diff options
Diffstat (limited to 'tools/perf/builtin-report.c')
-rw-r--r-- | tools/perf/builtin-report.c | 578 |
1 files changed, 401 insertions, 177 deletions
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 5f1d2a878fad..dcd93ee5fc24 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -59,6 +59,7 @@ #include <linux/ctype.h> #include <signal.h> #include <linux/bitmap.h> +#include <linux/list_sort.h> #include <linux/string.h> #include <linux/stringify.h> #include <linux/time64.h> @@ -67,11 +68,21 @@ #include <unistd.h> #include <linux/mman.h> +#ifdef HAVE_LIBTRACEEVENT +#include <traceevent/event-parse.h> +#endif + struct report { struct perf_tool tool; struct perf_session *session; struct evswitch evswitch; - bool use_tui, use_gtk, use_stdio; +#ifdef HAVE_SLANG_SUPPORT + bool use_tui; +#endif +#ifdef HAVE_GTK2_SUPPORT + bool use_gtk; +#endif + bool use_stdio; bool show_full_info; bool show_threads; bool inverted_callchain; @@ -84,9 +95,11 @@ struct report { bool nonany_branch_mode; bool group_set; bool stitch_lbr; + bool disable_order; + bool skip_empty; + bool data_type; int max_stack; struct perf_read_values show_threads_values; - struct annotation_options annotation_opts; const char *pretty_printing_style; const char *cpu_list; const char *symbol_filter_str; @@ -131,9 +144,19 @@ static int report__config(const char *var, const char *value, void *cb) if (!strcmp(var, "report.sort_order")) { default_sort_order = strdup(value); + if (!default_sort_order) { + pr_err("Not enough memory for report.sort_order\n"); + return -1; + } + return 0; + } + + if (!strcmp(var, "report.skip-empty")) { + rep->skip_empty = perf_config_bool(var, value); return 0; } + pr_debug("%s variable unknown, ignoring...", var); return 0; } @@ -149,7 +172,7 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter, struct mem_info *mi; struct branch_info *bi; - if (!ui__has_annotation() && !rep->symbol_ipc) + if (!ui__has_annotation() && !rep->symbol_ipc && !rep->data_type) return 0; if (sort__mode == SORT_MODE__BRANCH) { @@ -211,7 +234,7 @@ static void setup_forced_leader(struct report *report, struct evlist *evlist) { if (report->group_set) - perf_evlist__force_leader(evlist); + evlist__force_leader(evlist); } static int process_feature_event(struct perf_session *session, @@ -226,6 +249,8 @@ static int process_feature_event(struct perf_session *session, pr_err("failed: wrong feature ID: %" PRI_lu64 "\n", event->feat.feat_id); return -1; + } else if (rep->header_only) { + session_done = 1; } /* @@ -261,14 +286,16 @@ static int process_sample_event(struct perf_tool *tool, if (evswitch__discard(&rep->evswitch, evsel)) return 0; + addr_location__init(&al); if (machine__resolve(machine, &al, sample) < 0) { pr_debug("problem processing %d event, skipping it.\n", event->header.type); - return -1; + ret = -1; + goto out_put; } if (rep->stitch_lbr) - al.thread->lbr_stitch_enable = true; + thread__set_lbr_stitch_enable(al.thread, true); if (symbol_conf.hide_unresolved && al.sym == NULL) goto out_put; @@ -295,7 +322,7 @@ static int process_sample_event(struct perf_tool *tool, } if (al.map != NULL) - al.map->dso->hit = 1; + map__dso(al.map)->hit = 1; if (ui__has_annotation() || rep->symbol_ipc || rep->total_cycles_mode) { hist__account_cycles(sample->branch_stack, &al, sample, @@ -307,7 +334,7 @@ static int process_sample_event(struct perf_tool *tool, if (ret < 0) pr_debug("problem adding hist entry, skipping event\n"); out_put: - addr_location__put(&al); + addr_location__exit(&al); return ret; } @@ -323,7 +350,7 @@ static int process_read_event(struct perf_tool *tool, const char *name = evsel__name(evsel); int err = perf_read_values_add_value(&rep->show_threads_values, event->read.pid, event->read.tid, - evsel->idx, + evsel->core.idx, name, event->read.value); @@ -338,8 +365,9 @@ static int process_read_event(struct perf_tool *tool, static int report__setup_sample_type(struct report *rep) { struct perf_session *session = rep->session; - u64 sample_type = perf_evlist__combined_sample_type(session->evlist); + u64 sample_type = evlist__combined_sample_type(session->evlist); bool is_pipe = perf_data__is_pipe(session->data); + struct evsel *evsel; if (session->itrace_synth_opts->callchain || session->itrace_synth_opts->add_callchain || @@ -394,6 +422,19 @@ static int report__setup_sample_type(struct report *rep) } if (sort__mode == SORT_MODE__MEMORY) { + /* + * FIXUP: prior to kernel 5.18, Arm SPE missed to set + * PERF_SAMPLE_DATA_SRC bit in sample type. For backward + * compatibility, set the bit if it's an old perf data file. + */ + evlist__for_each_entry(session->evlist, evsel) { + if (strstr(evsel->name, "arm_spe") && + !