--- zzzz-none-000/linux-3.10.107/tools/perf/util/session.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/tools/perf/util/session.c 2021-02-04 17:41:59.000000000 +0000 @@ -1,4 +1,5 @@ #include +#include #include #include @@ -12,72 +13,45 @@ #include "sort.h" #include "util.h" #include "cpumap.h" -#include "event-parse.h" #include "perf_regs.h" -#include "vdso.h" +#include "asm/bug.h" +#include "auxtrace.h" +#include "thread-stack.h" -static int perf_session__open(struct perf_session *self, bool force) -{ - struct stat input_stat; - - if (!strcmp(self->filename, "-")) { - self->fd_pipe = true; - self->fd = STDIN_FILENO; - - if (perf_session__read_header(self, self->fd) < 0) - pr_err("incompatible file format (rerun with -v to learn more)"); - - return 0; - } - - self->fd = open(self->filename, O_RDONLY); - if (self->fd < 0) { - int err = errno; - - pr_err("failed to open %s: %s", self->filename, strerror(err)); - if (err == ENOENT && !strcmp(self->filename, "perf.data")) - pr_err(" (try 'perf record' first)"); - pr_err("\n"); - return -errno; - } +static int perf_session__deliver_event(struct perf_session *session, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool, + u64 file_offset); - if (fstat(self->fd, &input_stat) < 0) - goto out_close; +static int perf_session__open(struct perf_session *session) +{ + struct perf_data_file *file = session->file; - if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) { - pr_err("file %s not owned by current user or root\n", - self->filename); - goto out_close; + if (perf_session__read_header(session) < 0) { + pr_err("incompatible file format (rerun with -v to learn more)\n"); + return -1; } - if (!input_stat.st_size) { - pr_info("zero-sized file (%s), nothing to do!\n", - self->filename); - goto out_close; - } + if (perf_data_file__is_pipe(file)) + return 0; - if (perf_session__read_header(self, self->fd) < 0) { - pr_err("incompatible file format (rerun with -v to learn more)"); - goto out_close; + if (!perf_evlist__valid_sample_type(session->evlist)) { + pr_err("non matching sample_type\n"); + return -1; } - if (!perf_evlist__valid_sample_type(self->evlist)) { - pr_err("non matching sample_type"); - goto out_close; + if (!perf_evlist__valid_sample_id_all(session->evlist)) { + pr_err("non matching sample_id_all\n"); + return -1; } - if (!perf_evlist__valid_sample_id_all(self->evlist)) { - pr_err("non matching sample_id_all"); - goto out_close; + if (!perf_evlist__valid_read_format(session->evlist)) { + pr_err("non matching read_format\n"); + return -1; } - self->size = input_stat.st_size; return 0; - -out_close: - close(self->fd); - self->fd = -1; - return -1; } void perf_session__set_id_hdr_size(struct perf_session *session) @@ -87,77 +61,110 @@ machines__set_id_hdr_size(&session->machines, id_hdr_size); } -int perf_session__create_kernel_maps(struct perf_session *self) +int perf_session__create_kernel_maps(struct perf_session *session) { - int ret = machine__create_kernel_maps(&self->machines.host); + int ret = machine__create_kernel_maps(&session->machines.host); if (ret >= 0) - ret = machines__create_guest_kernel_maps(&self->machines); + ret = machines__create_guest_kernel_maps(&session->machines); return ret; } -static void perf_session__destroy_kernel_maps(struct perf_session *self) +static void perf_session__destroy_kernel_maps(struct perf_session *session) { - machines__destroy_kernel_maps(&self->machines); + machines__destroy_kernel_maps(&session->machines); } -struct perf_session *perf_session__new(const char *filename, int mode, - bool force, bool repipe, - struct perf_tool *tool) +static bool perf_session__has_comm_exec(struct perf_session *session) { - struct perf_session *self; - struct stat st; - size_t len; + struct perf_evsel *evsel; - if (!filename || !strlen(filename)) { - if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode)) - filename = "-"; - else - filename = "perf.data"; + evlist__for_each(session->evlist, evsel) { + if (evsel->attr.comm_exec) + return true; + } + + return false; +} + +static void perf_session__set_comm_exec(struct perf_session *session) +{ + bool comm_exec = perf_session__has_comm_exec(session); + + machines__set_comm_exec(&session->machines, comm_exec); +} + +static int ordered_events__deliver_event(struct ordered_events *oe, + struct ordered_event *event) +{ + struct perf_sample sample; + struct perf_session *session = container_of(oe, struct perf_session, + ordered_events); + int ret = perf_evlist__parse_sample(session->evlist, event->event, &sample); + + if (ret) { + pr_err("Can't parse sample, err = %d\n", ret); + return ret; } - len = strlen(filename); - self = zalloc(sizeof(*self) + len); + return perf_session__deliver_event(session, event->event, &sample, + session->tool, event->file_offset); +} + +struct perf_session *perf_session__new(struct perf_data_file *file, + bool repipe, struct perf_tool *tool) +{ + struct perf_session *session = zalloc(sizeof(*session)); - if (self == NULL) + if (!session) goto out; - memcpy(self->filename, filename, len); - self->repipe = repipe; - INIT_LIST_HEAD(&self->ordered_samples.samples); - INIT_LIST_HEAD(&self->ordered_samples.sample_cache); - INIT_LIST_HEAD(&self->ordered_samples.to_free); - machines__init(&self->machines); + session->repipe = repipe; + session->tool = tool; + INIT_LIST_HEAD(&session->auxtrace_index); + machines__init(&session->machines); + ordered_events__init(&session->ordered_events, ordered_events__deliver_event); - if (mode == O_RDONLY) { - if (perf_session__open(self, force) < 0) + if (file) { + if (perf_data_file__open(file)) goto out_delete; - perf_session__set_id_hdr_size(self); - } else if (mode == O_WRONLY) { + + session->file = file; + + if (perf_data_file__is_read(file)) { + if (perf_session__open(session) < 0) + goto out_close; + + perf_session__set_id_hdr_size(session); + perf_session__set_comm_exec(session); + } + } else { + session->machines.host.env = &perf_env; + } + + if (!file || perf_data_file__is_write(file)) { /* * In O_RDONLY mode this will be performed when reading the * kernel MMAP event, in perf_event__process_mmap(). */ - if (perf_session__create_kernel_maps(self) < 0) - goto out_delete; + if (perf_session__create_kernel_maps(session) < 0) + pr_warning("Cannot read kernel map\n"); } if (tool && tool->ordering_requires_timestamps && - tool->ordered_samples && !perf_evlist__sample_id_all(self->evlist)) { + tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); - tool->ordered_samples = false; + tool->ordered_events = false; } -out: - return self; -out_delete: - perf_session__delete(self); - return NULL; -} + return session; -static void perf_session__delete_dead_threads(struct perf_session *session) -{ - machine__delete_dead_threads(&session->machines.host); + out_close: + perf_data_file__close(file); + out_delete: + perf_session__delete(session); + out: + return NULL; } static void perf_session__delete_threads(struct perf_session *session) @@ -165,35 +172,22 @@ machine__delete_threads(&session->machines.host); } -static void perf_session_env__delete(struct perf_session_env *env) +void perf_session__delete(struct perf_session *session) { - free(env->hostname); - free(env->os_release); - free(env->version); - free(env->arch); - free(env->cpu_desc); - free(env->cpuid); - - free(env->cmdline); - free(env->sibling_cores); - free(env->sibling_threads); - free(env->numa_nodes); - free(env->pmu_mappings); -} - -void perf_session__delete(struct perf_session *self) -{ - perf_session__destroy_kernel_maps(self); - perf_session__delete_dead_threads(self); - perf_session__delete_threads(self); - perf_session_env__delete(&self->header.env); - machines__exit(&self->machines); - close(self->fd); - free(self); - vdso__exit(); + auxtrace__free(session); + auxtrace_index__free(&session->auxtrace_index); + perf_session__destroy_kernel_maps(session); + perf_session__delete_threads(session); + perf_env__exit(&session->header.env); + machines__exit(&session->machines); + if (session->file) + perf_data_file__close(session->file); + free(session); } -static int process_event_synth_tracing_data_stub(union perf_event *event +static int process_event_synth_tracing_data_stub(struct perf_tool *tool + __maybe_unused, + union perf_event *event __maybe_unused, struct perf_session *session __maybe_unused) @@ -202,7 +196,8 @@ return 0; } -static int process_event_synth_attr_stub(union perf_event *event __maybe_unused, +static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, struct perf_evlist **pevlist __maybe_unused) { @@ -229,17 +224,17 @@ return 0; } -static int process_finished_round_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused, - struct perf_session *perf_session - __maybe_unused) +static int process_build_id_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *session __maybe_unused) { dump_printf(": unhandled!