diff options
Diffstat (limited to 'tools/perf')
26 files changed, 109 insertions, 43 deletions
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 3f72d8e261f3..bd50cdff08a8 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -33,6 +33,10 @@ OPTIONS - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a hexadecimal event descriptor. + - a symbolic or raw PMU event followed by an optional colon + and a list of event modifiers, e.g., cpu-cycles:p. See the + linkperf:perf-list[1] man page for details on event modifiers. + - a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where 'param1', 'param2', etc are defined as formats for the PMU in /sys/bus/event_source/devices/<pmu>/format/*. diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index c9bfefc051fb..db420dd75e43 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -39,6 +39,10 @@ report:: - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a hexadecimal event descriptor. + - a symbolic or raw PMU event followed by an optional colon + and a list of event modifiers, e.g., cpu-cycles:p. See the + linkperf:perf-list[1] man page for details on event modifiers. + - a symbolically formed event like 'pmu/param1=0x3,param2/' where param1 and param2 are defined as formats for the PMU in /sys/bus/event_source/devices/<pmu>/format/* @@ -416,6 +420,9 @@ counts for all hardware threads in a core but show the sum counts per hardware thread. This is essentially a replacement for the any bit and convenient for post processing. +--summary:: +Print summary for interval mode (-I). + EXAMPLES -------- diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c index 8d624aea1c5e..b2924e3181dc 100644 --- a/tools/perf/bench/synthesize.c +++ b/tools/perf/bench/synthesize.c @@ -162,8 +162,8 @@ static int do_run_multi_threaded(struct target *target, init_stats(&event_stats); for (i = 0; i < multi_iterations; i++) { session = perf_session__new(NULL, false, NULL); - if (!session) - return -ENOMEM; + if (IS_ERR(session)) + return PTR_ERR(session); atomic_set(&event_count, 0); gettimeofday(&start, NULL); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f91352f847c0..772f1057647f 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -2452,7 +2452,7 @@ static struct option __record_options[] = { OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize, "synthesize non-sample events at the end of output"), OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"), - OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "record bpf events"), + OPT_BOOLEAN(0, "no-bpf-event", &record.opts.no_bpf_event, "do not record bpf events"), OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq, "Fail if the specified frequency can't be used"), OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'", diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index ece1cddfcd7c..3c74c9c0f3c3 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1332,6 +1332,9 @@ int cmd_report(int argc, const char **argv) if (report.mmaps_mode) report.tasks_mode = true; + if (dump_trace) + report.tool.ordered_events = false; + if (quiet) perf_quiet_option(); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 0c7d599fa555..e6fc297cee91 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -2584,7 +2584,8 @@ static int timehist_sched_change_event(struct perf_tool *tool, } if (!sched->idle_hist || thread->tid == 0) { - timehist_update_runtime_stats(tr, t, tprev); + if (!cpu_list || test_bit(sample->cpu, cpu_bitmap)) + timehist_update_runtime_stats(tr, t, tprev); if (sched->idle_hist) { struct idle_thread_runtime *itr = (void *)tr; @@ -2857,6 +2858,9 @@ static void timehist_print_summary(struct perf_sched *sched, printf("\nIdle stats:\n"); for (i = 0; i < idle_max_cpu; ++i) { + if (cpu_list && !test_bit(i, cpu_bitmap)) + continue; + t = idle_threads[i]; if (!t) continue; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 483a28ef4ec4..fddc97cac984 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -404,7 +404,7 @@ static void read_counters(struct timespec *rs) { struct evsel *counter; - if (!stat_config.summary && (read_affinity_counters(rs) < 0)) + if (!stat_config.stop_read_counter && (read_affinity_counters(rs) < 0)) return; evlist__for_each_entry(evsel_list, counter) { @@ -897,9 +897,9 @@ try_again_reset: if (stat_config.walltime_run_table) stat_config.walltime_run[run_idx] = t1 - t0; - if (interval) { + if (interval && stat_config.summary) { stat_config.interval = 0; - stat_config.summary = true; + stat_config.stop_read_counter = true; init_stats(&walltime_nsecs_stats); update_stats(&walltime_nsecs_stats, t1 - t0); @@ -1164,6 +1164,8 @@ static struct option stat_options[] = { "Use with 'percore' event qualifier to show the event " "counts of one hardware thread by sum up total hardware " "threads of same physical core"), + OPT_BOOLEAN(0, "summary", &stat_config.summary, + "print summary for interval mode"), #ifdef HAVE_LIBPFM OPT_CALLBACK(0, "pfm-events", &evsel_list, "event", "libpfm4 event selector. use 'perf list' to list available events", diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 994c230027bb..7c64134472c7 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1746,6 +1746,7 @@ int cmd_top(int argc, const char **argv) goto out_delete_evlist; } +#ifdef HAVE_LIBBPF_SUPPORT if (!top.record_opts.no_bpf_event) { top.sb_evlist = evlist__new(); @@ -1759,6 +1760,7 @@ int cmd_top(int argc, const char **argv) goto out_delete_evlist; } } +#endif if (perf_evlist__start_sb_thread(top.sb_evlist, target)) { pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n"); diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index fa86c5f997cc..fc9c158bfa13 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -137,7 +137,7 @@ static char *fixregex(char *s) return s; /* allocate space for a new string */ - fixed = (char *) malloc(len + 1); + fixed = (char *) malloc(len + esc_count + 1); if (!fixed) return NULL; diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 5d20bf8397f0..cd77e334e577 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -197,7 +197,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void), perf_mmap__read_done(&md->core); } - if (count != expect) { + if (count != expect * evlist->core.nr_entries) { pr_debug("BPF filter result incorrect, expected %d, got %d samples\n", expect, count); goto out_delete_evlist; } diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 7f9f87a470c3..aae0fd9045c1 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -719,7 +719,7 @@ static int test__group2(struct evlist *evlist) TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel)); @@ -842,7 +842,7 @@ static int test__group3(struct evlist *evlist __maybe_unused) TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); - TEST_ASSERT_VAL("wrong exclude guest", !evsel->core.attr.exclude_guest); + TEST_ASSERT_VAL("wrong exclude guest", evsel->core.attr.exclude_guest); TEST_ASSERT_VAL("wrong exclude host", !evsel->core.attr.exclude_host); TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip); TEST_ASSERT_VAL("wrong leader", evsel__is_group_leader(evsel)); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index fc0838a7abc2..23db8acc492d 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -70,6 +70,9 @@ static struct pmu_event pme_test[] = { { .metric_expr = "1/m3", .metric_name = "M3", +}, +{ + .name = NULL, } }; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index be9c4c0549bc..a07626f07208 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -3629,8 +3629,8 @@ int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, { int nr_entries = evlist->core.nr_entries; -single_entry: if (perf_evlist__single_entry(evlist)) { +single_entry: { struct evsel *first = evlist__first(evlist); return perf_evsel__hists_browse(first, nr_entries, help, @@ -3638,6 +3638,7 @@ single_entry: env, warn_lost_event, annotation_opts); } + } if (symbol_conf.event_group) { struct evsel *pos; diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index 302a14d0aca9..93e063f22be5 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -182,15 +182,15 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) if (payload & BIT(EV_TLB_ACCESS)) decoder->record.type |= ARM_SPE_TLB_ACCESS; - if ((idx == 1 || idx == 2 || idx == 3) && + if ((idx == 2 || idx == 4 || idx == 8) && (payload & BIT(EV_LLC_MISS))) decoder->record.type |= ARM_SPE_LLC_MISS; - if ((idx == 1 || idx == 2 || idx == 3) && + if ((idx == 2 || idx == 4 || idx == 8) && (payload & BIT(EV_LLC_ACCESS))) decoder->record.type |= ARM_SPE_LLC_ACCESS; - if ((idx == 1 || idx == 2 || idx == 3) && + if ((idx == 2 || idx == 4 || idx == 8) && (payload & BIT(EV_REMOTE_ACCESS))) decoder->record.type |= ARM_SPE_REMOTE_ACCESS; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index c283223fb31f..a2a369e2fbb6 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -1344,8 +1344,15 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm, attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR; } - if (etm->synth_opts.last_branch) + if (etm->synth_opts.last_branch) { attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + /* + * We don't use the hardware index, but the sample generation + * code uses the new format branch_stack with this field, + * so the event attributes must indicate that it's present. + */ + attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX; + } if (etm->synth_opts.instructions) { attr.config = PERF_COUNT_HW_INSTRUCTIONS; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 2a8d245351e7..0af4e81c46e2 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -3017,8 +3017,15 @@ static int intel_pt_synth_events(struct intel_pt *pt, if (pt->synth_opts.callchain) attr.sample_type |= PERF_SAMPLE_CALLCHAIN; - if (pt->synth_opts.last_branch) + if (pt->synth_opts.last_branch) { attr.sample_type |= PERF_SAMPLE_BRANCH_STACK; + /* + * We don't use the hardware index, but the sample generation + * code uses the new format branch_stack with this field, + * so the event attributes must indicate that it's present. + */ + attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX; + } if (pt->synth_opts.instructions) { attr.config = PERF_COUNT_HW_INSTRUCTIONS; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 208b813e00ea..85587de027a5 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -736,12 +736,6 @@ int machine__process_switch_event(struct machine *machine __maybe_unused, return 0; } -static int is_bpf_image(const char *name) -{ - return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 || - strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0; -} - static int machine__process_ksymbol_register(struct machine *machine, union perf_event *event, struct perf_sample *sample __maybe_unused) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 1d7210804639..cc0faf8f1321 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -267,6 +267,22 @@ bool __map__is_bpf_prog(const struct map *map) return name && (strstr(name, "bpf_prog_") == name); } +bool __map__is_bpf_image(const struct map *map) +{ + const char *name; + + if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) + return true; + + /* + * If PERF_RECORD_KSYMBOL is not included, the dso will not have + * type of DSO_BINARY_TYPE__BPF_IMAGE. In such cases, we can + * guess the type based on name. + */ + name = map->dso->short_name; + return name && is_bpf_image(name); +} + bool __map__is_ool(const struct map *map) { return map->dso && map->dso->binary_type == DSO_BINARY_TYPE__OOL; diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 9e312ae2d656..c2f5d28fe73a 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -147,12 +147,14 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, bool __map__is_kernel(const struct map *map); bool __map__is_extra_kernel_map(const struct map *map); bool __map__is_bpf_prog(const struct map *map); +bool __map__is_bpf_image(const struct map *map); bool __map__is_ool(const struct map *map); static inline bool __map__is_kmodule(const struct map *map) { return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) && - !__map__is_bpf_prog(map) && !__map__is_ool(map); + !__map__is_bpf_prog(map) && !__map__is_ool(map) && + !__map__is_bpf_image(map); } bool map__has_symbols(const struct map *map); @@ -164,4 +166,9 @@ static inline bool is_entry_trampoline(const char *name) return !strcmp(name, ENTRY_TRAMPOLINE_NAME); } +static inline bool is_bpf_image(const char *name) +{ + return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) == 0 || + strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1) == 0; +} #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 9f7260e69113..c4d2394e2b2d 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -37,6 +37,7 @@ #include "util/evsel_config.h" #include "util/event.h" #include "util/pfm.h" +#include "perf.h" #define MAX_NAME_LEN 100 @@ -1533,19 +1534,23 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel = __add_event(list, &parse_state->idx, &attr, true, get_config_name(head_config), pmu, &config_terms, auto_merge_stats, NULL); - if (evsel) { - evsel->unit = info.unit; - evsel->scale = info.scale; - evsel->per_pkg = info.per_pkg; - evsel->snapshot = info.snapshot; - evsel->metric_expr = info.metric_expr; - evsel->metric_name = info.metric_name; - evsel->pmu_name = name ? strdup(name) : NULL; - evsel->use_uncore_alias = use_uncore_alias; - evsel->percore = config_term_percore(&evsel->config_terms); - } + if (!evsel) + return -ENOMEM; + + evsel->pmu_name = name ? strdup(name) : NULL; + evsel->use_uncore_alias = use_uncore_alias; + evsel->percore = config_term_percore(&evsel->config_terms); - return evsel ? 