(sample_type & PERF_SAMPLE_DATA_SRC)) { + evsel->core.attr.sample_type |= PERF_SAMPLE_DATA_SRC; + sample_type |= PERF_SAMPLE_DATA_SRC; + } + } + if (!is_pipe && !(sample_type & PERF_SAMPLE_DATA_SRC)) { ui__error("Selected --mem-mode but no mem data. " "Did you call perf record without -d?\n"); @@ -401,7 +442,7 @@ static int report__setup_sample_type(struct report *rep) } } - callchain_param_setup(sample_type); + callchain_param_setup(sample_type, perf_env__arch(&rep->session->header.env)); if (rep->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) { ui__warning("Can't find LBR callchain. Switch off --stitch-lbr.\n" @@ -410,8 +451,7 @@ static int report__setup_sample_type(struct report *rep) } /* ??? handle more cases than just ANY? */ - if (!(perf_evlist__combined_branch_type(session->evlist) & - PERF_SAMPLE_BRANCH_ANY)) + if (!(evlist__combined_branch_type(session->evlist) & PERF_SAMPLE_BRANCH_ANY)) rep->nonany_branch_mode = true; #if !defined(HAVE_LIBUNWIND_SUPPORT) && !defined(HAVE_DWARF_SUPPORT) @@ -434,7 +474,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report { size_t ret; char unit; - unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE]; + unsigned long nr_samples = hists->stats.nr_samples; u64 nr_events = hists->stats.total_period; struct evsel *evsel = hists_to_evsel(hists); char buf[512]; @@ -462,7 +502,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report nr_samples += pos_hists->stats.nr_non_filtered_samples; nr_events += pos_hists->stats.total_non_filtered_period; } else { - nr_samples += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE]; + nr_samples += pos_hists->stats.nr_samples; nr_events += pos_hists->stats.total_period; } } @@ -494,8 +534,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report return ret + fprintf(fp, "\n#\n"); } -static int perf_evlist__tui_block_hists_browse(struct evlist *evlist, - struct report *rep) +static int evlist__tui_block_hists_browse(struct evlist *evlist, struct report *rep) { struct evsel *pos; int i = 0, ret; @@ -503,8 +542,7 @@ static int perf_evlist__tui_block_hists_browse(struct evlist *evlist, evlist__for_each_entry(evlist, pos) { ret = report__browse_block_hists(&rep->block_reports[i++].hist, rep->min_percent, pos, - &rep->session->header.env, - &rep->annotation_opts); + &rep->session->header.env); if (ret != 0) return ret; } @@ -512,9 +550,7 @@ static int perf_evlist__tui_block_hists_browse(struct evlist *evlist, return 0; } -static int perf_evlist__tty_browse_hists(struct evlist *evlist, - struct report *rep, - const char *help) +static int evlist__tty_browse_hists(struct evlist *evlist, struct report *rep, const char *help) { struct evsel *pos; int i = 0; @@ -531,12 +567,14 @@ static int perf_evlist__tty_browse_hists(struct evlist *evlist, if (symbol_conf.event_group && !evsel__is_group_leader(pos)) continue; + if (rep->skip_empty && !hists->stats.nr_samples) + continue; + hists__fprintf_nr_sample_events(hists, rep, evname, stdout); if (rep->total_cycles_mode) { report__browse_block_hists(&rep->block_reports[i++].hist, - rep->min_percent, pos, - NULL, NULL); + rep->min_percent, pos, NULL); continue; } @@ -567,11 +605,11 @@ static void report__warn_kptr_restrict(const struct report *rep) struct map *kernel_map = machine__kernel_map(&rep->session->machines.host); struct kmap *kernel_kmap = kernel_map ? map__kmap(kernel_map) : NULL; - if (perf_evlist__exclude_kernel(rep->session->evlist)) + if (evlist__exclude_kernel(rep->session->evlist)) return; if (kernel_map == NULL || - (kernel_map->dso->hit && + (map__dso(kernel_map)->hit && (kernel_kmap->ref_reloc_sym == NULL || kernel_kmap->ref_reloc_sym->addr == 0))) { const char *desc = @@ -596,7 +634,7 @@ static int report__gtk_browse_hists(struct report *rep, const char *help) int (*hist_browser)(struct evlist *evlist, const char *help, struct hist_browser_timer *timer, float min_pcnt); - hist_browser = dlsym(perf_gtk_handle, "perf_evlist__gtk_browse_hists"); + hist_browser = dlsym(perf_gtk_handle, "evlist__gtk_browse_hists"); if (hist_browser == NULL) { ui__error("GTK browser not found!