diff options
Diffstat (limited to 'tools/perf/builtin-top.c')
-rw-r--r-- | tools/perf/builtin-top.c | 102 |
1 files changed, 57 insertions, 45 deletions
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 35ac016fcb98..aa0c73e57924 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -123,14 +123,9 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) } notes = symbol__annotation(sym); - if (notes->src != NULL) { - pthread_mutex_lock(¬es->lock); - goto out_assign; - } - pthread_mutex_lock(¬es->lock); - if (symbol__alloc_hist(sym) < 0) { + if (!symbol__hists(sym, top->evlist->nr_entries)) { pthread_mutex_unlock(¬es->lock); pr_err("Not enough memory for annotating '%s' symbol!\n", sym->name); @@ -138,9 +133,8 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) return err; } - err = symbol__annotate(sym, map, evsel, 0, NULL); + err = symbol__annotate(sym, map, evsel, 0, &top->annotation_opts, NULL); if (err == 0) { -out_assign: top->sym_filter_entry = he; } else { char msg[BUFSIZ]; @@ -188,7 +182,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip) static void perf_top__record_precise_ip(struct perf_top *top, struct hist_entry *he, struct perf_sample *sample, - int counter, u64 ip) + struct perf_evsel *evsel, u64 ip) { struct annotation *notes; struct symbol *sym = he->ms.sym; @@ -204,7 +198,7 @@ static void perf_top__record_precise_ip(struct perf_top *top, if (pthread_mutex_trylock(¬es->lock)) return; - err = hist_entry__inc_addr_samples(he, sample, counter, ip); + err = hist_entry__inc_addr_samples(he, sample, evsel, ip); pthread_mutex_unlock(¬es->lock); @@ -249,10 +243,9 @@ static void perf_top__show_details(struct perf_top *top) goto out_unlock; printf("Showing %s for %s\n", perf_evsel__name(top->sym_evsel), symbol->name); - printf(" Events Pcnt (>=%d%%)\n", top->sym_pcnt_filter); + printf(" Events Pcnt (>=%d%%)\n", top->annotation_opts.min_pcnt); - more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel, - 0, top->sym_pcnt_filter, top->print_entries, 4); + more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel, &top->annotation_opts); if (top->evlist->enabled) { if (top->zero) @@ -314,7 +307,7 @@ static void perf_top__print_sym_table(struct perf_top *top) hists__output_recalc_col_len(hists, top->print_entries - printed); putchar('\n'); hists__fprintf(hists, false, top->print_entries - printed, win_width, - top->min_percent, stdout, symbol_conf.use_callchain); + top->min_percent, stdout, !symbol_conf.use_callchain); } static void prompt_integer(int *target, const char *msg) @@ -412,7 +405,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top) fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top->count_filter); - fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", top->sym_pcnt_filter); + fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", top->annotation_opts.min_pcnt); fprintf(stdout, "\t[s] annotate symbol. \t(%s)\n", name?: "NULL"); fprintf(stdout, "\t[S] stop annotation.\n"); @@ -515,7 +508,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) prompt_integer(&top->count_filter, "Enter display event count filter"); break; case 'F': - prompt_percent(&top->sym_pcnt_filter, + prompt_percent(&top->annotation_opts.min_pcnt, "Enter details display event filter (percent)"); break; case 'K': @@ -613,7 +606,8 @@ static void *display_thread_tui(void *arg) perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, &top->session->header.env, - !top->record_opts.overwrite); + !top->record_opts.overwrite, + &top->annotation_opts); done = 1; return NULL; @@ -691,7 +685,7 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter, struct perf_evsel *evsel = iter->evsel; if (perf_hpp_list.sym && single) - perf_top__record_precise_ip(top, he, iter->sample, evsel->idx, al->addr); + perf_top__record_precise_ip(top, he, iter->sample, evsel, al->addr); hist__account_cycles(iter->sample->branch_stack, al, iter->sample, !(top->record_opts.branch_stack & PERF_SAMPLE_BRANCH_ANY)); @@ -742,7 +736,7 @@ static void perf_event__process_sample(struct perf_tool *tool, "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n" "Check /proc/sys/kernel/kptr_restrict.\n\n" "Kernel%s samples will not be resolved.\n", - al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ? + al.map && map__has_symbols(al.map) ? " modules" : ""); if (use_browser <= 0) sleep(5); @@ -750,7 +744,7 @@ static void perf_event__process_sample(struct perf_tool *tool, machine->kptr_restrict_warned = true; } - if (al.sym == NULL) { + if (al.sym == NULL && al.map != NULL) { const char *msg = "Kernel samples will not be resolved.\n"; /* * As we do lazy loading of symtabs we only will know if the @@ -764,8 +758,7 @@ static void perf_event__process_sample(struct perf_tool *tool, * invalid --vmlinux ;-) */ if (!machine->kptr_restrict_warned && !top->vmlinux_warned && - al.map == machine->vmlinux_maps[MAP__FUNCTION] && - RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) { + __map__is_kernel(al.map) && map__has_symbols(al.map)) { if (symbol_conf.vmlinux_name) { char serr[256]; dso__strerror_load(al.map->dso, serr, sizeof(serr)); @@ -817,14 +810,13 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) struct perf_session *session = top->session; union perf_event *event; struct machine *machine; - u64 end, start; int ret; md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx]; - if (perf_mmap__read_init(md, opts->overwrite, &start, &end) < 0) + if (perf_mmap__read_init(md) < 0) return; - while ((event = perf_mmap__read_event(md, opts->overwrite, &start, end)) != NULL) { + while ((event = perf_mmap__read_event(md)) != NULL) { ret = perf_evlist__parse_sample(evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); @@ -879,7 +871,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) } else ++session->evlist->stats.nr_unknown_events; next_event: - perf_mmap__consume(md, opts->overwrite); + perf_mmap__consume(md); } perf_mmap__read_done(md); @@ -1085,8 +1077,9 @@ static int __cmd_top(struct perf_top *top) if (top->session == NULL) return -1; - if (!objdump_path) { - ret = perf_env__lookup_objdump(&top->session->header.env); + if (!top->annotation_opts.objdump_path) { + ret = perf_env__lookup_objdump(&top->session->header.env, + &top->annotation_opts.objdump_path); if (ret) goto out_delete; } @@ -1141,11 +1134,6 @@ static int __cmd_top(struct perf_top *top) if (!target__none(&opts->target)) perf_evlist__enable(top->evlist); - /* Wait for a minimal set of events before starting the snapshot */ - perf_evlist__poll(top->evlist, 100); - - perf_top__mmap_read(top); - ret = -1; if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui : display_thread), top)) { @@ -1163,6 +1151,11 @@ static int __cmd_top(struct perf_top *top) } } + /* Wait for a minimal set of events before starting the snapshot */ + perf_evlist__poll(top->evlist, 100); + + perf_top__mmap_read(top); + while (!done) { u64 hits = top->samples; @@ -1224,8 +1217,10 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset) static int perf_top_config(const char *var, const char *value, void *cb __maybe_unused) { - if (!strcmp(var, "top.call-graph")) - var = "call-graph.record-mode"; /* fall-through */ + if (!strcmp(var, "top.call-graph")) { + var = "call-graph.record-mode"; + return perf_default_config(var, value, cb); + } if (!strcmp(var, "top.children")) { symbol_conf.cumulate_callchain = perf_config_bool(var, value); return 0; @@ -1262,10 +1257,17 @@ int cmd_top(int argc, const char **argv) .uses_mmap = true, }, .proc_map_timeout = 500, - .overwrite = 1, + /* + * FIXME: This will lose PERF_RECORD_MMAP and other metadata + * when we pause, fix that and reenable. Probably using a + * separate evlist with a dummy event, i.e. a non-overwrite + * ring buffer just for metadata events, while PERF_RECORD_SAMPLE + * stays in overwrite mode. -acme + * */ + .overwrite = 0, }, - .max_stack = sysctl_perf_event_max_stack, - .sym_pcnt_filter = 5, + .max_stack = sysctl__max_stack(), + .annotation_opts = annotation__default_options, .nr_threads_synthesize = UINT_MAX, }; struct record_opts *opts = &top.record_opts; @@ -1307,7 +1309,9 @@ int cmd_top(int argc, const char **argv) OPT_STRING(0, "sym-annotate", &top.sym_filter, "symbol name", "symbol to annotate"), OPT_BOOLEAN('z', "zero", &top.zero, "zero history across updates"), - OPT_UINTEGER('F', "freq", &opts->user_freq, "profile at this frequency"), + OPT_CALLBACK('F', "freq", &top.record_opts, "freq or 'max'", + "profile at this frequency", + record__parse_freq), OPT_INTEGER('E', "entries", &top.print_entries, "display this many functions"), OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols, @@ -1345,15 +1349,15 @@ int cmd_top(int argc, const char **argv) "only consider symbols in these comms"), OPT_STRING(0, "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", "only consider these symbols"), - OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src, + OPT_BOOLEAN(0, "source", &top.annotation_opts.annotate_src, "Interleave source code with assembly code (default)"), - OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw, + OPT_BOOLEAN(0, "asm-raw", &top.annotation_opts.show_asm_raw, "Display raw encoding of assembly instructions (default)"), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), - OPT_STRING(0, "objdump", &objdump_path, "path", + OPT_STRING(0, "objdump", &top.annotation_opts.objdump_path, "path", "objdump binary to use for disassembly and annotations"), - OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", + OPT_STRING('M', "disassembler-style", &top.annotation_opts.disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"), OPT_CALLBACK(0, "percent-limit", &top, "percent", @@ -1375,6 +1379,8 @@ int cmd_top(int argc, const char **argv) "Show raw trace event output (do not use print fmt or plugins)"), OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy, "Show entries in a hierarchy"), + OPT_BOOLEAN(0, "overwrite", &top.record_opts.overwrite, + "Use a backward ring buffer, default: no"), OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"), OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize, "number of thread to run event synthesize"), @@ -1389,6 +1395,9 @@ int cmd_top(int argc, const char **argv) if (status < 0) return status; + top.annotation_opts.min_pcnt = 5; + top.annotation_opts.context = 4; + top.evlist = perf_evlist__new(); if (top.evlist == NULL) return -ENOMEM; @@ -1420,6 +1429,9 @@ int cmd_top(int argc, const char **argv) } } + if (opts->branch_stack && callchain_param.enabled) + symbol_conf.show_branchflag_count = true; + sort__mode = SORT_MODE__TOP; /* display thread wants entries to be collapsed in a different tree */ perf_hpp_list.need_collapse = 1; @@ -1466,8 +1478,6 @@ int cmd_top(int argc, const char **argv) goto out_delete_evlist; } - symbol_conf.nr_events = top.evlist->nr_entries; - if (top.delay_secs < 1) top.delay_secs = 1; @@ -1490,6 +1500,8 @@ int cmd_top(int argc, const char **argv) if (status < 0) goto out_delete_evlist; + annotation_config__init(); + symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); if (symbol__init(NULL) < 0) return -1; |