0 : -ENOMEM; + if (parse_state->fake_pmu) + return 0; + + evsel->unit = info.unit; + evsel->scale = info.scale; + evsel->per_pkg = info.per_pkg; + evsel->snapshot = info.snapshot; + evsel->metric_expr = info.metric_expr; + evsel->metric_name = info.metric_name; + return 0; } int parse_events_multi_pmu_add(struct parse_events_state *parse_state, @@ -1794,6 +1799,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str, if (*str == 'u') { if (!exclude) exclude = eu = ek = eh = 1; + if (!exclude_GH && !perf_guest) + eG = 1; eu = 0; } else if (*str == 'k') { if (!exclude) diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index b9fb91fdc5de..645bf4f1859f 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -511,7 +511,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE ':' PE_MODIFIER_BP sep_dc list = alloc_list(); ABORT_ON(!list); err = parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, $6, $4); + (void *)(uintptr_t) $2, $6, $4); free($6); if (err) { free(list); @@ -528,7 +528,7 @@ PE_PREFIX_MEM PE_VALUE '/' PE_VALUE sep_dc list = alloc_list(); ABORT_ON(!list); if (parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, NULL, $4)) { + (void *)(uintptr_t) $2, NULL, $4)) { free(list); YYABORT; } @@ -544,7 +544,7 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc list = alloc_list(); ABORT_ON(!list); err = parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, $4, 0); + (void *)(uintptr_t) $2, $4, 0); free($4); if (err) { free(list); @@ -561,7 +561,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc list = alloc_list(); ABORT_ON(!list); if (parse_events_add_breakpoint(list, &parse_state->idx, - (void *) $2, NULL, 0)) { + (void *)(uintptr_t) $2, NULL, 0)) { free(list); YYABORT; } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index ffbc9d35a383..7a5f03764702 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -87,7 +87,7 @@ static int perf_session__process_compressed_event(struct perf_session *session, session->decomp_last = decomp; } - pr_debug("decomp (B): %ld to %ld\n", src_size, decomp_size); + pr_debug("decomp (B): %zd to %zd\n", src_size, decomp_size); return 0; } diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 57d0706e1330..493ec372fdec 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -117,7 +117,7 @@ static void aggr_printout(struct perf_stat_config *config, cpu_map__id_to_die(id), config->csv_output ? 0 : -3, cpu_map__id_to_cpu(id), config->csv_sep); - } else { + } else if (id > -1) { fprintf(config->output, "CPU%*d%s", config->csv_output ? 0 : -7, evsel__cpus(evsel)->map[id], diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index f8778cffd941..aa3bed48511b 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -113,6 +113,7 @@ struct perf_stat_config { bool summary; bool metric_no_group; bool metric_no_merge; + bool stop_read_counter; FILE *output; unsigned int interval; unsigned int timeout; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 1f5fcb828a21..5151a8c0b791 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -663,6 +663,7 @@ static bool symbol__is_idle(const char *name) "exit_idle", "mwait_idle", "mwait_idle_with_hints", + "mwait_idle_with_hints.constprop.0", "poll_idle", "ppc64_runlatch_off", "pseries_dedicated_idle_sleep", diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c index d2202392ffdb..48dd2b018c47 100644 --- a/tools/perf/util/zstd.c +++ b/tools/perf/util/zstd.c @@ -99,7 +99,7 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size while (input.pos < input.size) { ret = ZSTD_decompressStream(data->dstream, &output, &input); if (ZSTD_isError(ret)) { - pr_err("failed to decompress (B): %ld -> %ld, dst_size %ld : %s\n", + pr_err("failed to decompress (B): %zd -> %zd, dst_size %zd : %s\n", src_size, output.size, dst_size, ZSTD_getErrorName(ret)); break; } |