\n"); @@ -611,26 +649,27 @@ static int report__browse_hists(struct report *rep) int ret; struct perf_session *session = rep->session; struct evlist *evlist = session->evlist; - const char *help = perf_tip(system_path(TIPDIR)); + char *help = NULL, *path = NULL; - if (help == NULL) { + path = system_path(TIPDIR); + if (perf_tip(&help, path) || help == NULL) { /* fallback for people who don't install perf ;-) */ - help = perf_tip(DOCDIR); - if (help == NULL) - help = "Cannot load tips.txt file, please install perf!"; + free(path); + path = system_path(DOCDIR); + if (perf_tip(&help, path) || help == NULL) + help = strdup("Cannot load tips.txt file, please install perf!"); } + free(path); switch (use_browser) { case 1: if (rep->total_cycles_mode) { - ret = perf_evlist__tui_block_hists_browse(evlist, rep); + ret = evlist__tui_block_hists_browse(evlist, rep); break; } - ret = perf_evlist__tui_browse_hists(evlist, help, NULL, - rep->min_percent, - &session->header.env, - true, &rep->annotation_opts); + ret = evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent, + &session->header.env, true); /* * Usually "ret" is the last pressed key, and we only * care if the key notifies us to switch data file. @@ -642,25 +681,40 @@ static int report__browse_hists(struct report *rep) ret = report__gtk_browse_hists(rep, help); break; default: - ret = perf_evlist__tty_browse_hists(evlist, rep, help); + ret = evlist__tty_browse_hists(evlist, rep, help); break; } - + free(help); return ret; } static int report__collapse_hists(struct report *rep) { + struct perf_session *session = rep->session; + struct evlist *evlist = session->evlist; struct ui_progress prog; struct evsel *pos; int ret = 0; + /* + * The pipe data needs to setup hierarchy hpp formats now, because it + * cannot know about evsels in the data before reading the data. The + * normal file data saves the event (attribute) info in the header + * section, but pipe does not have the luxury. + */ + if (perf_data__is_pipe(session->data)) { + if (perf_hpp__setup_hists_formats(&perf_hpp_list, evlist) < 0) { + ui__error("Failed to setup hierarchy output formats\n"); + return -1; + } + } + ui_progress__init(&prog, rep->nr_entries, "Merging related events..."); evlist__for_each_entry(rep->session->evlist, pos) { struct hists *hists = evsel__hists(pos); - if (pos->idx == 0) + if (pos->core.idx == 0) hists->symbol_filter_str = rep->symbol_filter_str; hists->socket_filter = rep->socket_filter; @@ -671,7 +725,7 @@ static int report__collapse_hists(struct report *rep) /* Non-group events are considered as leader */ if (symbol_conf.event_group && !evsel__is_group_leader(pos)) { - struct hists *leader_hists = evsel__hists(pos->leader); + struct hists *leader_hists = evsel__hists(evsel__leader(pos)); hists__match(leader_hists, hists); hists__link(leader_hists, hists); @@ -690,8 +744,7 @@ static int hists__resort_cb(struct hist_entry *he, void *arg) if (rep->symbol_ipc && sym && !sym->annotate2) { struct evsel *evsel = hists_to_evsel(he->hists); - symbol__annotate2(&he->ms, evsel, - &annotation__default_options, NULL); + symbol__annotate2(&he->ms, evsel, NULL); } return 0; @@ -711,9 +764,44 @@ static void report__output_resort(struct report *rep) ui_progress__finish(); } +static int count_sample_event(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct evsel *evsel, + struct machine *machine __maybe_unused) +{ + struct hists *hists = evsel__hists(evsel); + + hists__inc_nr_events(hists); + return 0; +} + +static int count_lost_samples_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine __maybe_unused) +{ + struct report *rep = container_of(tool, struct report, tool); + struct evsel *evsel; + + evsel = evlist__id2evsel(rep->session->evlist, sample->id); + if (evsel) { + hists__inc_nr_lost_samples(evsel__hists(evsel), + event->lost_samples.lost); + } + return 0; +} + +static int