\n"); return 0; } -static int process_event_type_stub(struct perf_tool *tool __maybe_unused, - union perf_event *event __maybe_unused) +static int process_finished_round_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct ordered_events *oe __maybe_unused) { dump_printf(": unhandled!\n"); return 0; @@ -247,14 +242,68 @@ static int process_finished_round(struct perf_tool *tool, union perf_event *event, - struct perf_session *session); + struct ordered_events *oe); + +static int process_id_index_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *perf_session + __maybe_unused) +{ + dump_printf(": unhandled!\n"); + return 0; +} + +static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *session __maybe_unused) +{ + dump_printf(": unhandled!\n"); + return 0; +} + +static int skipn(int fd, off_t n) +{ + char buf[4096]; + ssize_t ret; + + while (n > 0) { + ret = read(fd, buf, min(n, (off_t)sizeof(buf))); + if (ret <= 0) + return ret; + n -= ret; + } + + return 0; +} + +static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session + __maybe_unused) +{ + dump_printf(": unhandled!\n"); + if (perf_data_file__is_pipe(session->file)) + skipn(perf_data_file__fd(session->file), event->auxtrace.size); + return event->auxtrace.size; +} + +static +int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *session __maybe_unused) +{ + dump_printf(": unhandled!\n"); + return 0; +} -static void perf_tool__fill_defaults(struct perf_tool *tool) +void perf_tool__fill_defaults(struct perf_tool *tool) { if (tool->sample == NULL) tool->sample = process_event_sample_stub; if (tool->mmap == NULL) tool->mmap = process_event_stub; + if (tool->mmap2 == NULL) + tool->mmap2 = process_event_stub; if (tool->comm == NULL) tool->comm = process_event_stub; if (tool->fork == NULL) @@ -263,6 +312,14 @@ tool->exit = process_event_stub; if (tool->lost == NULL) tool->lost = perf_event__process_lost; + if (tool->lost_samples == NULL) + tool->lost_samples = perf_event__process_lost_samples; + if (tool->aux == NULL) + tool->aux = perf_event__process_aux; + if (tool->itrace_start == NULL) + tool->itrace_start = perf_event__process_itrace_start; + if (tool->context_switch == NULL) + tool->context_switch = perf_event__process_switch; if (tool->read == NULL) tool->read = process_event_sample_stub; if (tool->throttle == NULL) @@ -271,39 +328,24 @@ tool->unthrottle = process_event_stub; if (tool->attr == NULL) tool->attr = process_event_synth_attr_stub; - if (tool->event_type == NULL) - tool->event_type = process_event_type_stub; if (tool->tracing_data == NULL) tool->tracing_data = process_event_synth_tracing_data_stub; if (tool->build_id == NULL) - tool->build_id = process_finished_round_stub; + tool->build_id = process_build_id_stub; if (tool->finished_round == NULL) { - if (tool->ordered_samples) + if (tool->ordered_events) tool->finished_round = process_finished_round; else tool->finished_round = process_finished_round_stub; } -} - -void mem_bswap_32(void *src, int byte_size) -{ - u32 *m = src; - while (byte_size > 0) { - *m = bswap_32(*m); - byte_size -= sizeof(u32); - ++m; - } -} - -void mem_bswap_64(void *src, int byte_size) -{ - u64 *m = src; - - while (byte_size > 0) { - *m = bswap_64(*m); - byte_size -= sizeof(u64); - ++m; - } + if (tool->id_index == NULL) + tool->id_index = process_id_index_stub; + if (tool->auxtrace_info == NULL) + tool->auxtrace_info = process_event_auxtrace_info_stub; + if (tool->auxtrace == NULL) + tool->auxtrace = process_event_auxtrace_stub; + if (tool->auxtrace_error == NULL) + tool->auxtrace_error = process_event_auxtrace_error_stub; } static void swap_sample_id_all(union perf_event *event, void *data) @@ -352,6 +394,25 @@ } } +static void perf_event__mmap2_swap(union perf_event *event, + bool sample_id_all) +{ + event->mmap2.pid = bswap_32(event->mmap2.pid); + event->mmap2.tid = bswap_32(event->mmap2.tid); + event->mmap2.start = bswap_64(event->mmap2.start); + event->mmap2.len = bswap_64(event->mmap2.len); + event->mmap2.pgoff = bswap_64(event->mmap2.pgoff); + event->mmap2.maj = bswap_32(event->mmap2.maj); + event->mmap2.min = bswap_32(event->mmap2.min); + event->mmap2.ino = bswap_64(event->mmap2.ino); + + if (sample_id_all) { + void *data = &event->mmap2.filename; + + data += PERF_ALIGN(strlen(data) + 1, sizeof(u64)); + swap_sample_id_all(event, data); + } +} static void perf_event__task_swap(union perf_event *event, bool sample_id_all) { event->fork.pid = bswap_32(event->fork.pid); @@ -377,6 +438,50 @@ swap_sample_id_all(event, &event->read + 1); } +static void perf_event__aux_swap(union perf_event *event, bool sample_id_all) +{ + event->aux.aux_offset = bswap_64(event->aux.aux_offset); + event->aux.aux_size = bswap_64(event->aux.aux_size); + event->aux.flags = bswap_64(event->aux.flags); + + if (sample_id_all) + swap_sample_id_all(event, &event->aux + 1); +} + +static void perf_event__itrace_start_swap(union perf_event *event, + bool sample_id_all) +{ + event->itrace_start.pid = bswap_32(event->itrace_start.pid); + event->itrace_start.tid = bswap_32(event->itrace_start.tid); + + if (sample_id_all) + swap_sample_id_all(event, &event->itrace_start + 1); +} + +static void perf_event__switch_swap(union perf_event *event, bool sample_id_all) +{ + if (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) { + event->context_switch.next_prev_pid = + bswap_32(event->context_switch.next_prev_pid); + event->context_switch.next_prev_tid = + bswap_32(event->context_switch.next_prev_tid); + } + + if (sample_id_all) + swap_sample_id_all(event, &event->context_switch + 1); +} + +static void perf_event__throttle_swap(union perf_event *event, + bool sample_id_all) +{ + event->throttle.time = bswap_64(event->throttle.time); + event->throttle.id = bswap_64(event->throttle.id); + event->throttle.stream_id = bswap_64(event->throttle.stream_id); + + if (sample_id_all) + swap_sample_id_all(event, &event->throttle + 1); +} + static u8 revbyte(u8 b) { int rev = (b >> 4) | ((b & 0xf) << 4); @@ -414,16 +519,42 @@ { attr->type = bswap_32(attr->type); attr->size = bswap_32(attr->size); - attr->config = bswap_64(attr->config); - attr->sample_period = bswap_64(attr->sample_period); - attr->sample_type = bswap_64(attr->sample_type); - attr->read_format = bswap_64(attr->read_format); - attr->wakeup_events = bswap_32(attr->wakeup_events); - attr->bp_type = bswap_32(attr->bp_type); - attr->bp_addr = bswap_64(attr->bp_addr); - attr->bp_len = bswap_64(attr->bp_len); - swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64)); +#define bswap_safe(f, n) \ + (attr->size > (offsetof(struct perf_event_attr, f) + \ + sizeof(attr->f) * (n))) +#define bswap_field(f, sz) \ +do { \ + if (bswap_safe(f, 0)) \ + attr->f = bswap_##sz(attr->f); \ +} while(0) +#define bswap_field_32(f) bswap_field(f, 32) +#define bswap_field_64(f) bswap_field(f, 64) + + bswap_field_64(config); + bswap_field_64(sample_period); + bswap_field_64(sample_type); + bswap_field_64(read_format); + bswap_field_32(wakeup_events); + bswap_field_32(bp_type); + bswap_field_64(bp_addr); + bswap_field_64(bp_len); + bswap_field_64(branch_sample_type); + bswap_field_64(sample_regs_user); + bswap_field_32(sample_stack_user); + bswap_field_32(aux_watermark); + + /* + * After read_format are bitfields. Check read_format because + * we are unable to use