ') + snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); + print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio); + } else + num = 0; + } } if ((me = metricgroup__lookup(metric_events, evsel, false)) != NULL) { -- cgit v1.2.3-70-g09d2 From aa0964e3ecebe92243bac30f9317117037adecb9 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:48 -0800 Subject: perf stat: Remove saved_value/runtime_stat As saved_value/runtime_stat are only written to and not read, remove the associated logic and writes. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-52-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 5 - tools/perf/builtin-stat.c | 6 -- tools/perf/tests/parse-metric.c | 1 - tools/perf/tests/pmu-events.c | 1 - tools/perf/util/stat-shadow.c | 198 ---------------------------------------- tools/perf/util/stat.c | 24 ----- tools/perf/util/stat.h | 4 - 7 files changed, 239 deletions(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index e9b5387161df..522226114263 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2072,9 +2072,6 @@ static void perf_sample__fprint_metric(struct perf_script *script, if (evsel_script(leader)->gnum++ == 0) perf_stat__reset_shadow_stats(); val = sample->period * evsel->scale; - perf_stat__update_shadow_stats(evsel, - val, - sample->cpu); evsel_script(evsel)->val = val; if (evsel_script(leader)->gnum == leader->core.nr_members) { for_each_group_member (ev2, leader) { @@ -2792,8 +2789,6 @@ static int __cmd_script(struct perf_script *script) signal(SIGINT, sig_handler); - perf_stat__init_shadow_stats(); - /* override event processing functions */ if (script->show_task_events) { script->tool.comm = process_comm_event; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 619387459914..d70b1ec88594 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -424,7 +424,6 @@ 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) @@ -434,7 +433,6 @@ static void process_interval(void) clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); - perf_stat__reset_shadow_per_stat(); evlist__reset_aggr_stats(evsel_list); if (read_counters(&rs) == 0) @@ -910,7 +908,6 @@ 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(); } else { update_stats(&walltime_nsecs_stats, t1 - t0); update_rusage_stats(&ru_stats, &stat_config.ru_data); @@ -2132,8 +2129,6 @@ 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; @@ -2413,7 +2408,6 @@ int cmd_stat(int argc, const char **argv) &stat_config.metric_events); zfree(&metrics); } - perf_stat__init_shadow_stats(); if (add_default_attributes()) goto out; diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index b9b8a48289c4..c43b056f9fa3 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -296,7 +296,6 @@ static int test_metric_group(void) static int test__parse_metric(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { - perf_stat__init_shadow_stats(); TEST_ASSERT_VAL("IPC failed", test_ipc() == 0); TEST_ASSERT_VAL("frontend failed", test_frontend() == 0); TEST_ASSERT_VAL("DCache_L2 failed", test_dcache_l2() == 0); diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 4ec2a4ca1a82..6ccd413b5983 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -905,7 +905,6 @@ static int test__parsing(struct test_suite *test __maybe_unused, { int failures = 0; - perf_stat__init_shadow_stats(); pmu_for_each_core_metric(test__parsing_callback, &failures); pmu_for_each_sys_metric(test__parsing_callback, &failures); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 9d22cde09dc9..ef85f1ae1ab2 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -16,22 +16,9 @@ #include "iostat.h" #include "util/hashmap.h" -/* - * AGGR_GLOBAL: Use CPU 0 - * AGGR_SOCKET: Use first CPU of socket - * AGGR_DIE: Use first CPU of die - * AGGR_CORE: Use first CPU of core - * AGGR_NONE: Use matching CPU - * AGGR_THREAD: Not supported? - */ - struct stats walltime_nsecs_stats; struct rusage_stats ru_stats; -static struct runtime_stat { - struct rblist value_list; -} rt_stat; - enum { CTX_BIT_USER = 1 << 0, CTX_BIT_KERNEL = 1 << 1, @@ -65,117 +52,6 @@ enum stat_type { STAT_MAX }; -struct saved_value { - struct rb_node rb_node; - struct evsel *evsel; - enum stat_type type; - int ctx; - int