diff options
Diffstat (limited to 'tools/perf/util')
107 files changed, 5188 insertions, 1676 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 8c6c8a0ca642..2fa7d8b69873 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -70,6 +70,7 @@ libperf-y += stat.o libperf-y += stat-shadow.o libperf-y += record.o libperf-y += srcline.o +libperf-y += str_error_r.o libperf-y += data.o libperf-y += tsc.o libperf-y += cloexec.o @@ -84,6 +85,7 @@ libperf-y += parse-regs-options.o libperf-y += term.o libperf-y += help-unknown-cmd.o libperf-y += mem-events.o +libperf-y += vsprintf.o libperf-$(CONFIG_LIBBPF) += bpf-loader.o libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o @@ -99,7 +101,10 @@ libperf-$(CONFIG_DWARF) += probe-finder.o libperf-$(CONFIG_DWARF) += dwarf-aux.o libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o +libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind-local.o libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o +libperf-$(CONFIG_LIBUNWIND_X86) += libunwind/x86_32.o +libperf-$(CONFIG_LIBUNWIND_AARCH64) += libunwind/arm64.o libperf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o @@ -108,6 +113,7 @@ libperf-y += scripting-engines/ libperf-$(CONFIG_ZLIB) += zlib.o libperf-$(CONFIG_LZMA) += lzma.o libperf-y += demangle-java.o +libperf-y += demangle-rust.o ifdef CONFIG_JITDUMP libperf-$(CONFIG_LIBELF) += jitdump.o @@ -170,6 +176,14 @@ $(OUTPUT)util/libstring.o: ../lib/string.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) +$(OUTPUT)util/str_error_r.o: ../lib/str_error_r.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) + $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) + +$(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c index c0b43ee40d95..6455471d9cd1 100644 --- a/tools/perf/util/alias.c +++ b/tools/perf/util/alias.c @@ -1,4 +1,6 @@ #include "cache.h" +#include "util.h" +#include "config.h" static const char *alias_key; static char *alias_val; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 7e5a1e8874ce..e9825fe825fd 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -354,6 +354,15 @@ static struct ins_ops nop_ops = { .scnprintf = nop__scnprintf, }; +static struct ins_ops ret_ops = { + .scnprintf = ins__raw_scnprintf, +}; + +bool ins__is_ret(const struct ins *ins) +{ + return ins->ops == &ret_ops; +} + static struct ins instructions[] = { { .name = "add", .ops = &mov_ops, }, { .name = "addl", .ops = &mov_ops, }, @@ -444,6 +453,7 @@ static struct ins instructions[] = { { .name = "xadd", .ops = &mov_ops, }, { .name = "xbeginl", .ops = &jump_ops, }, { .name = "xbeginq", .ops = &jump_ops, }, + { .name = "retq", .ops = &ret_ops, }, }; static int ins__key_cmp(const void *name, const void *insp) @@ -1512,13 +1522,14 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, const char *d_filename; const char *evsel_name = perf_evsel__name(evsel); struct annotation *notes = symbol__annotation(sym); + struct sym_hist *h = annotation__histogram(notes, evsel->idx); struct disasm_line *pos, *queue = NULL; u64 start = map__rip_2objdump(map, sym->start); int printed = 2, queue_len = 0; int more = 0; u64 len; int width = 8; - int namelen, evsel_name_len, graph_dotted_len; + int graph_dotted_len; filename = strdup(dso->long_name); if (!filename) @@ -1530,17 +1541,14 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, d_filename = basename(filename); len = symbol__size(sym); - namelen = strlen(d_filename); - evsel_name_len = strlen(evsel_name); if (perf_evsel__is_group_event(evsel)) width *= evsel->nr_members; - printf(" %-*.*s| Source code & Disassembly of %s for %s\n", - width, width, "Percent", d_filename, evsel_name); + graph_dotted_len = printf(" %-*.*s| Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n", + width, width, "Percent", d_filename, evsel_name, h->sum); - graph_dotted_len = width + namelen + evsel_name_len; - printf("-%-*.*s-----------------------------------------\n", + printf("%-*.*s----\n", graph_dotted_len, graph_dotted_len, graph_dotted_line); if (verbose) @@ -1676,11 +1684,6 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, return 0; } -int hist_entry__annotate(struct hist_entry *he, size_t privsize) -{ - return symbol__annotate(he->ms.sym, he->ms.map, privsize); -} - bool ui__has_annotation(void) { return use_browser == 1 && perf_hpp_list.sym; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 9241f8c2b7e1..a23084f54128 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -48,6 +48,7 @@ struct ins { bool ins__is_jump(const struct ins *ins); bool ins__is_call(const struct ins *ins); +bool ins__is_ret(const struct ins *ins); int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops); struct annotation; @@ -156,8 +157,6 @@ void symbol__annotate_zero_histograms(struct symbol *sym); int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize); -int hist_entry__annotate(struct hist_entry *he, size_t privsize); - int symbol__annotate_init(struct map *map, struct symbol *sym); int symbol__annotate_printf(struct symbol *sym, struct map *map, struct perf_evsel *evsel, bool full_paths, diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 767989e0e312..ac5f0d7167e6 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -63,6 +63,7 @@ enum itrace_period_type { * @calls: limit branch samples to