offsetof on bitfield. + */ + if (bswap_safe(read_format, 1)) + swap_bitfield((u8 *) (&attr->read_format + 1), + sizeof(u64)); +#undef bswap_field_64 +#undef bswap_field_32 +#undef bswap_field +#undef bswap_safe } static void perf_event__hdr_attr_swap(union perf_event *event, @@ -451,101 +582,70 @@ event->tracing_data.size = bswap_32(event->tracing_data.size); } +static void perf_event__auxtrace_info_swap(union perf_event *event, + bool sample_id_all __maybe_unused) +{ + size_t size; + + event->auxtrace_info.type = bswap_32(event->auxtrace_info.type); + + size = event->header.size; + size -= (void *)&event->auxtrace_info.priv - (void *)event; + mem_bswap_64(event->auxtrace_info.priv, size); +} + +static void perf_event__auxtrace_swap(union perf_event *event, + bool sample_id_all __maybe_unused) +{ + event->auxtrace.size = bswap_64(event->auxtrace.size); + event->auxtrace.offset = bswap_64(event->auxtrace.offset); + event->auxtrace.reference = bswap_64(event->auxtrace.reference); + event->auxtrace.idx = bswap_32(event->auxtrace.idx); + event->auxtrace.tid = bswap_32(event->auxtrace.tid); + event->auxtrace.cpu = bswap_32(event->auxtrace.cpu); +} + +static void perf_event__auxtrace_error_swap(union perf_event *event, + bool sample_id_all __maybe_unused) +{ + event->auxtrace_error.type = bswap_32(event->auxtrace_error.type); + event->auxtrace_error.code = bswap_32(event->auxtrace_error.code); + event->auxtrace_error.cpu = bswap_32(event->auxtrace_error.cpu); + event->auxtrace_error.pid = bswap_32(event->auxtrace_error.pid); + event->auxtrace_error.tid = bswap_32(event->auxtrace_error.tid); + event->auxtrace_error.ip = bswap_64(event->auxtrace_error.ip); +} + typedef void (*perf_event__swap_op)(union perf_event *event, bool sample_id_all); static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_MMAP] = perf_event__mmap_swap, + [PERF_RECORD_MMAP2] = perf_event__mmap2_swap, [PERF_RECORD_COMM] = perf_event__comm_swap, [PERF_RECORD_FORK] = perf_event__task_swap, [PERF_RECORD_EXIT] = perf_event__task_swap, [PERF_RECORD_LOST] = perf_event__all64_swap, [PERF_RECORD_READ] = perf_event__read_swap, + [PERF_RECORD_THROTTLE] = perf_event__throttle_swap, + [PERF_RECORD_UNTHROTTLE] = perf_event__throttle_swap, [PERF_RECORD_SAMPLE] = perf_event__all64_swap, + [PERF_RECORD_AUX] = perf_event__aux_swap, + [PERF_RECORD_ITRACE_START] = perf_event__itrace_start_swap, + [PERF_RECORD_LOST_SAMPLES] = perf_event__all64_swap, + [PERF_RECORD_SWITCH] = perf_event__switch_swap, + [PERF_RECORD_SWITCH_CPU_WIDE] = perf_event__switch_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, [PERF_RECORD_HEADER_BUILD_ID] = NULL, + [PERF_RECORD_ID_INDEX] = perf_event__all64_swap, + [PERF_RECORD_AUXTRACE_INFO] = perf_event__auxtrace_info_swap, + [PERF_RECORD_AUXTRACE] = perf_event__auxtrace_swap, + [PERF_RECORD_AUXTRACE_ERROR] = perf_event__auxtrace_error_swap, [PERF_RECORD_HEADER_MAX] = NULL, }; -struct sample_queue { - u64 timestamp; - u64 file_offset; - union perf_event *event; - struct list_head list; -}; - -static void perf_session_free_sample_buffers(struct perf_session *session) -{ - struct ordered_samples *os = &session->ordered_samples; - - while (!list_empty(&os->to_free)) { - struct sample_queue *sq; - - sq = list_entry(os->to_free.next, struct sample_queue, list); - list_del(&sq->list); - free(sq); - } -} - -static int perf_session_deliver_event(struct perf_session *session, - union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool, - u64 file_offset); - -static int flush_sample_queue(struct perf_session *s, - struct perf_tool *tool) -{ - struct ordered_samples *os = &s->ordered_samples; - struct list_head *head = &os->samples; - struct sample_queue *tmp, *iter; - struct perf_sample sample; - u64 limit = os->next_flush; - u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL; - unsigned idx = 0, progress_next = os->nr_samples / 16; - int ret; - - if (!tool->ordered_samples || !limit) - return 0; - - list_for_each_entry_safe(iter, tmp, head, list) { - if (iter->timestamp > limit) - break; - - ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample); - if (ret) - pr_err("Can't parse sample, err = %d\n", ret); - else { - ret = perf_session_deliver_event(s, iter->event, &sample, tool, - iter->file_offset); - if (ret) - return ret; - } - - os->last_flush = iter->timestamp; - list_del(&iter->list); - list_add(&iter->list, &os->sample_cache); - if (++idx >= progress_next) { - progress_next += os->nr_samples / 16; - ui_progress__update(idx, os->nr_samples, - "Processing time ordered events..."); - } - } - - if (list_empty(head)) { - os->last_sample = NULL; - } else if (last_ts <= limit) { - os->last_sample = - list_entry(head->prev, struct sample_queue, list); - } - - os->nr_samples = 0; - - return 0; -} - /* * When perf record finishes a pass on every buffers, it records this pseudo * event. @@ -585,114 +685,82 @@ * Flush every events below timestamp 7 * etc... */ -static int process_finished_round(struct perf_tool *tool, +static int process_finished_round(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, - struct perf_session *session) + struct ordered_events *oe) { - int ret = flush_sample_queue(session, tool); - if (!ret) - session->ordered_samples.next_flush = session->ordered_samples.max_timestamp; - - return ret; + if (dump_trace) + fprintf(stdout, "\n"); + return ordered_events__flush(oe, OE_FLUSH__ROUND); } -/* The queue is ordered by time */ -static void __queue_event(struct sample_queue *new, struct perf_session *s) +int perf_session__queue_event(struct perf_session *s, union perf_event *event, + struct perf_sample *sample, u64 file_offset) { - struct ordered_samples *os = &s->ordered_samples; - struct sample_queue *sample = os->last_sample; - u64 timestamp = new->timestamp; - struct list_head *p; - - ++os->nr_samples; - os->last_sample = new; - - if (!sample) { - list_add(&new->list, &os->samples); - os->max_timestamp = timestamp; - return; - } - - /* - * last_sample might point to some random place in the list as it's - * the last queued event. We expect that the new event is close to - * this. - */ - if (sample->timestamp <= timestamp) { - while (sample->timestamp <= timestamp) { - p = sample->list.next; - if (p == &os->samples) { - list_add_tail(&new->list, &os->samples); - os->max_timestamp = timestamp; - return; - } - sample = list_entry(p, struct sample_queue, list); - } - list_add_tail(&new->list, &sample->list); - } else { - while (sample->timestamp > timestamp) { - p = sample->list.prev; - if (p == &os->samples) { - list_add(&new->list, &os->samples); - return; - } - sample = list_entry(p, struct sample_queue, list); - } - list_add(&new->list, &sample->list); - } + return ordered_events__queue(&s->ordered_events, event, sample, file_offset); } -#define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct sample_queue)) - -static int perf_session_queue_event(struct perf_session *s, union perf_event *event, - struct perf_sample *sample, u64 file_offset) +static void callchain__lbr_callstack_printf(struct perf_sample *sample) { - struct ordered_samples *os = &s->ordered_samples; - struct list_head *sc = &os->sample_cache; - u64 timestamp = sample->time; - struct sample_queue *new; - - if (!timestamp || timestamp == ~0ULL) - return -ETIME; + struct ip_callchain *callchain = sample->callchain; + struct branch_stack *lbr_stack = sample->branch_stack; + u64 kernel_callchain_nr = callchain->nr; + unsigned int i; - if (timestamp < s->ordered_samples.last_flush) { - s->stats.nr_unordered_events++; + for (i = 0; i < kernel_callchain_nr; i++) { + if (callchain->ips[i] == PERF_CONTEXT_USER) + break; } - if (!list_empty(sc)) { - new = list_entry(sc->next, struct sample_queue, list); - list_del(&new->list); - } else if (os->sample_buffer) { - new = os->sample_buffer + os->sample_buffer_idx; - if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER) - os->sample_buffer = NULL; - } else { - os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new)); - if (!os->sample_buffer) - return -ENOMEM; - list_add(&os->sample_buffer->list, &os->to_free); - os->sample_buffer_idx = 2; - new = os->sample_buffer + 1; - } + if ((i != kernel_callchain_nr) && lbr_stack->nr) { + u64 total_nr; + /* + * LBR callstack can only get user call chain, + * i is kernel call chain number, + * 1 is PERF_CONTEXT_USER. + * + * The user call chain is stored in LBR registers. + * LBR are pair registers. The caller is stored + * in "from" register, while the callee is stored + * in "to" register. + * For example, there is a call stack + * "A"->"B"->"C"->"D". + * The LBR registers will recorde like + * "C"->"D", "B"->"C", "A"->"B". + * So only the first "to" register and all "from" + * registers are needed to construct the whole stack. + */ + total_nr = i + 1 + lbr_stack->nr + 1; + kernel_callchain_nr = i + 1; - new->timestamp = timestamp; - new->file_offset = file_offset; - new->event = event; + printf("... LBR call chain: nr:%" PRIu64 "\n", total_nr); - __queue_event(new, s); + for (i = 0; i < kernel_callchain_nr; i++) + printf("..... %2d: %016" PRIx64 "\n", + i, callchain->ips[i]); - return 0; + printf("..... %2d: %016" PRIx64 "\n", + (int)(kernel_callchain_nr), lbr_stack->entries[0].to); + for (i = 0; i < lbr_stack->nr; i++) + printf("..... %2d: %016" PRIx64 "\n", + (int)(i + kernel_callchain_nr + 1), lbr_stack->entries[i].from); + } } -static void callchain__printf(struct perf_sample *sample) +static void callchain__printf(struct perf_evsel *evsel, + struct perf_sample *sample) { unsigned int i; + struct ip_callchain *callchain = sample->callchain; - printf("... chain: nr:%" PRIu64 "\n", sample->callchain->nr); + if (has_branch_callstack(evsel)) + callchain__lbr_callstack_printf(sample); - for (i = 0; i < sample->callchain->nr; i++) + printf("... FP chain: nr:%" PRIu64 "\n", callchain->nr); + + for (i = 0; i < callchain->nr; i++) printf("..... %2d: %016" PRIx64 "\n", - i, sample->callchain->ips[i]); + i, callchain->ips[i]); } static void branch_stack__printf(struct perf_sample *sample) @@ -701,10 +769,18 @@ printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr); - for (i = 0; i < sample->branch_stack->nr; i++) - printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 "\n", - i, sample->branch_stack->entries[i].from, - sample->branch_stack->entries[i].to); + for (i = 0; i < sample->branch_stack->nr; i++) { + struct branch_entry *e = &sample->branch_stack->entries[i]; + + printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n", + i, e->from, e->to, + e->flags.cycles, + e->flags.mispred ? "M" : " ", + e->flags.predicted ? "P" : " ", + e->flags.abort ? "A" : " ", + e->flags.in_tx ? "T" : " ", + (unsigned)e->flags.reserved); + } } static void regs_dump__printf(u64 mask, u64 *regs) @@ -719,14 +795,46 @@ } } -static void regs_user__printf(struct perf_sample *sample, u64 mask) +static const char *regs_abi[] = { + [PERF_SAMPLE_REGS_ABI_NONE] = "none", + [PERF_SAMPLE_REGS_ABI_32] = "32-bit", + [PERF_SAMPLE_REGS_ABI_64] = "64-bit", +}; + +static inline const char *regs_dump_abi(struct regs_dump *d) +{ + if (d->abi > PERF_SAMPLE_REGS_ABI_64) + return "unknown"; + + return regs_abi[d->abi]; +} + +static void regs__printf(const char *type, struct regs_dump *regs) +{ + u64 mask = regs->mask; + + printf("... %s regs: mask 0x%" PRIx64 " ABI %s\n", + type, + mask, + regs_dump_abi(regs)); + + regs_dump__printf(mask, regs->regs); +} + +static void regs_user__printf(struct perf_sample *sample) { struct regs_dump *user_regs = &sample->user_regs; - if (user_regs->regs) { - printf("... user regs: mask 0x%" PRIx64 "\n", mask); - regs_dump__printf(mask, user_regs->regs); - } + if (user_regs->regs) + regs__printf("user", user_regs); +} + +static void regs_intr__printf(struct perf_sample *sample) +{ + struct regs_dump *intr_regs = &sample->intr_regs; + + if (intr_regs->regs) + regs__printf("intr", intr_regs); } static void stack_user__printf(struct stack_dump *dump) @@ -735,14 +843,14 @@ dump->size, dump->offset); } -static void perf_session__print_tstamp(struct perf_session *session, +static void perf_evlist__print_tstamp(struct perf_evlist *evlist, union perf_event *event, struct perf_sample *sample) { - u64 sample_type = perf_evlist__sample_type(session->evlist); + u64 sample_type = __perf_evlist__combined_sample_type(evlist); if (event->header.type != PERF_RECORD_SAMPLE && - !perf_evlist__sample_id_all(session->evlist)) { + !perf_evlist__sample_id_all(evlist)) { fputs("-1 -1 ", stdout); return; } @@ -754,7 +862,37 @@ printf("%" PRIu64 " ", sample->time); } -static void dump_event(struct perf_session *session, union perf_event *event, +static void sample_read__printf(struct perf_sample *sample, u64 read_format) +{ + printf("... sample_read:\n"); + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + printf("...... time enabled %016" PRIx64 "\n", + sample->read.time_enabled); + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + printf("...... time running %016" PRIx64 "\n", + sample->read.time_running); + + if (read_format & PERF_FORMAT_GROUP) { + u64 i; + + printf(".... group nr %" PRIu64 "\n", sample->read.group.nr); + + for (i = 0; i < sample->read.group.nr; i++) { + struct sample_read_value *value; + + value = &sample->read.group.values[i]; + printf("..... id %016" PRIx64 + ", value %016" PRIx64 "\n", + value->id, value->value); + } + } else + printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n", + sample->read.one.id, sample->read.one.value); +} + +static void dump_event(struct perf_evlist *evlist, union perf_event *event, u64 file_offset, struct perf_sample *sample) { if (!dump_trace) @@ -766,7 +904,7 @@ trace_event(event); if (sample) - perf_session__print_tstamp(session, event, sample); + perf_evlist__print_tstamp(evlist, event, sample); printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset, event->header.size, perf_event__name(event->header.type)); @@ -780,20 +918,23 @@ if (!dump_trace) return; - printf("(IP, %d): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n", + printf("(IP, 0x%x): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n", event->header.misc, sample->pid, sample->tid, sample->ip, sample->period, sample->addr); sample_type = evsel->attr.sample_type; if (sample_type & PERF_SAMPLE_CALLCHAIN) - callchain__printf(sample); + callchain__printf(evsel, sample); - if (sample_type & PERF_SAMPLE_BRANCH_STACK) + if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !has_branch_callstack(evsel)) branch_stack__printf(sample); if (sample_type & PERF_SAMPLE_REGS_USER) - regs_user__printf(sample, evsel->attr.sample_regs_user); + regs_user__printf(sample); + + if (sample_type & PERF_SAMPLE_REGS_INTR) + regs_intr__printf(sample); if (sample_type & PERF_SAMPLE_STACK_USER) stack_user__printf(&sample->user_stack); @@ -803,11 +944,17 @@ if (sample_type & PERF_SAMPLE_DATA_SRC) printf(" . data_src: 0x%"PRIx64"\n", sample->data_src); + + if (sample_type & PERF_SAMPLE_TRANSACTION) + printf("... transaction: %" PRIx64 "\n", sample->transaction); + + if (sample_type & PERF_SAMPLE_READ) + sample_read__printf(sample, evsel->attr.read_format); } -static struct machine * - perf_session__find_machine_for_cpumode(struct perf_session *session, - union perf_event *event) +static struct machine *machines__find_for_cpumode(struct machines *machines, + union perf_event *event, + struct perf_sample *sample) { const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; struct machine *machine; @@ -817,66 +964,122 @@ (cpumode == PERF_RECORD_MISC_GUEST_USER))) { u32 pid; - if (event->header.type == PERF_RECORD_MMAP) + if (event->header.type == PERF_RECORD_MMAP + || event->header.type == PERF_RECORD_MMAP2) pid = event->mmap.pid; else - pid = event->ip.pid; + pid = sample->pid; - machine = perf_session__find_machine(session, pid); + machine = machines__find(machines, pid); if (!machine) - machine = perf_session__findnew_machine(session, - DEFAULT_GUEST_KERNEL_ID); + machine = machines__findnew(machines, DEFAULT_GUEST_KERNEL_ID); return machine; } - return &session->machines.host; + return &machines->host; } -static int perf_session_deliver_event(struct perf_session *session, - union perf_event *event, - struct perf_sample *sample, - struct perf_tool *tool, - u64 file_offset) +static int deliver_sample_value(struct perf_evlist *evlist, + struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct sample_read_value *v, + struct machine *machine) +{ + struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id); + + if (sid) { + sample->id = v->id; + sample->period = v->value - sid->period; + sid->period = v->value; + } + + if (!sid || sid->evsel == NULL) { + ++evlist->stats.nr_unknown_id; + return 0; + } + + return tool->sample(tool, event, sample, sid->evsel, machine); +} + +static int deliver_sample_group(struct perf_evlist *evlist, + struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + int ret = -EINVAL; + u64 i; + + for (i = 0; i < sample->read.group.nr; i++) { + ret = deliver_sample_value(evlist, tool, event, sample, + &sample->read.group.values[i], + machine); + if (ret) + break; + } + + return ret; +} + +static int + perf_evlist__deliver_sample(struct perf_evlist *evlist, + struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine) +{ + /* We know evsel != NULL. */ + u64 sample_type = evsel->attr.sample_type; + u64 read_format = evsel->attr.read_format; + + /* Standard sample delievery. */ + if (!(sample_type & PERF_SAMPLE_READ)) + return tool->sample(tool, event, sample, evsel, machine); + + /* 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); + else + return deliver_sample_value(evlist, tool, event, sample, + &sample->read.one, machine); +} + +static int machines__deliver_event(struct machines *machines, + struct perf_evlist *evlist, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool, u64 file_offset) { struct perf_evsel *evsel; struct machine *machine; - dump_event(session, event, file_offset, sample); + dump_event(evlist, event, file_offset, sample); - evsel = perf_evlist__id2evsel(session->evlist, sample->id); - if (evsel != NULL && event->header.type != PERF_RECORD_SAMPLE) { - /* - * XXX We're leaving PERF_RECORD_SAMPLE unnacounted here - * because the tools right now may apply filters, discarding - * some of the samples. For consistency, in the future we - * should have something like nr_filtered_samples and remove - * the sample->period from total_sample_period, etc, KISS for - * now tho. - * - * Also testing against NULL allows us to handle files without - * attr.sample_id_all and/or without PERF_SAMPLE_ID. In the - * future probably it'll be a good idea to restrict event - * processing via perf_session to files with both set. - */ - hists__inc_nr_events(&evsel->hists, event->header.type); - } + evsel = perf_evlist__id2evsel(evlist, sample->id); - machine = perf_session__find_machine_for_cpumode(session, event); + machine = machines__find_for_cpumode(machines, event, sample); switch (event->header.type) { case PERF_RECORD_SAMPLE: - dump_sample(evsel, event, sample); if (evsel == NULL) { - ++session->stats.nr_unknown_id; + ++evlist->stats.nr_unknown_id; return 0; } + dump_sample(evsel, event, sample); if (machine == NULL) { - ++session->stats.nr_unprocessable_samples; + ++evlist->stats.nr_unprocessable_samples; return 0; } - return tool->sample(tool, event, sample, evsel, machine); + return perf_evlist__deliver_sample(evlist, tool, event, sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); + case PERF_RECORD_MMAP2: + if (event->header.misc & PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT) + ++evlist->stats.nr_proc_map_timeout; + return tool->mmap2(tool, event, sample, machine); case PERF_RECORD_COMM: return tool->comm(tool, event, sample, machine); case PERF_RECORD_FORK: @@ -885,65 +1088,117 @@ return tool->exit(tool, event, sample, machine); case PERF_RECORD_LOST: if (tool->lost == perf_event__process_lost) - session->stats.total_lost += event->lost.lost; + evlist->stats.total_lost += event->lost.lost; return tool->lost(tool, event, sample, machine); + case PERF_RECORD_LOST_SAMPLES: + if (tool->lost_samples == perf_event__process_lost_samples) + evlist->stats.total_lost_samples += event->lost_samples.lost; + return tool->lost_samples(tool, event, sample, machine); case PERF_RECORD_READ: return tool->read(tool, event, sample, evsel, machine); case PERF_RECORD_THROTTLE: return tool->throttle(tool, event, sample, machine); case PERF_RECORD_UNTHROTTLE: return tool->unthrottle(tool, event, sample, machine); + case PERF_RECORD_AUX: + if (tool->aux == perf_event__process_aux && + (event->aux.flags & PERF_AUX_FLAG_TRUNCATED)) + evlist->stats.total_aux_lost += 1; + return tool->aux(tool, event, sample, machine); + case PERF_RECORD_ITRACE_START: + return tool->itrace_start(tool, event, sample, machine); + case PERF_RECORD_SWITCH: + case PERF_RECORD_SWITCH_CPU_WIDE: + return tool->context_switch(tool, event, sample, machine); default: - ++session->stats.nr_unknown_events; + ++evlist->stats.nr_unknown_events; return -1; } } -static int perf_session__preprocess_sample(struct perf_session *session, - union perf_event *event, struct perf_sample *sample) +static int perf_session__deliver_event(struct perf_session *session, + union perf_event *event, + struct perf_sample *sample, + struct perf_tool *tool, + u64 file_offset) { - if (event->header.type != PERF_RECORD_SAMPLE || - !(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_CALLCHAIN)) + int ret; + + ret = auxtrace__process_event(session, event, sample, tool); + if (ret < 0) + return ret; + if (ret > 0) return 0; - if (!ip_callchain__valid(sample->callchain, event)) { - pr_debug("call-chain problem with event, skipping it.\n"); - ++session->stats.nr_invalid_chains; - session->stats.total_invalid_chains += sample->period; - return -EINVAL; - } - return 0; + return machines__deliver_event(&session->machines, session->evlist, + event, sample, tool, file_offset); } -static int perf_session__process_user_event(struct perf_session *session, union perf_event *event, - struct perf_tool *tool, u64 file_offset) +static s64 perf_session__process_user_event(struct perf_session *session, + union perf_event *event, + u64 file_offset) { + struct ordered_events *oe = &session->ordered_events; + struct perf_tool *tool = session->tool; + int fd = perf_data_file__fd(session->file); int err; - dump_event(session, event, file_offset, NULL); + dump_event(session->evlist, event, file_offset, NULL); /* These events are processed right away */ switch (event->header.type) { case PERF_RECORD_HEADER_ATTR: - err = tool->attr(event, &session->evlist); - if (err == 0) + err = tool->attr(tool, event, &session->evlist); + if (err == 0) { perf_session__set_id_hdr_size(session); + perf_session__set_comm_exec(session); + } return err; case PERF_RECORD_HEADER_EVENT_TYPE: - return tool->event_type(tool, event); + /* + * Depreceated, but we need to handle it for sake + * of old data files create in pipe mode. + */ + return 0; case PERF_RECORD_HEADER_TRACING_DATA: /* setup for reading amidst mmap */ - lseek(session->fd, file_offset, SEEK_SET); - return tool->tracing_data(event, session); + lseek(fd, file_offset, SEEK_SET); + return tool->tracing_data(tool, event, session); case PERF_RECORD_HEADER_BUILD_ID: return tool->build_id(tool, event, session); case PERF_RECORD_FINISHED_ROUND: - return tool->finished_round(tool, event, session); + return tool->finished_round(tool, event, oe); + case PERF_RECORD_ID_INDEX: + return tool->id_index(tool, event, session); + case PERF_RECORD_AUXTRACE_INFO: + return tool->auxtrace_info(tool, event, session); + case PERF_RECORD_AUXTRACE: + /* setup for reading amidst mmap */ + lseek(fd, file_offset + event->header.size, SEEK_SET); + return tool->auxtrace(tool, event, session); + case PERF_RECORD_AUXTRACE_ERROR: + perf_session__auxtrace_error_inc(session, event); + return tool->auxtrace_error(tool, event, session); default: return -EINVAL; } } +int perf_session__deliver_synth_event(struct perf_session *session, + union perf_event *event, + struct perf_sample *sample) +{ + struct perf_evlist *evlist = session->evlist; + struct perf_tool *tool = session->tool; + + events_stats__inc(&evlist->stats, event->header.type); + + if (event->header.type >= PERF_RECORD_USER_TYPE_START) + return perf_session__process_user_event(session, event, 0); + + return machines__deliver_event(&session->machines, evlist, event, sample, tool, 0); +} + static void event_swap(union perf_event *event, bool sample_id_all) { perf_event__swap_op swap; @@ -953,64 +1208,115 @@ swap(event, sample_id_all); } -static int perf_session__process_event(struct perf_session *session, - union perf_event *event, - struct perf_tool *tool, - u64 file_offset) +int perf_session__peek_event(struct perf_session *session, off_t file_offset, + void *buf, size_t buf_sz, + union perf_event **event_ptr, + struct perf_sample *sample) +{ + union perf_event *event; + size_t hdr_sz, rest; + int fd; + + if (session->one_mmap && !session->header.needs_swap) { + event = file_offset - session->one_mmap_offset + + session->one_mmap_addr; + goto out_parse_sample; + } + + if (perf_data_file__is_pipe(session->file)) + return -1; + + fd = perf_data_file__fd(session->file); + hdr_sz = sizeof(struct perf_event_header); + + if (buf_sz < hdr_sz) + return -1; + + if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 || + readn(fd, buf, hdr_sz) != (ssize_t)hdr_sz) + return -1; + + event = (union perf_event *)buf; + + if (session->header.needs_swap) + perf_event_header__bswap(&event->header); + + if (event->header.size < hdr_sz || event->header.size > buf_sz) + return -1; + + rest = event->header.size - hdr_sz; + + if (readn(fd, buf, rest) != (ssize_t)rest) + return -1; + + if (session->header.needs_swap) + event_swap(event, perf_evlist__sample_id_all(session->evlist)); + +out_parse_sample: + + if (sample && event->header.type < PERF_RECORD_USER_TYPE_START && + perf_evlist__parse_sample(session->evlist, event, sample)) + return -1; + + *event_ptr = event; + + return 0; +} + +static s64 perf_session__process_event(struct perf_session *session, + union perf_event *event, u64 file_offset) { + struct perf_evlist *evlist = session->evlist; + struct perf_tool *tool = session->tool; struct perf_sample sample; int ret; if (session->header.needs_swap) - event_swap(event, perf_evlist__sample_id_all(session->evlist)); + event_swap(event, perf_evlist__sample_id_all(evlist)); if (event->header.type >= PERF_RECORD_HEADER_MAX) return -EINVAL; - events_stats__inc(&session->stats, event->header.type); + events_stats__inc(&evlist->stats, event->header.type); if (event->header.type >= PERF_RECORD_USER_TYPE_START) - return perf_session__process_user_event(session, event, tool, file_offset); + return perf_session__process_user_event(session, event, file_offset); /* * For all kernel events we get the sample data */ - ret = perf_evlist__parse_sample(session->evlist, event, &sample); + ret = perf_evlist__parse_sample(evlist, event, &sample); if (ret) return ret; - /* Preprocess sample records - precheck callchains */ - if (perf_session__preprocess_sample(session, event, &sample)) - return 0; - - if (tool->ordered_samples) { - ret = perf_session_queue_event(session, event, &sample, - file_offset); + if (tool->ordered_events) { + ret = perf_session__queue_event(session, event, &sample, file_offset); if (ret != -ETIME) return ret; } - return perf_session_deliver_event(session, event, &sample, tool, - file_offset); + return perf_session__deliver_event(session, event, &sample, tool, + file_offset); } -void perf_event_header__bswap(struct perf_event_header *self) +void perf_event_header__bswap(struct perf_event_header *hdr) { - self->type = bswap_32(self->type); - self->misc = bswap_16(self->misc); - self->size = bswap_16(self->size); + hdr->type = bswap_32(hdr->type); + hdr->misc = bswap_16(hdr->misc); + hdr->size = bswap_16(hdr->size); } struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) { - return machine__findnew_thread(&session->machines.host, pid); + return machine__findnew_thread(&session->machines.host, -1, pid); } -static struct thread *perf_session__register_idle_thread(struct perf_session *self) +struct thread *perf_session__register_idle_thread(struct perf_session *session) { - struct thread *thread = perf_session__findnew(self, 0); + struct thread *thread; - if (thread == NULL || thread__set_comm(thread, "swapper")) { + thread = machine__findnew_thread(&session->machines.host, 0, 0); + if (thread == NULL || thread__set_comm(thread, "swapper", 0)) { pr_err("problem inserting idle task.\n"); thread = NULL; } @@ -1018,60 +1324,109 @@ return thread; } -static void perf_session__warn_about_errors(const struct perf_session *session, - const struct perf_tool *tool) +static void perf_session__warn_about_errors(const struct perf_session *session) { - if (tool->lost == perf_event__process_lost && - session->stats.nr_events[PERF_RECORD_LOST] != 0) { + const struct events_stats *stats = &session->evlist->stats; + const struct ordered_events *oe = &session->ordered_events; + + if (session->tool->lost == perf_event__process_lost && + stats->nr_events[PERF_RECORD_LOST] != 0) { ui__warning("Processed %d events and lost %d chunks!\n\n" "Check IO/CPU overload!\n\n", - session->stats.nr_events[0], - session->stats.nr_events[PERF_RECORD_LOST]); + stats->nr_events[0], + stats->nr_events[PERF_RECORD_LOST]); } - if (session->stats.nr_unknown_events != 0) { + if (session->tool->lost_samples == perf_event__process_lost_samples) { + double drop_rate; + + drop_rate = (double)stats->total_lost_samples / + (double) (stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples); + if (drop_rate > 0.05) { + ui__warning("Processed %" PRIu64 " samples and lost %3.2f%% samples!\n\n", + stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples, + drop_rate * 100.0); + } + } + + if (session->tool->aux == perf_event__process_aux && + stats->total_aux_lost != 0) { + ui__warning("AUX data lost %" PRIu64 " times out of %u!\n\n", + stats->total_aux_lost, + stats->nr_events[PERF_RECORD_AUX]); + } + + if (stats->nr_unknown_events != 0) { ui__warning("Found %u unknown events!\n\n" "Is this an older tool processing a perf.data " "file generated by a more recent tool?\n\n" "If that is not the case, consider " "reporting to linux-kernel@vger.kernel.org.\n\n", - session->stats.nr_unknown_events); + stats->nr_unknown_events); } - if (session->stats.nr_unknown_id != 0) { + if (stats->nr_unknown_id != 0) { ui__warning("%u samples with id not present in the header\n", - session->stats.nr_unknown_id); + stats->nr_unknown_id); } - if (session->stats.nr_invalid_chains != 0) { - ui__warning("Found invalid callchains!\n\n" - "%u out of %u events were discarded for this reason.\n\n" - "Consider reporting to linux-kernel@vger.kernel.org.\n\n", - session->stats.nr_invalid_chains, - session->stats.nr_events[PERF_RECORD_SAMPLE]); - } + if (stats->nr_invalid_chains != 0) { + ui__warning("Found invalid callchains!\n\n" + "%u out of %u events were discarded for this reason.\n\n" + "Consider reporting to linux-kernel@vger.kernel.org.\n\n", + stats->nr_invalid_chains, + stats->nr_events[PERF_RECORD_SAMPLE]); + } - if (session->stats.nr_unprocessable_samples != 0) { + if (stats->nr_unprocessable_samples != 0) { ui__warning("%u unprocessable samples recorded.\n" "Do you have a KVM guest running and not using 'perf kvm'?\n", - session->stats.nr_unprocessable_samples); + stats->nr_unprocessable_samples); } - if (session->stats.nr_unordered_events != 0) - ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events); + + if (oe->nr_unordered_events != 0) + ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events); + + events_stats__auxtrace_error_warn(stats); + + if (stats->nr_proc_map_timeout != 0) { + ui__warning("%d map information files for pre-existing threads were\n" + "not processed, if there are samples for addresses they\n" + "will not be resolved, you may find out which are these\n" + "threads by running with -v and redirecting the output\n" + "to a file.\n" + "The time limit to process proc map is too short?