diff options
Diffstat (limited to 'tools/perf/util/session.c')
| -rw-r--r-- | tools/perf/util/session.c | 330 |
1 files changed, 281 insertions, 49 deletions
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index dbaf07bf6c5f..4236503c8f6c 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -12,6 +12,7 @@ #include <sys/types.h> #include <sys/mman.h> #include <perf/cpumap.h> +#include <perf/event.h> #include "map_symbol.h" #include "branch.h" @@ -37,6 +38,7 @@ #include "arch/common.h" #include "units.h" #include "annotate.h" +#include "perf.h" #include <internal/lib.h> static int perf_session__deliver_event(struct perf_session *session, @@ -136,7 +138,8 @@ static int ordered_events__deliver_event(struct ordered_events *oe, struct perf_session *__perf_session__new(struct perf_data *data, struct perf_tool *tool, - bool trace_event_repipe) + bool trace_event_repipe, + struct perf_env *host_env) { int ret = -ENOMEM; struct perf_session *session = zalloc(sizeof(*session)); @@ -175,7 +178,7 @@ struct perf_session *__perf_session__new(struct perf_data *data, perf_session__set_comm_exec(session); } - evlist__init_trace_event_sample_raw(session->evlist); + evlist__init_trace_event_sample_raw(session->evlist, &session->header.env); /* Open the directory data. */ if (data->is_dir) { @@ -189,8 +192,11 @@ struct perf_session *__perf_session__new(struct perf_data *data, symbol_conf.kallsyms_name = perf_data__kallsyms_name(data); } } else { - session->machines.host.env = &perf_env; + assert(host_env != NULL); + session->machines.host.env = host_env; } + if (session->evlist) + session->evlist->session = session; session->machines.host.single_address_space = perf_env__single_address_space(session->machines.host.env); @@ -714,6 +720,7 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_CGROUP] = perf_event__cgroup_swap, [PERF_RECORD_TEXT_POKE] = perf_event__text_poke_swap, [PERF_RECORD_AUX_OUTPUT_HW_ID] = perf_event__all64_swap, + [PERF_RECORD_CALLCHAIN_DEFERRED] = perf_event__all64_swap, [PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap, [PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap, [PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap, @@ -848,6 +855,9 @@ static void callchain__printf(struct evsel *evsel, for (i = 0; i < callchain->nr; i++) printf("..... %2d: %016" PRIx64 "\n", i, callchain->ips[i]); + + if (sample->deferred_callchain) + printf("...... (deferred)\n"); } static void branch_stack__printf(struct perf_sample *sample, @@ -949,7 +959,12 @@ static void regs__printf(const char *type, struct regs_dump *regs, const char *a static void regs_user__printf(struct perf_sample *sample, const char *arch) { - struct regs_dump *user_regs = &sample->user_regs; + struct regs_dump *user_regs; + + if (!sample->user_regs) + return; + + user_regs = perf_sample__user_regs(sample); if (user_regs->regs) regs__printf("user", user_regs, arch); @@ -957,7 +972,12 @@ static void regs_user__printf(struct perf_sample *sample, const char *arch) static void regs_intr__printf(struct perf_sample *sample, const char *arch) { - struct regs_dump *intr_regs = &sample->intr_regs; + struct regs_dump *intr_regs; + + if (!sample->intr_regs) + return; + + intr_regs = perf_sample__intr_regs(sample); if (intr_regs->regs) regs__printf("intr", intr_regs, arch); @@ -1083,7 +1103,7 @@ static void dump_sample(struct evsel *evsel, union perf_event *event, printf("... weight: %" PRIu64 "", sample->weight); if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) { printf(",0x%"PRIx16"", sample->ins_lat); - printf(",0x%"PRIx16"", sample->p_stage_cyc); + printf(",0x%"PRIx16"", sample->weight3); } printf("\n"); } @@ -1107,6 +1127,19 @@ static void dump_sample(struct evsel *evsel, union perf_event *event, sample_read__printf(sample, evsel->core.attr.read_format); } +static void dump_deferred_callchain(struct evsel *evsel, union perf_event *event, + struct perf_sample *sample) +{ + if (!dump_trace) + return; + + printf("(IP, 0x%x): %d/%d: %#" PRIx64 "\n", + event->header.misc, sample->pid, sample->tid, sample->deferred_cookie); + + if (evsel__has_callchain(evsel)) + callchain__printf(evsel, sample); +} + static void dump_read(struct evsel *evsel, union perf_event *event) { struct perf_record_read *read_event = &event->read; @@ -1171,18 +1204,24 @@ static int deliver_sample_value(struct evlist *evlist, union perf_event *event, struct perf_sample *sample, struct sample_read_value *v, - struct machine *machine) + struct machine *machine, + bool per_thread) { struct perf_sample_id *sid = evlist__id2sid(evlist, v->id); struct evsel *evsel; + u64 *storage = NULL; if (sid) { + storage = perf_sample_id__get_period_storage(sid, sample->tid, per_thread); + } + + if (storage) { sample->id = v->id; - sample->period = v->value - sid->period; - sid->period = v->value; + sample->period = v->value - *storage; + *storage = v->value; } - if (!sid || sid->evsel == NULL) { + if (!storage || sid->evsel == NULL) { ++evlist->stats.nr_unknown_id; return 0; } @@ -1203,17 +1242,19 @@ static int deliver_sample_group(struct evlist *evlist, union perf_event *event, struct perf_sample *sample, struct machine *machine, - u64 read_format) + u64 read_format, + bool per_thread) { int ret = -EINVAL; struct sample_read_value *v = sample->read.group.values; if (tool->dont_split_sample_group) - return deliver_sample_value(evlist, tool, event, sample, v, machine); + return deliver_sample_value(evlist, tool, event, sample, v, machine, + per_thread); sample_read_group__for_each(v, sample->read.group.nr, read_format) { ret = deliver_sample_value(evlist, tool, event, sample, v, - machine); + machine, per_thread); if (ret) break; } @@ -1228,6 +1269,7 @@ static int evlist__deliver_sample(struct evlist *evlist, const struct perf_tool /* We know evsel != NULL. */ u64 sample_type = evsel->core.attr.sample_type; u64 read_format = evsel->core.attr.read_format; + bool per_thread = perf_evsel__attr_has_per_thread_sample_period(&evsel->core); /* Standard sample delivery. */ if (!(sample_type & PERF_SAMPLE_READ)) @@ -1236,10 +1278,111 @@ static int evlist__deliver_sample(struct evlist *evlist, const struct perf_tool /* For PERF_SAMPLE_READ we have either single or group mode. */ if (read_format & PERF_FORMAT_GROUP) return deliver_sample_group(evlist, tool, event, sample, - machine, read_format); + machine, read_format, per_thread); else return deliver_sample_value(evlist, tool, event, sample, - &sample->read.one, machine); + &sample->read.one, machine, + per_thread); +} + +/* + * Samples with deferred callchains should wait for the next matching + * PERF_RECORD_CALLCHAIN_RECORD entries. Keep the events in a list and + * deliver them once it finds the callchains. + */ +struct deferred_event { + struct list_head list; + union perf_event *event; +}; + +/* + * This is called when a deferred callchain record comes up. Find all matching + * samples, merge the callchains and process them. + */ +static int evlist__deliver_deferred_callchain(struct evlist *evlist, + const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct deferred_event *de, *tmp; + struct evsel *evsel; + int ret = 0; + + if (!tool->merge_deferred_callchains) { + evsel = evlist__id2evsel(evlist, sample->id); + return tool->callchain_deferred(tool, event, sample, + evsel, machine); + } + + list_for_each_entry_safe(de, tmp, &evlist->deferred_samples, list) { + struct perf_sample orig_sample; + + ret = evlist__parse_sample(evlist, de->event, &orig_sample); + if (ret < 0) { + pr_err("failed to parse original sample\n"); + break; + } + + if (sample->tid != orig_sample.tid) + continue; + + if (event->callchain_deferred.cookie == orig_sample.deferred_cookie) + sample__merge_deferred_callchain(&orig_sample, sample); + else + orig_sample.deferred_callchain = false; + + evsel = evlist__id2evsel(evlist, orig_sample.id); + ret = evlist__deliver_sample(evlist, tool, de->event, + &orig_sample, evsel, machine); + + if (orig_sample.deferred_callchain) + free(orig_sample.callchain); + + list_del(&de->list); + free(de->event); + free(de); + + if (ret) + break; + } + return ret; +} + +/* + * This is called at the end of the data processing for the session. Flush the + * remaining samples as there's no hope for matching deferred callchains. + */ +static int session__flush_deferred_samples(struct perf_session *session, + const struct perf_tool *tool) +{ + struct evlist *evlist = session->evlist; + struct machine *machine = &session->machines.host; + struct deferred_event *de, *tmp; + struct evsel *evsel; + int ret = 0; + + list_for_each_entry_safe(de, tmp, &evlist->deferred_samples, list) { + struct perf_sample sample; + + ret = evlist__parse_sample(evlist, de->event, &sample); + if (ret < 0) { + pr_err("failed to parse original sample\n"); + break; + } + + evsel = evlist__id2evsel(evlist, sample.id); + ret = evlist__deliver_sample(evlist, tool, de->event, + &sample, evsel, machine); + + list_del(&de->list); + free(de->event); + free(de); + + if (ret) + break; + } + return ret; } static int machines__deliver_event(struct machines *machines, @@ -1270,6 +1413,22 @@ static int machines__deliver_event(struct machines *machines, return 0; } dump_sample(evsel, event, sample, perf_env__arch(machine->env)); + if (sample->deferred_callchain && tool->merge_deferred_callchains) { + struct deferred_event *de = malloc(sizeof(*de)); + size_t sz = event->header.size; + + if (de == NULL) + return -ENOMEM; + + de->event = malloc(sz); + if (de->event == NULL) { + free(de); + return -ENOMEM; + } + memcpy(de->event, event, sz); + list_add_tail(&de->list, &evlist->deferred_samples); + return 0; + } return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); @@ -1327,6 +1486,10 @@ static int machines__deliver_event(struct machines *machines, return tool->text_poke(tool, event, sample, machine); case PERF_RECORD_AUX_OUTPUT_HW_ID: return tool->aux_output_hw_id(tool, event, sample, machine); + case PERF_RECORD_CALLCHAIN_DEFERRED: + dump_deferred_callchain(evsel, event, sample); + return evlist__deliver_deferred_callchain(evlist, tool, event, + sample, machine); default: ++evlist->stats.nr_unknown_events; return -1; @@ -1340,25 +1503,30 @@ static int perf_session__deliver_event(struct perf_session *session, const char *file_path) { struct perf_sample sample; - int ret = evlist__parse_sample(session->evlist, event, &sample); + int ret; + perf_sample__init(&sample, /*all=*/false); + ret = evlist__parse_sample(session->evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); - return ret; + goto out; } ret = auxtrace__process_event(session, event, &sample, tool); if (ret < 0) - return ret; - if (ret > 0) - return 0; + goto out; + if (ret > 0) { + ret = 0; + goto out; + } ret = machines__deliver_event(&session->machines, session->evlist, event, &sample, tool, file_offset, file_path); if (dump_trace && sample.aux_sample.size) auxtrace__dump_auxtrace_sample(session, &sample); - +out: + perf_sample__exit(&sample); return ret; } @@ -1369,11 +1537,14 @@ static s64 perf_session__process_user_event(struct perf_session *session, { struct ordered_events *oe = &session->ordered_events; const struct perf_tool *tool = session->tool; - struct perf_sample sample = { .time = 0, }; + struct perf_sample sample; int fd = perf_data__fd(session->data); - int err; + s64 err; - if (event->header.type != PERF_RECORD_COMPRESSED || perf_tool__compressed_is_stub(tool)) + perf_sample__init(&sample, /*all=*/true); + if ((event->header.type != PERF_RECORD_COMPRESSED && + event->header.type != PERF_RECORD_COMPRESSED2) || + perf_tool__compressed_is_stub(tool)) dump_event(session->evlist, event, file_offset, &sample, file_path); /* These events are processed right away */ @@ -1384,15 +1555,17 @@ static s64 perf_session__process_user_event(struct perf_session *session, perf_session__set_id_hdr_size(session); perf_session__set_comm_exec(session); } - return err; + break; case PERF_RECORD_EVENT_UPDATE: - return tool->event_update(tool, event, &session->evlist); + err = tool->event_update(tool, event, &session->evlist); + break; case PERF_RECORD_HEADER_EVENT_TYPE: /* * Deprecated, but we need to handle it for sake * of old data files create in pipe mode. */ - return 0; + err = 0; + break; case PERF_RECORD_HEADER_TRACING_DATA: /* * Setup for reading amidst mmap, but only when we @@ -1401,15 +1574,20 @@ static s64 perf_session__process_user_event(struct perf_session *session, */ if (!perf_data__is_pipe(session->data)) lseek(fd, file_offset, SEEK_SET); - return tool->tracing_data(session, event); + err = tool->tracing_data(tool, session, event); + break; case PERF_RECORD_HEADER_BUILD_ID: - return tool->build_id(session, event); + err = tool->build_id(tool, session, event); + break; case PERF_RECORD_FINISHED_ROUND: - return tool->finished_round(tool, event, oe); + err = tool->finished_round(tool, event, oe); + break; case PERF_RECORD_ID_INDEX: - return tool->id_index(session, event); + err = tool->id_index(tool, session, event); + break; case PERF_RECORD_AUXTRACE_INFO: - return tool->auxtrace_info(session, event); + err = tool->auxtrace_info(tool, session, event); + break; case PERF_RECORD_AUXTRACE: /* * Setup for reading amidst mmap, but only when we @@ -1418,35 +1596,52 @@ static s64 perf_session__process_user_event(struct perf_session *session, */ if (!perf_data__is_pipe(session->data)) lseek(fd, file_offset + event->header.size, SEEK_SET); - return tool->auxtrace(session, event); + err = tool->auxtrace(tool, session, event); + break; case PERF_RECORD_AUXTRACE_ERROR: perf_session__auxtrace_error_inc(session, event); - return tool->auxtrace_error(session, event); + err = tool->auxtrace_error(tool, session, event); + break; case PERF_RECORD_THREAD_MAP: - return tool->thread_map(session, event); + err = tool->thread_map(tool, session, event); + break; case PERF_RECORD_CPU_MAP: - return tool->cpu_map(session, event); + err = tool->cpu_map(tool, session, event); + break; case PERF_RECORD_STAT_CONFIG: - return tool->stat_config(session, event); + err = tool->stat_config(tool, session, event); + break; case PERF_RECORD_STAT: - return tool->stat(session, event); + err = tool->stat(tool, session, event); + break; case PERF_RECORD_STAT_ROUND: - return tool->stat_round(session, event); + err = tool->stat_round(tool, session, event); + break; case PERF_RECORD_TIME_CONV: session->time_conv = event->time_conv; - return tool->time_conv(session, event); + err = tool->time_conv(tool, session, event); + break; case PERF_RECORD_HEADER_FEATURE: - return tool->feature(session, event); + err = tool->feature(tool, session, event); + break; case PERF_RECORD_COMPRESSED: - err = tool->compressed(session, event, file_offset, file_path); + case PERF_RECORD_COMPRESSED2: + err = tool->compressed(tool, session, event, file_offset, file_path); if (err) dump_event(session->evlist, event, file_offset, &sample, file_path); - return err; + break; case PERF_RECORD_FINISHED_INIT: - return tool->finished_init(session, event); + err = tool->finished_init(tool, session, event); + break; + case PERF_RECORD_BPF_METADATA: + err = tool->bpf_metadata(tool, session, event); + break; default: - return -EINVAL; + err = -EINVAL; + break; } + perf_sample__exit(&sample); + return err; } int perf_session__deliver_synth_event(struct perf_session *session, @@ -1592,8 +1787,17 @@ static s64 perf_session__process_event(struct perf_session *session, if (session->header.needs_swap) event_swap(event, evlist__sample_id_all(evlist)); - if (event->header.type >= PERF_RECORD_HEADER_MAX) - return -EINVAL; + if (event->header.type >= PERF_RECORD_HEADER_MAX) { + /* perf should not support unaligned event, stop here. */ + if (event->header.size % sizeof(u64)) + return -EINVAL; + + /* This perf is outdated and does not support the latest event type. */ + ui__warning("Unsupported header type %u, please consider updating perf.\n", + event->header.type); + /* Skip unsupported event by returning its size. */ + return event->header.size; + } events_stats__inc(&evlist->stats, event->header.type); @@ -1876,6 +2080,9 @@ done: err = ordered_events__flush(oe, OE_FLUSH__FINAL); if (err) goto out_err; + err = session__flush_deferred_samples(session, tool); + if (err) + goto out_err; err = auxtrace__flush_events(session, tool); if (err) goto out_err; @@ -2222,6 +2429,9 @@ static int __perf_session__process_events(struct perf_session *session) err = auxtrace__flush_events(session, tool); if (err) goto out_err; + err = session__flush_deferred_samples(session, tool); + if (err) + goto out_err; err = perf_session__flush_thread_stacks(session); out_err: ui_progress__finish(); @@ -2342,6 +2552,10 @@ static int __perf_session__process_dir_events(struct perf_session *session) if (ret) goto out_err; + ret = session__flush_deferred_samples(session, tool); + if (ret) + goto out_err; + ret = perf_session__flush_thread_stacks(session); out_err: ui_progress__finish(); @@ -2392,6 +2606,18 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg) return false; } +bool perf_session__has_switch_events(struct perf_session *session) +{ + struct evsel *evsel; + + evlist__for_each_entry(session->evlist, evsel) { + if (evsel->core.attr.context_switch) + return true; + } + + return false; +} + int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, u64 addr) { char *bracket; @@ -2483,7 +2709,7 @@ int perf_session__cpu_bitmap(struct perf_session *session, { int i, err = -1; struct perf_cpu_map *map; - int nr_cpus = min(session->header.env.nr_cpus_avail, MAX_NR_CPUS); + int nr_cpus = min(perf_session__env(session)->nr_cpus_avail, MAX_NR_CPUS); struct perf_cpu cpu; for (i = 0; i < PERF_TYPE_MAX; ++i) { @@ -2568,7 +2794,8 @@ static int perf_session__set_guest_cpu(struct perf_session *session, pid_t pid, return 0; } -int perf_event__process_id_index(struct perf_session *session, +int perf_event__process_id_index(const struct perf_tool *tool __maybe_unused, + struct perf_session *session, union perf_event *event) { struct evlist *evlist = session->evlist; @@ -2672,3 +2899,8 @@ int perf_session__dsos_hit_all(struct perf_session *session) return 0; } + +struct perf_env *perf_session__env(struct perf_session *session) +{ + return &session->header.env; +} |