process_attr(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct evlist **pevlist); + static void stats_setup(struct report *rep) { memset(&rep->tool, 0, sizeof(rep->tool)); + rep->tool.attr = process_attr; + rep->tool.sample = count_sample_event; + rep->tool.lost_samples = count_lost_samples_event; rep->tool.no_warn = true; } @@ -721,7 +809,8 @@ static int stats_print(struct report *rep) { struct perf_session *session = rep->session; - perf_session__fprintf_nr_events(session, stdout); + perf_session__fprintf_nr_events(session, stdout, rep->skip_empty); + evlist__fprintf_nr_events(session->evlist, stdout, rep->skip_empty); return 0; } @@ -733,142 +822,206 @@ static void tasks_setup(struct report *rep) rep->tool.mmap = perf_event__process_mmap; rep->tool.mmap2 = perf_event__process_mmap2; } + rep->tool.attr = process_attr; rep->tool.comm = perf_event__process_comm; rep->tool.exit = perf_event__process_exit; rep->tool.fork = perf_event__process_fork; rep->tool.no_warn = true; } -struct task { - struct thread *thread; - struct list_head list; - struct list_head children; +struct maps__fprintf_task_args { + int indent; + FILE *fp; + size_t printed; }; -static struct task *tasks_list(struct task *task, struct machine *machine) +static int maps__fprintf_task_cb(struct map *map, void *data) { - struct thread *parent_thread, *thread = task->thread; - struct task *parent_task; - - /* Already listed. */ - if (!list_empty(&task->list)) - return NULL; + struct maps__fprintf_task_args *args = data; + const struct dso *dso = map__dso(map); + u32 prot = map__prot(map); + int ret; - /* Last one in the chain. */ - if (thread->ppid == -1) - return task; + ret = fprintf(args->fp, + "%*s %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n", + args->indent, "", map__start(map), map__end(map), + prot & PROT_READ ? 'r' : '-', + prot & PROT_WRITE ? 'w' : '-', + prot & PROT_EXEC ? 'x' : '-', + map__flags(map) ? 's' : 'p', + map__pgoff(map), + dso->id.ino, dso->name); - parent_thread = machine__find_thread(machine, -1, thread->ppid); - if (!parent_thread) - return ERR_PTR(-ENOENT); + if (ret < 0) + return ret; - parent_task = thread__priv(parent_thread); - list_add_tail(&task->list, &parent_task->children); - return tasks_list(parent_task, machine); + args->printed += ret; + return 0; } static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp) { - size_t printed = 0; - struct map *map; + struct maps__fprintf_task_args args = { + .indent = indent, + .fp = fp, + .printed = 0, + }; - maps__for_each_entry(maps, map) { - printed += fprintf(fp, "%*s %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n", - indent, "", map->start, map->end, - map->prot & PROT_READ ? 'r' : '-', - map->prot & PROT_WRITE ? 'w' : '-', - map->prot & PROT_EXEC ? 'x' : '-', - map->flags & MAP_SHARED ? 's' : 'p', - map->pgoff, - map->dso->id.ino, map->dso->name); - } + maps__for_each_map(maps, maps__fprintf_task_cb, &args); - return printed; + return args.printed; } -static void task__print_level(struct task *task, FILE *fp, int level) +static int thread_level(struct machine *machine, const struct thread *thread) { - struct thread *thread = task->thread; - struct task *child; - int comm_indent = fprintf(fp, " %8d %8d %8d |%*s", - thread->pid_, thread->tid, thread->ppid, - level, ""); + struct thread *parent_thread; + int res; - fprintf(fp, "%s\n", thread__comm_str(thread)); + if (thread__tid(thread) <= 0) + return 0; - maps__fprintf_task(thread->maps, comm_indent, fp); + if (thread__ppid(thread) <= 0) + return 1; - if (!list_empty(&task->children)) { - list_for_each_entry(child, &task->children, list) - task__print_level(child, fp, level + 1); + parent_thread = machine__find_thread(machine, -1, thread__ppid(thread)); + if (!parent_thread) { + pr_err("Missing parent thread of %d\n", thread__tid(thread)); + return 0; } + res = 1 + thread_level(machine, parent_thread); + thread__put(parent_thread); + return res; } -static int tasks_print(struct report *rep, FILE *fp) +static void task__print_level(struct machine *machine, struct thread *thread, FILE *fp) { - struct perf_session *session = rep->session; - struct machine *machine = &session->machines.host; - struct task *tasks, *task; - unsigned int nr = 0, itask = 0, i; - struct rb_node *nd; - LIST_HEAD(list); + int level = thread_level(machine, thread); + int comm_indent = fprintf(fp, " %8d %8d %8d |%*s", + thread__pid(thread), thread__tid(thread), + thread__ppid(thread), level, ""); - /* - * No locking needed while accessing machine->threads, - * because --tasks is single threaded command. - */ + fprintf(fp, "%s\n", thread__comm_str(thread)); - /* Count all the threads. */ - for (i = 0; i < THREADS__TABLE_SIZE; i++) - nr += machine->threads[i].nr; + maps__fprintf_task(thread__maps(thread), comm_indent, fp); +} - tasks = malloc(sizeof(*tasks) * nr); - if (!tasks) - return -ENOMEM; +/* + * Sort two thread list nodes such that they form a tree. The first node is the + * root of the tree, its children are ordered numerically after it. If a child + * has children itself then they appear immediately after their parent. For + * example, the 4 threads in the order they'd appear in the list: + * - init with a TID 1 and a parent of 0 + * - systemd with a TID 3000 and a parent of init/1 + * - systemd child thread with TID 4000, the parent is 3000 + * - NetworkManager is a child of init with a TID of 3500. + */ +static int task_list_cmp(void *priv, const struct list_head *la, const struct list_head *lb) +{ + struct machine *machine = priv; + struct thread_list *task_a = list_entry(la, struct thread_list, list); + struct thread_list *task_b = list_entry(lb, struct thread_list, list); + struct thread *a = task_a->thread; + struct thread *b = task_b->thread; + int level_a, level_b, res; + + /* Same thread? */ + if (thread__tid(a) == thread__tid(b)) + return 0; - for (i = 0; i < THREADS__TABLE_SIZE; i++) { - struct threads *threads = &machine->threads[i]; + /* Compare a and b to root. */ + if (thread__tid(a) == 0) + return -1; - for (nd = rb_first_cached(&threads->entries); nd; - nd = rb_next(nd)) { - task = tasks + itask++; + if (thread__tid(b) == 0) + return 1; - task->thread = rb_entry(nd, struct thread, rb_node); - INIT_LIST_HEAD(&task->children); - INIT_LIST_HEAD(&task->list); - thread__set_priv(task->thread, task); - } - } + /* If parents match sort by tid. */ + if (thread__ppid(a) == thread__ppid(b)) + return thread__tid(a) < thread__tid(b) ? -1 : 1; /* - * Iterate every task down to the unprocessed parent - * and link all in task children list. Task with no - * parent is added into 'list'. + * Find a and b such that if they are a child of each other a and b's + * tid's match, otherwise a and b have a common parent and distinct + * tid's to sort by. First make the depths of the threads match. */ - for (itask = 0; itask < nr; itask++) { - task = tasks + itask; - - if (!list_empty(&task->list)) - continue; - - task = tasks_list(task, machine); - if (IS_ERR(task)) { - pr_err("Error: failed to process tasks\n"); - free(tasks); - return PTR_ERR(task); + level_a = thread_level(machine, a); + level_b = thread_level(machine, b); + a = thread__get(a); + b = thread__get(b); + for (int i = level_a; i > level_b; i--) { + struct thread *parent = machine__find_thread(machine, -1, thread__ppid(a)); + + thread__put(a); + if (!parent) { + pr_err("Missing parent thread of %d\n", thread__tid(a)); + thread__put(b); + return -1; } + a = parent; + } + for (int i = level_b; i > level_a; i--) { + struct thread *parent = machine__find_thread(machine, -1, thread__ppid(b)); - if (task) - list_add_tail(&task->list, &list); + thread__put(b); + if (!parent) { + pr_err("Missing parent thread of %d\n", thread__tid(b)); + thread__put(a); + return 1; + } + b = parent; + } + /* Search up to a common parent. */ + while (thread__ppid(a) != thread__ppid(b)) { + struct thread *parent; + + parent = machine__find_thread(machine, -1, thread__ppid(a)); + thread__put(a); + if (!parent) + pr_err("Missing parent thread of %d\n", thread__tid(a)); + a = parent; + parent = machine__find_thread(machine, -1, thread__ppid(b)); + thread__put(b); + if (!parent) + pr_err("Missing parent thread of %d\n", thread__tid(b)); + b = parent; + if (!a || !b) { + /* Handle missing parent (unexpected) with some sanity. */ + thread__put(a); + thread__put(b); + return !a && !b ? 