\n" + "Increase it by --proc-map-timeout\n", + stats->nr_proc_map_timeout); + } +} + +static int perf_session__flush_thread_stack(struct thread *thread, + void *p __maybe_unused) +{ + return thread_stack__flush(thread); +} + +static int perf_session__flush_thread_stacks(struct perf_session *session) +{ + return machines__for_each_thread(&session->machines, + perf_session__flush_thread_stack, + NULL); } -#define session_done() (*(volatile int *)(&session_done)) volatile int session_done; -static int __perf_session__process_pipe_events(struct perf_session *self, - struct perf_tool *tool) +static int __perf_session__process_pipe_events(struct perf_session *session) { + struct ordered_events *oe = &session->ordered_events; + struct perf_tool *tool = session->tool; + int fd = perf_data_file__fd(session->file); union perf_event *event; uint32_t size, cur_size = 0; void *buf = NULL; - int skip = 0; + s64 skip = 0; u64 head; - int err; + ssize_t err; void *p; perf_tool__fill_defaults(tool); @@ -1084,7 +1439,7 @@ return -errno; more: event = buf; - err = readn(self->fd, event, sizeof(struct perf_event_header)); + err = readn(fd, event, sizeof(struct perf_event_header)); if (err <= 0) { if (err == 0) goto done; @@ -1093,12 +1448,14 @@ goto out_err; } - if (self->header.needs_swap) + if (session->header.needs_swap) perf_event_header__bswap(&event->header); size = event->header.size; - if (size == 0) - size = 8; + if (size < sizeof(struct perf_event_header)) { + pr_err("bad event header size\n"); + goto out_err; + } if (size > cur_size) { void *new = realloc(buf, size); @@ -1114,7 +1471,7 @@ p += sizeof(struct perf_event_header); if (size - sizeof(struct perf_event_header)) { - err = readn(self->fd, p, size - sizeof(struct perf_event_header)); + err = readn(fd, p, size - sizeof(struct perf_event_header)); if (err <= 0) { if (err == 0) { pr_err("unexpected end of event stream\n"); @@ -1126,7 +1483,7 @@ } } - if ((skip = perf_session__process_event(self, event, tool, head)) < 0) { + if ((skip = perf_session__process_event(session, event, head)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", head, event->header.size, event->header.type); err = -EINVAL; @@ -1141,11 +1498,19 @@ if (!session_done()) goto more; done: - err = 0; + /* do the final flush for ordered samples */ + err = ordered_events__flush(oe, OE_FLUSH__FINAL); + if (err) + goto out_err; + err = auxtrace__flush_events(session, tool); + if (err) + goto out_err; + err = perf_session__flush_thread_stacks(session); out_err: free(buf); - perf_session__warn_about_errors(self, tool); - perf_session_free_sample_buffers(self); + perf_session__warn_about_errors(session); + ordered_events__free(&session->ordered_events); + auxtrace__free_events(session); return err; } @@ -1167,8 +1532,12 @@ if (session->header.needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size > mmap_size) + if (head + event->header.size > mmap_size) { + /* We're not fetching the event so swap back again */ + if (session->header.needs_swap) + perf_event_header__bswap(&event->header); return NULL; + } return event; } @@ -1185,16 +1554,20 @@ #define NUM_MMAPS 128 #endif -int __perf_session__process_events(struct perf_session *session, - u64 data_offset, u64 data_size, - u64 file_size, struct perf_tool *tool) -{ - u64 head, page_offset, file_offset, file_pos, progress_next; +static int __perf_session__process_events(struct perf_session *session, + u64 data_offset, u64 data_size, + u64 file_size) +{ + struct ordered_events *oe = &session->ordered_events; + struct perf_tool *tool = session->tool; + int fd = perf_data_file__fd(session->file); + u64 head, page_offset, file_offset, file_pos, size; int err, mmap_prot, mmap_flags, map_idx = 0; size_t mmap_size; char *buf, *mmaps[NUM_MMAPS]; union perf_event *event; - uint32_t size; + struct ui_progress prog; + s64 skip; perf_tool__fill_defaults(tool); @@ -1202,14 +1575,19 @@ file_offset = page_offset; head = data_offset - page_offset; + if (data_size == 0) + goto out; + if (data_offset + data_size < file_size) file_size = data_offset + data_size; - progress_next = file_size / 16; + ui_progress__init(&prog, file_size, "Processing events..."); mmap_size = MMAP_SIZE; - if (mmap_size > file_size) + if (mmap_size > file_size) { mmap_size = file_size; + session->one_mmap = true; + } memset(mmaps, 0, sizeof(mmaps)); @@ -1221,7 +1599,7 @@ mmap_flags = MAP_PRIVATE; } remap: - buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, session->fd, + buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, fd, file_offset); if (buf == MAP_FAILED) { pr_err("failed to mmap file\n"); @@ -1231,6 +1609,10 @@ mmaps[map_idx] = buf; map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1); file_pos = file_offset + head; + if (session->one_mmap) { + session->one_mmap_addr = buf; + session->one_mmap_offset = file_offset; + } more: event = fetch_mmaped_event(session, head, mmap_size, buf); @@ -1248,8 +1630,8 @@ size = event->header.size; - if (size == 0 || - perf_session__process_event(session, event, tool, file_pos) < 0) { + if (size < sizeof(struct perf_event_header) || + (skip = perf_session__process_event(session, event, file_pos)) < 0) { pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", file_offset + head, event->header.size, event->header.type); @@ -1257,56 +1639,67 @@ goto out_err; } + if (skip) + size += skip; + head += size; file_pos += size; - if (file_pos >= progress_next) { - progress_next += file_size / 16; - ui_progress__update(file_pos, file_size, - "Processing events..."); - } + ui_progress__update(&prog, size); + + if (session_done()) + goto out; if (file_pos < file_size) goto more; - err = 0; +out: /* do the final flush for ordered samples */ - session->ordered_samples.next_flush = ULLONG_MAX; - err = flush_sample_queue(session, tool); + err = ordered_events__flush(oe, OE_FLUSH__FINAL); + if (err) + goto out_err; + err = auxtrace__flush_events(session, tool); + if (err) + goto out_err; + err = perf_session__flush_thread_stacks(session); out_err: ui_progress__finish(); - perf_session__warn_about_errors(session, tool); - perf_session_free_sample_buffers(session); + perf_session__warn_about_errors(session); + ordered_events__free(&session->ordered_events); + auxtrace__free_events(session); + session->one_mmap = false; return err; } -int perf_session__process_events(struct perf_session *self, - struct perf_tool *tool) +int perf_session__process_events(struct perf_session *session) { + u64 size = perf_data_file__size(session->file); int err; - if (perf_session__register_idle_thread(self) == NULL) + if (perf_session__register_idle_thread(session) == NULL) return -ENOMEM; - if (!self->fd_pipe) - err = __perf_session__process_events(self, - self->header.data_offset, - self->header.data_size, - self->size, tool); + if (!perf_data_file__is_pipe(session->file)) + err = __perf_session__process_events(session, + session->header.data_offset, + session->header.data_size, size); else - err = __perf_session__process_pipe_events(self, tool); + err = __perf_session__process_pipe_events(session); return err; } bool perf_session__has_traces(struct perf_session *session, const char *msg) { - if (!