map_idx; /* cpu or thread map index */ - struct cgroup *cgrp; - struct stats stats; - u64 metric_total; - int metric_other; -}; - -static int saved_value_cmp(struct rb_node *rb_node, const void *entry) -{ - struct saved_value *a = container_of(rb_node, - struct saved_value, - rb_node); - const struct saved_value *b = entry; - - if (a->map_idx != b->map_idx) - return a->map_idx - b->map_idx; - - /* - * Previously the rbtree was used to link generic metrics. - * The keys were evsel/cpu. Now the rbtree is extended to support - * per-thread shadow stats. For shadow stats case, the keys - * are cpu/type/ctx/stat (evsel is NULL). For generic metrics - * case, the keys are still evsel/cpu (type/ctx/stat are 0 or NULL). - */ - if (a->type != b->type) - return a->type - b->type; - - if (a->ctx != b->ctx) - return a->ctx - b->ctx; - - if (a->cgrp != b->cgrp) - return (char *)a->cgrp < (char *)b->cgrp ? -1 : +1; - - if (a->evsel == b->evsel) - return 0; - if ((char *)a->evsel < (char *)b->evsel) - return -1; - return +1; -} - -static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused, - const void *entry) -{ - struct saved_value *nd = malloc(sizeof(struct saved_value)); - - if (!nd) - return NULL; - memcpy(nd, entry, sizeof(struct saved_value)); - return &nd->rb_node; -} - -static void saved_value_delete(struct rblist *rblist __maybe_unused, - struct rb_node *rb_node) -{ - struct saved_value *v; - - BUG_ON(!rb_node); - v = container_of(rb_node, struct saved_value, rb_node); - free(v); -} - -static struct saved_value *saved_value_lookup(struct evsel *evsel, - int map_idx, - bool create, - enum stat_type type, - int ctx, - struct cgroup *cgrp) -{ - struct rblist *rblist; - struct rb_node *nd; - struct saved_value dm = { - .map_idx = map_idx, - .evsel = evsel, - .type = type, - .ctx = ctx, - .cgrp = cgrp, - }; - - rblist = &rt_stat.value_list; - - /* don't use context info for clock events */ - if (type == STAT_NSECS) - dm.ctx = 0; - - nd = rblist__find(rblist, &dm); - if (nd) - return container_of(nd, struct saved_value, rb_node); - if (create) { - rblist__add_node(rblist, &dm); - nd = rblist__find(rblist, &dm); - if (nd) - return container_of(nd, struct saved_value, rb_node); - } - return NULL; -} - -void perf_stat__init_shadow_stats(void) -{ - struct rblist *rblist = &rt_stat.value_list; - - rblist__init(rblist); - rblist->node_cmp = saved_value_cmp; - rblist->node_new = saved_value_new; - rblist->node_delete = saved_value_delete; -} - static int evsel_context(const struct evsel *evsel) { int ctx = 0; @@ -194,86 +70,12 @@ static int evsel_context(const struct evsel *evsel) return ctx; } -void perf_stat__reset_shadow_per_stat(void) -{ - struct rblist *rblist; - struct rb_node *pos, *next; - - rblist = &rt_stat.value_list; - next = rb_first_cached(&rblist->entries); - while (next) { - pos = next; - next = rb_next(pos); - memset(&container_of(pos, struct saved_value, rb_node)->stats, - 0, - sizeof(struct stats)); - } -} - void perf_stat__reset_shadow_stats(void) { - perf_stat__reset_shadow_per_stat(); memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats)); memset(&ru_stats, 0, sizeof(ru_stats)); } -struct runtime_stat_data { - int ctx; - struct cgroup *cgrp; -}; - -static void update_runtime_stat(enum stat_type type, - int map_idx, u64 count, - struct runtime_stat_data *rsd) -{ - struct saved_value *v = saved_value_lookup(NULL, map_idx, true, type, - rsd->ctx, rsd->cgrp); - - if (v) - update_stats(&v->stats, count); -} - -/* - * Update various tracking values we maintain to print - * more semantic information such as miss/hit ratios, - * instruction rates, etc: - */ -void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, - int aggr_idx) -{ - u64 count_ns = count; - struct runtime_stat_data rsd = { - .ctx = evsel_context(counter), - .cgrp = counter->cgrp, - }; - count *= counter->scale; - - if (evsel__is_clock(counter)) - update_runtime_stat(STAT_NSECS, aggr_idx, count_ns, &rsd); - else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) - update_runtime_stat(STAT_CYCLES, aggr_idx, count, &rsd); - else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) - update_runtime_stat(STAT_STALLED_CYCLES_FRONT, - aggr_idx, count, &rsd); - else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) - update_runtime_stat(STAT_STALLED_CYCLES_BACK, - aggr_idx, count, &rsd); - else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) - update_runtime_stat(STAT_BRANCHES, aggr_idx, count, &rsd); - else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_runtime_stat(STAT_CACHE_REFS, aggr_idx, count, &rsd); - else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) - update_runtime_stat(STAT_L1_DCACHE, aggr_idx, count, &rsd); - else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) - update_runtime_stat(STAT_L1_ICACHE, aggr_idx, count, &rsd); - else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL)) - update_runtime_stat(STAT_LL_CACHE, aggr_idx, count, &rsd); - else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB)) - update_runtime_stat(STAT_DTLB_CACHE, aggr_idx, count, &rsd); - else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) - update_runtime_stat(STAT_ITLB_CACHE, aggr_idx, count, &rsd); -} - static enum stat_type evsel__stat_type(const struct evsel *evsel) { /* Fake perf_hw_cache_op_id values for use with evsel__match. */ diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 83dc4c1f4b12..4abfd87c5352 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -648,30 +648,6 @@ void perf_stat_process_percore(struct perf_stat_config *config, struct evlist *e evsel__process_percore(evsel); } -static void evsel__update_shadow_stats(struct evsel *evsel) -{ - struct perf_stat_evsel *ps = evsel->stats; - int aggr_idx; - - if (ps->aggr == NULL) - return; - - for (aggr_idx = 0; aggr_idx < ps->nr_aggr; aggr_idx++) { - struct perf_counts_values *aggr_counts = &ps->aggr[aggr_idx].counts; - - perf_stat__update_shadow_stats(evsel, aggr_counts->val, aggr_idx); - } -} - -void perf_stat_process_shadow_stats(struct perf_stat_config *config __maybe_unused, - struct evlist *evlist) -{ - struct evsel *evsel; - - evlist__for_each_entry(evlist, evsel) - evsel__update_shadow_stats(evsel); -} - int perf_event__process_stat_event(struct perf_session *session, union perf_event *event) { diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index b01c828c3799..41204547b76b 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -157,10 +157,7 @@ typedef void (*print_metric_t)(struct perf_stat_config *config, const char *fmt, double val); typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx); -void perf_stat__init_shadow_stats(void); void perf_stat__reset_shadow_stats(void); -void perf_stat__reset_shadow_per_stat(void); -void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int aggr_idx); struct perf_stat_output_ctx { void *ctx; print_metric_t print_metric; @@ -189,7 +186,6 @@ int perf_stat_process_counter(struct perf_stat_config *config, struct evsel *counter); void perf_stat_merge_counters(struct perf_stat_config *config, struct evlist *evlist); void perf_stat_process_percore(struct perf_stat_config *config, struct evlist *evlist); -void perf_stat_process_shadow_stats(struct perf_stat_config *config, struct evlist *evlist); struct perf_tool; union perf_event; -- cgit v1.2.3-70-g09d2 From ce5b85906cd6a14b00f6b2c09d066554d2c13abd Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:36 -0800 Subject: perf stat: Modify the group test Currently nr_members is 0 for an event with no group, however, they are always a leader of their own group. A later change will make that count 1 because the event is its own leader. Make the find_stat logic consistent with this, an improvement suggested by Namhyung Kim. Suggested-by: Namhyung Kim Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-shadow.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util/stat-shadow.c') diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index ef85f1ae1ab2..eeccab6751d7 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -163,7 +163,7 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type continue; /* Ignore evsels that are part of different groups. */ - if (evsel->core.leader->nr_members && + if (evsel->core.leader->nr_members > 1 && evsel->core.leader != cur->core.leader) continue; /* Ignore evsels with mismatched modifiers. */ -- cgit v1.2.3-70-g09d2