0 : (!a ? -1 : 1); + } + } + if (thread__tid(a) == thread__tid(b)) { + /* a is a child of b or vice-versa, deeper levels appear later. */ + res = level_a < level_b ? -1 : (level_a > level_b ? 1 : 0); + } else { + /* Sort by tid now the parent is the same. */ + res = thread__tid(a) < thread__tid(b) ? -1 : 1; } + thread__put(a); + thread__put(b); + return res; +} - fprintf(fp, "# %8s %8s %8s %s\n", "pid", "tid", "ppid", "comm"); +static int tasks_print(struct report *rep, FILE *fp) +{ + struct machine *machine = &rep->session->machines.host; + LIST_HEAD(tasks); + int ret; - list_for_each_entry(task, &list, list) - task__print_level(task, fp, 0); + ret = machine__thread_list(machine, &tasks); + if (!ret) { + struct thread_list *task; - free(tasks); - return 0; + list_sort(machine, &tasks, task_list_cmp); + + fprintf(fp, "# %8s %8s %8s %s\n", "pid", "tid", "ppid", "comm"); + + list_for_each_entry(task, &tasks, list) + task__print_level(machine, task->thread, fp); + } + thread_list__delete(&tasks); + return ret; } static int __cmd_report(struct report *rep) @@ -914,6 +1067,8 @@ static int __cmd_report(struct report *rep) return ret; } + evlist__check_mem_load_aux(session->evlist); + if (rep->stats_mode) return stats_print(rep); @@ -933,8 +1088,10 @@ static int __cmd_report(struct report *rep) perf_session__fprintf_dsos(session, stdout); if (dump_trace) { - perf_session__fprintf_nr_events(session, stdout); - perf_evlist__fprintf_nr_events(session->evlist, stdout); + perf_session__fprintf_nr_events(session, stdout, + rep->skip_empty); + evlist__fprintf_nr_events(session->evlist, stdout, + rep->skip_empty); return 0; } } @@ -1093,8 +1250,8 @@ static int process_attr(struct perf_tool *tool __maybe_unused, * Check if we need to enable callchains based * on events sample_type. */ - sample_type = perf_evlist__combined_sample_type(*pevlist); - callchain_param_setup(sample_type); + sample_type = evlist__combined_sample_type(*pevlist); + callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env)); return 0; } @@ -1129,7 +1286,9 @@ int cmd_report(int argc, const char **argv) .lost = perf_event__process_lost, .read = process_read_event, .attr = process_attr, +#ifdef HAVE_LIBTRACEEVENT .tracing_data = perf_event__process_tracing_data, +#endif .build_id = perf_event__process_build_id, .id_index = perf_event__process_id_index, .auxtrace_info = perf_event__process_auxtrace_info, @@ -1142,14 +1301,17 @@ int cmd_report(int argc, const char **argv) .max_stack = PERF_MAX_STACK_DEPTH, .pretty_printing_style = "normal", .socket_filter = -1, - .annotation_opts = annotation__default_options, + .skip_empty = true, }; + char *sort_order_help = sort_help("sort by key(s):"); + char *field_order_help = sort_help("output field(s): overhead period sample "); + const char *disassembler_style = NULL, *objdump_path = NULL, *addr2line_path = NULL; const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), - OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"), + OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any warnings or messages"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_BOOLEAN(0, "stats", &report.stats_mode, "Display event stats"), @@ -1170,17 +1332,21 @@ int cmd_report(int argc, const char **argv) "Show per-thread event counters"), OPT_STRING(0, "pretty", &report.pretty_printing_style, "key", "pretty printing style key: normal raw"), +#ifdef HAVE_SLANG_SUPPORT OPT_BOOLEAN(0, "tui", &report.use_tui, "Use the TUI interface"), +#endif +#ifdef HAVE_GTK2_SUPPORT OPT_BOOLEAN(0, "gtk", &report.use_gtk, "Use the GTK2 interface"), +#endif OPT_BOOLEAN(0, "stdio", &report.use_stdio, "Use the stdio interface"), OPT_BOOLEAN(0, "header", &report.header, "Show data header."), OPT_BOOLEAN(0, "header-only", &report.header_only, "Show only data header."), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - sort_help("sort by key(s):")), + sort_order_help), OPT_STRING('F', "fields", &field_order, "key[,keys...]", - sort_help("output field(s): overhead period sample ")), + field_order_help), OPT_BOOLEAN(0, "show-cpu-utilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_BOOLEAN_FLAG(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, @@ -1232,15 +1398,15 @@ int cmd_report(int argc, const char **argv) "list of cpus to