(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_RAW)) { - pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg); - return false; + struct perf_evsel *evsel; + + evlist__for_each(session->evlist, evsel) { + if (evsel->attr.type == PERF_TYPE_TRACEPOINT) + return true; } - return true; + pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg); + return false; } int maps__set_kallsyms_ref_reloc_sym(struct map **maps, @@ -1334,35 +1727,37 @@ for (i = 0; i < MAP__NR_TYPES; ++i) { struct kmap *kmap = map__kmap(maps[i]); + + if (!kmap) + continue; kmap->ref_reloc_sym = ref; } return 0; } -size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp) +size_t perf_session__fprintf_dsos(struct perf_session *session, FILE *fp) { - return machines__fprintf_dsos(&self->machines, fp); + return machines__fprintf_dsos(&session->machines, fp); } -size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp, +size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp, bool (skip)(struct dso *dso, int parm), int parm) { - return machines__fprintf_dsos_buildid(&self->machines, fp, skip, parm); + return machines__fprintf_dsos_buildid(&session->machines, fp, skip, parm); } size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) { - struct perf_evsel *pos; - size_t ret = fprintf(fp, "Aggregated stats:\n"); + size_t ret; + const char *msg = ""; - ret += events_stats__fprintf(&session->stats, fp); + if (perf_header__has_feat(&session->header, HEADER_AUXTRACE)) + msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)"; - list_for_each_entry(pos, &session->evlist->entries, node) { - ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos)); - ret += events_stats__fprintf(&pos->hists.stats, fp); - } + ret = fprintf(fp, "\nAggregated stats:%s\n", msg); + ret += events_stats__fprintf(&session->evlist->stats, fp); return ret; } @@ -1380,81 +1775,116 @@ { struct perf_evsel *pos; - list_for_each_entry(pos, &session->evlist->entries, node) { + evlist__for_each(session->evlist, pos) { if (pos->attr.type == type) return pos; } return NULL; } -void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event, - struct perf_sample *sample, struct machine *machine, - int print_sym, int print_dso, int print_symoffset) +void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample, + struct addr_location *al, + unsigned int print_opts, unsigned int stack_depth) { - struct addr_location al; struct callchain_cursor_node *node; - - if (perf_event__preprocess_sample(event, machine, &al, sample, - NULL) < 0) { - error("problem processing %d event, skipping it.\n", - event->header.type); - return; - } + int print_ip = print_opts & PRINT_IP_OPT_IP; + int print_sym = print_opts & PRINT_IP_OPT_SYM; + int print_dso = print_opts & PRINT_IP_OPT_DSO; + int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET; + int print_oneline = print_opts & PRINT_IP_OPT_ONELINE; + int print_srcline = print_opts & PRINT_IP_OPT_SRCLINE; + char s = print_oneline ? ' ' : '\t'; if (symbol_conf.use_callchain && sample->callchain) { + struct addr_location node_al; - - if (machine__resolve_callchain(machine, evsel, al.thread, - sample, NULL) != 0) { + if (thread__resolve_callchain(al->thread, evsel, + sample, NULL, NULL, + stack_depth) != 0) { if (verbose) error("Failed to resolve callchain. Skipping\n"); return; } callchain_cursor_commit(&callchain_cursor); - while (1) { + if (print_symoffset) + node_al = *al; + + while (stack_depth) { + u64 addr = 0; + node = callchain_cursor_current(&callchain_cursor); if (!node) break; - printf("\t%16" PRIx64, node->ip); + if (node->sym && node->sym->ignore) + goto next; + + if (print_ip) + printf("%c%16" PRIx64, s, node->ip); + + if (node->map) + addr = node->map->map_ip(node->map, node->ip); + if (print_sym) { printf(" "); - symbol__fprintf_symname(node->sym, stdout); + if (print_symoffset) { + node_al.addr = addr; + node_al.map = node->map; + symbol__fprintf_symname_offs(node->sym, &node_al, stdout); + } else + symbol__fprintf_symname(node->sym, stdout); } + if (print_dso) { printf(" ("); map__fprintf_dsoname(node->map, stdout); printf(")"); } - printf("\n"); + if (print_srcline) + map__fprintf_srcline(node->map, addr, "\n ", + stdout); + + if (!print_oneline) + printf("\n"); + + stack_depth--; +next: callchain_cursor_advance(&callchain_cursor); } } else { - printf("%16" PRIx64, sample->ip); + if (al->sym && al->sym->ignore) + return; + + if (print_ip) + printf("%16" PRIx64, sample->ip); + if (print_sym) { printf(" "); if (print_symoffset) - symbol__fprintf_symname_offs(al.sym, &al, + symbol__fprintf_symname_offs(al->sym, al, stdout); else - symbol__fprintf_symname(al.sym, stdout); + symbol__fprintf_symname(al->sym, stdout); } if (print_dso) { printf(" ("); - map__fprintf_dsoname(al.map, stdout); + map__fprintf_dsoname(al->map, stdout); printf(")"); } + + if (print_srcline) + map__fprintf_srcline(al->map, al->addr, "\n ", stdout); } } int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap) { - int i; + int i, err = -1; struct cpu_map *map; for (i = 0; i < PERF_TYPE_MAX; ++i) { @@ -1483,25 +1913,31 @@ if (cpu >= MAX_NR_CPUS) { pr_err("Requested CPU %d too large. " "Consider raising MAX_NR_CPUS\n", cpu); - return -1; + goto out_delete_map; } set_bit(cpu, cpu_bitmap); } - return 0; + err = 0; + +out_delete_map: + cpu_map__put(map); + return err; } void perf_session__fprintf_info(struct perf_session *session, FILE *fp, bool full) { struct stat st; - int ret; + int fd, ret; if (session == NULL || fp == NULL) return; - ret = fstat(session->fd, &st); + fd = perf_data_file__fd(session->file); + + ret = fstat(fd, &st); if (ret == -1) return; @@ -1516,52 +1952,134 @@ const struct perf_evsel_str_handler *assocs, size_t nr_assocs) { - struct perf_evlist *evlist = session->evlist; - struct event_format *format; struct perf_evsel *evsel; - char *tracepoint, *name; size_t i; int err; for (i = 0; i < nr_assocs; i++) { - err = -ENOMEM; - tracepoint = strdup(assocs[i].name); - if (tracepoint == NULL) - goto out; - - err = -ENOENT; - name = strchr(tracepoint, ':'); - if (name == NULL) - goto out_free; - - *name++ = '\0'; - format = pevent_find_event_by_name(session->pevent, - tracepoint, name); - if (format == NULL) { - /* - * Adding a handler for an event not in the session, - * just ignore it. - */ - goto next; - } - - evsel = perf_evlist__find_tracepoint_by_id(evlist, format->id); + /* + * Adding a handler for an event not in the session, + * just ignore it. + */ + evsel = perf_evlist__find_tracepoint_by_name(session->evlist, assocs[i].name); if (evsel == NULL) - goto next; + continue; err = -EEXIST; - if (evsel->handler.func != NULL) - goto out_free; - evsel->handler.func = assocs[i].handler; -next: - free(tracepoint); + if (evsel->handler != NULL) + goto out; + evsel->handler = assocs[i].handler; } err = 0; out: return err; +} + +int perf_event__process_id_index(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session) +{ + struct perf_evlist *evlist = session->evlist; + struct id_index_event *ie = &event->id_index; + size_t i, nr, max_nr; + + max_nr = (ie->header.size - sizeof(struct id_index_event)) / + sizeof(struct id_index_entry); + nr = ie->nr; + if (nr > max_nr) + return -EINVAL; + + if (dump_trace) + fprintf(stdout, " nr: %zu\n", nr); + + for (i = 0; i < nr; i++) { + struct id_index_entry *e = &ie->entries[i]; + struct perf_sample_id *sid; + + if (dump_trace) { + fprintf(stdout, " ... id: %"PRIu64, e->id); + fprintf(stdout, " idx: %"PRIu64, e->idx); + fprintf(stdout, " cpu: %"PRId64, e->cpu); + fprintf(stdout, " tid: %"PRId64"\n", e->tid); + } -out_free: - free(tracepoint); - goto out; + sid = perf_evlist__id2sid(evlist, e->id); + if (!sid) + return -ENOENT; + sid->idx = e->idx; + sid->cpu = e->cpu; + sid->tid = e->tid; + } + return 0; +} + +int perf_event__synthesize_id_index(struct perf_tool *tool, + perf_event__handler_t process, + struct perf_evlist *evlist, + struct machine *machine) +{ + union perf_event *ev; + struct perf_evsel *evsel; + size_t nr = 0, i = 0, sz, max_nr, n; + int err; + + pr_debug2("Synthesizing id index\n"); + + max_nr = (UINT16_MAX - sizeof(struct id_index_event)) / + sizeof(struct id_index_entry); + + evlist__for_each(evlist, evsel) + nr += evsel->ids; + + n = nr > max_nr ? max_nr : nr; + sz = sizeof(struct id_index_event) + n * sizeof(struct id_index_entry); + ev = zalloc(sz); + if (!ev) + return -ENOMEM; + + ev->id_index.header.type = PERF_RECORD_ID_INDEX; + ev->id_index.header.size = sz; + ev->id_index.nr = n; + + evlist__for_each(evlist, evsel) { + u32 j; + + for (j = 0; j < evsel->ids; j++) { + struct id_index_entry *e; + struct perf_sample_id *sid; + + if (i >= n) { + err = process(tool, ev, NULL, machine); + if (err) + goto out_err; + nr -= n; + i = 0; + } + + e = &ev->id_index.entries[i++]; + + e->id = evsel->id[j]; + + sid = perf_evlist__id2sid(evlist, e->id); + if (!sid) { + free(ev); + return -ENOENT; + } + + e->idx = sid->idx; + e->cpu = sid->cpu; + e->tid = sid->tid; + } + } + + sz = sizeof(struct id_index_event) + nr * sizeof(struct id_index_entry); + ev->id_index.header.size = sz; + ev->id_index.nr = nr; + + err = process(tool, ev, NULL, machine); +out_err: + free(ev); + + return err; }