profile"), OPT_BOOLEAN('I', "show-info", &report.show_full_info, "Display extended information about perf.data file"), - OPT_BOOLEAN(0, "source", &report.annotation_opts.annotate_src, + OPT_BOOLEAN(0, "source", &annotate_opts.annotate_src, "Interleave source code with assembly code (default)"), - OPT_BOOLEAN(0, "asm-raw", &report.annotation_opts.show_asm_raw, + OPT_BOOLEAN(0, "asm-raw", &annotate_opts.show_asm_raw, "Display raw encoding of assembly instructions (default)"), - OPT_STRING('M', "disassembler-style", &report.annotation_opts.disassembler_style, "disassembler style", + OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), - OPT_STRING(0, "prefix", &report.annotation_opts.prefix, "prefix", + OPT_STRING(0, "prefix", &annotate_opts.prefix, "prefix", "Add prefix to source file path names in programs (with --prefix-strip)"), - OPT_STRING(0, "prefix-strip", &report.annotation_opts.prefix_strip, "N", + OPT_STRING(0, "prefix-strip", &annotate_opts.prefix_strip, "N", "Strip first N entries of source file path name in programs (with --prefix)"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), @@ -1255,8 +1421,10 @@ int cmd_report(int argc, const char **argv) parse_branch_mode), OPT_BOOLEAN(0, "branch-history", &branch_call_mode, "add last branch records to call history"), - OPT_STRING(0, "objdump", &report.annotation_opts.objdump_path, "path", + OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), + OPT_STRING(0, "addr2line", &addr2line_path, "path", + "addr2line binary to use for line numbers"), OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, "Disable symbol demangling"), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, @@ -1281,7 +1449,7 @@ int cmd_report(int argc, const char **argv) "only show processor socket that match with this filter"), OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace, "Show raw trace event output (do not use print fmt or plugins)"), - OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy, + OPT_BOOLEAN('H', "hierarchy", &symbol_conf.report_hierarchy, "Show entries in a hierarchy"), OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode", "'always' (default), 'never' or 'auto' only applicable to --stdio mode", @@ -1290,7 +1458,7 @@ int cmd_report(int argc, const char **argv) "Time span of interest (start,stop)"), OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name, "Show inline function"), - OPT_CALLBACK(0, "percent-type", &report.annotation_opts, "local-period", + OPT_CALLBACK(0, "percent-type", &annotate_opts, "local-period", "Set percent type local/global-period/hits", annotate_parse_percent_type), OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs, "Show times in nanosecs"), @@ -1300,6 +1468,10 @@ int cmd_report(int argc, const char **argv) OPTS_EVSWITCH(&report.evswitch), OPT_BOOLEAN(0, "total-cycles", &report.total_cycles_mode, "Sort all blocks by 'Sampled Cycles%'"), + OPT_BOOLEAN(0, "disable-order", &report.disable_order, + "Disable raw trace ordering"), + OPT_BOOLEAN(0, "skip-empty", &report.skip_empty, + "Do not display empty (or dummy) events in the output"), OPT_END() }; struct perf_data data = { @@ -1309,11 +1481,20 @@ int cmd_report(int argc, const char **argv) char sort_tmp[128]; if (ret < 0) - return ret; + goto exit; + + /* + * tasks_mode require access to exited threads to list those that are in + * the data file. Off-cpu events are synthesized after other events and + * reference exited threads. + */ + symbol_conf.keep_exited_threads = true; + + annotation_options__init(); ret = perf_config(report__config, &report); if (ret) - return ret; + goto exit; argc = parse_options(argc, argv, options, report_usage, 0); if (argc) { @@ -1327,25 +1508,39 @@ int cmd_report(int argc, const char **argv) report.symbol_filter_str = argv[0]; } - if (annotate_check_args(&report.annotation_opts) < 0) - return -EINVAL; + if (disassembler_style) { + annotate_opts.disassembler_style = strdup(disassembler_style); + if (!annotate_opts.disassembler_style) + return -ENOMEM; + } + if (objdump_path) { + annotate_opts.objdump_path = strdup(objdump_path); + if (!annotate_opts.objdump_path) + return -ENOMEM; + } + if (addr2line_path) { + symbol_conf.addr2line_path = strdup(addr2line_path); + if (!symbol_conf.addr2line_path) + return -ENOMEM; + } + + if (annotate_check_args() < 0) { + ret = -EINVAL; + goto exit; + } if (report.mmaps_mode) report.tasks_mode = true; + if (dump_trace && report.disable_order) + report.tool.ordered_events = false; + if (quiet) perf_quiet_option(); - if (symbol_conf.vmlinux_name && - access(symbol_conf.vmlinux_name, R_OK)) { - pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name); - return -EINVAL; - } - if (symbol_conf.kallsyms_name && - access(symbol_conf.kallsyms_name, R_OK)) { - pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name); - return -EINVAL; - } + ret = symbol__validate_sym_arguments(); + if (ret) + goto exit; if (report.inverted_callchain) callchain_param.order = ORDER_CALLER; @@ -1367,13 +1562,15 @@ int cmd_report(int argc, const char **argv) data.force = symbol_conf.force; repeat: - session = perf_session__new(&data, false, &report.tool); - if (IS_ERR(session)) - return PTR_ERR(session); + session = perf_session__new(&data, &report.tool); + if (IS_ERR(session)) { + ret = PTR_ERR(session); + goto exit; + } ret = evswitch__init(&report.evswitch, session->evlist, stderr); if (ret) - return ret; + goto exit; if (zstd_init(&(session->zstd_data), 0) < 0) pr_warning("Decompression initialization failed. Reported data may be incomplete.\n"); @@ -1389,12 +1586,12 @@ repeat: has_br_stack = perf_header__has_feat(&session->header, HEADER_BRANCH_STACK); - if (perf_evlist__combined_sample_type(session->evlist) & PERF_SAMPLE_STACK_USER) + if (evlist__combined_sample_type(session->evlist) & PERF_SAMPLE_STACK_USER) has_br_stack = false; setup_forced_leader(&report, session->evlist); - if (symbol_conf.group_sort_idx && !session->evlist->nr_groups) { + if (symbol_conf.group_sort_idx && evlist__nr_groups(session->evlist) == 0) { parse_options_usage(NULL, options, "group-sort-idx", 0); ret = -EINVAL; goto error; @@ -1452,10 +1649,14 @@ repeat: if (report.use_stdio) use_browser = 0; +#ifdef HAVE_SLANG_SUPPORT else if (report.use_tui) use_browser = 1; +#endif +#ifdef HAVE_GTK2_SUPPORT else if (report.use_gtk) use_browser = 2; +#endif /* Force tty output for header output and per-thread stat. */ if (report.header || report.header_only || report.show_threads) @@ -1478,6 +1679,16 @@ repeat: sort_order = NULL; } + if (sort_order && strstr(sort_order, "type")) { + report.data_type = true; + annotate_opts.annotate_src = false; + +#ifndef HAVE_DWARF_GETLOCATIONS_SUPPORT + pr_err("Error: Data type profiling is disabled due to missing DWARF support\n"); + goto error; +#endif + } + if (strcmp(input_name, "-") != 0) setup_browser(true); else @@ -1515,6 +1726,13 @@ repeat: perf_session__fprintf_info(session, stdout, report.show_full_info); if (report.header_only) { + if (data.is_pipe) { + /* + * we need to process first few records + * which contains PERF_RECORD_HEADER_FEATURE. + */ + perf_session__process_events(session); + } ret = 0; goto error; } @@ -1529,7 +1747,7 @@ repeat: * so don't allocate extra space that won't be used in the stdio * implementation. */ - if (ui__has_annotation() || report.symbol_ipc || + if (ui__has_annotation() || report.symbol_ipc || report.data_type || report.total_cycles_mode) { ret = symbol__annotation_init(); if (ret < 0) @@ -1547,9 +1765,8 @@ repeat: * See symbol__browser_index. */ symbol_conf.priv_size += sizeof(u32); - symbol_conf.sort_by_name = true; } - annotation_config__init(&report.annotation_opts); + annotation_config__init(); } if (symbol__init(&session->header.env) < 0) @@ -1568,6 +1785,7 @@ repeat: report.range_num); } +#ifdef HAVE_LIBTRACEEVENT if (session->tevent.pevent && tep_set_function_resolver(session->tevent.pevent, machine__resolve_kernel_addr, @@ -1576,7 +1794,7 @@ repeat: __func__); return -1; } - +#endif sort__setup_elide(stdout); ret = __cmd_report(&report); @@ -1587,6 +1805,8 @@ repeat: } else ret = 0; + if (!use_browser && (verbose > 2 || debug_kmaps)) + perf_session__dump_kmaps(session); error: if (report.ptime_range) { itrace_synth_opts__clear_time_range(&itrace_synth_opts); @@ -1601,5 +1821,9 @@ error: zstd_fini(&(session->zstd_data)); perf_session__delete(session); +exit: + annotation_options__exit(); + free(sort_order_help); + free(field_order_help); return ret; } |