calls (can be combined with @returns) * @returns: limit branch samples to returns (can be combined with @calls) * @callchain: add callchain to 'instructions' events + * @thread_stack: feed branches to the thread_stack * @last_branch: add branch context to 'instruction' events * @callchain_sz: maximum callchain size * @last_branch_sz: branch context size @@ -82,6 +83,7 @@ struct itrace_synth_opts { bool calls; bool returns; bool callchain; + bool thread_stack; bool last_branch; unsigned int callchain_sz; unsigned int last_branch_sz; diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 493307d1414c..1f12e4e40006 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -37,6 +37,9 @@ DEFINE_PRINT_FN(info, 1) DEFINE_PRINT_FN(debug, 1) struct bpf_prog_priv { + bool is_tp; + char *sys_name; + char *evt_name; struct perf_probe_event pev; bool need_prologue; struct bpf_insn *insns_buf; @@ -118,6 +121,8 @@ clear_prog_priv(struct bpf_program *prog __maybe_unused, cleanup_perf_probe_events(&priv->pev, 1); zfree(&priv->insns_buf); zfree(&priv->type_mapping); + zfree(&priv->sys_name); + zfree(&priv->evt_name); free(priv); } @@ -269,7 +274,8 @@ nextline: } static int -parse_prog_config(const char *config_str, struct perf_probe_event *pev) +parse_prog_config(const char *config_str, const char **p_main_str, + bool *is_tp, struct perf_probe_event *pev) { int err; const char *main_str = parse_prog_config_kvpair(config_str, pev); @@ -277,6 +283,22 @@ parse_prog_config(const char *config_str, struct perf_probe_event *pev) if (IS_ERR(main_str)) return PTR_ERR(main_str); + *p_main_str = main_str; + if (!strchr(main_str, '=')) { + /* Is a tracepoint event? */ + const char *s = strchr(main_str, ':'); + + if (!s) { + pr_debug("bpf: '%s' is not a valid tracepoint\n", + config_str); + return -BPF_LOADER_ERRNO__CONFIG; + } + + *is_tp = true; + return 0; + } + + *is_tp = false; err = parse_perf_probe_command(main_str, pev); if (err < 0) { pr_debug("bpf: '%s' is not a valid config string\n", @@ -292,7 +314,8 @@ config_bpf_program(struct bpf_program *prog) { struct perf_probe_event *pev = NULL; struct bpf_prog_priv *priv = NULL; - const char *config_str; + const char *config_str, *main_str; + bool is_tp = false; int err; /* Initialize per-program probing setting */ @@ -313,10 +336,19 @@ config_bpf_program(struct bpf_program *prog) pev = &priv->pev; pr_debug("bpf: config program '%s'\n", config_str); - err = parse_prog_config(config_str, pev); + err = parse_prog_config(config_str, &main_str, &is_tp, pev); if (err) goto errout; + if (is_tp) { + char *s = strchr(main_str, ':'); + + priv->is_tp = true; + priv->sys_name = strndup(main_str, s - main_str); + priv->evt_name = strdup(s + 1); + goto set_priv; + } + if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) { pr_debug("bpf: '%s': group for event is set and not '%s'.\n", config_str, PERF_BPF_PROBE_GROUP); @@ -339,7 +371,8 @@ config_bpf_program(struct bpf_program *prog) } pr_debug("bpf: config '%s' is ok\n", config_str); - err = bpf_program__set_private(prog, priv, clear_prog_priv); +set_priv: + err = bpf_program__set_priv(prog, priv, clear_prog_priv); if (err) { pr_debug("Failed to set priv for program '%s'\n", config_str); goto errout; @@ -380,15 +413,14 @@ preproc_gen_prologue(struct bpf_program *prog, int n, struct bpf_insn *orig_insns, int orig_insns_cnt, struct bpf_prog_prep_result *res) { + struct bpf_prog_priv *priv = bpf_program__priv(prog); struct probe_trace_event *tev; struct perf_probe_event *pev; - struct bpf_prog_priv *priv; struct bpf_insn *buf; size_t prologue_cnt = 0; int i, err; - err = bpf_program__get_private(prog, (void **)&priv); - if (err || !priv) + if (IS_ERR(priv) || !priv || priv->is_tp) goto errout; pev = &priv->pev; @@ -535,17 +567,21 @@ static int map_prologue(struct perf_probe_event *pev, int *mapping, static int hook_load_preprocessor(struct bpf_program *prog) { + struct bpf_prog_priv *priv = bpf_program__priv(prog); struct perf_probe_event *pev; - struct bpf_prog_priv *priv; bool need_prologue = false; int err, i; - err = bpf_program__get_private(prog, (void **)&priv); - if (err || !priv) { + if (IS_ERR(priv) || !priv) { pr_debug("Internal error when hook preprocessor\n"); return -BPF_LOADER_ERRNO__INTERNAL; } + if (priv->is_tp) { + priv->need_prologue = false; + return 0; + } + pev = &priv->pev; for (i = 0; i < pev->ntevs; i++) { struct probe_trace_event *tev = &pev->tevs[i]; @@ -607,9 +643,18 @@ int bpf__probe(struct bpf_object *obj) if (err) goto out; - err = bpf_program__get_private(prog, (void **)&priv); - if (err || !priv) + priv = bpf_program__priv(prog); + if (IS_ERR(priv) || !priv) { + err = PTR_ERR(priv); goto out; + } + + if (priv->is_tp) { + bpf_program__set_tracepoint(prog); + continue; + } + + bpf_program__set_kprobe(prog); pev = &priv->pev; err = convert_perf_probe_events(pev, 1); @@ -645,13 +690,12 @@ int bpf__unprobe(struct bpf_object *obj) { int err, ret = 0; struct bpf_program *prog; - struct bpf_prog_priv *priv; bpf_object__for_each_program(prog, obj) { + struct bpf_prog_priv *priv = bpf_program__priv(prog); int i; - err = bpf_program__get_private(prog, (void **)&priv); - if (err || !priv) + if (IS_ERR(priv) || !priv || priv->is_tp) continue; for (i = 0; i < priv->pev.ntevs; i++) { @@ -694,26 +738,34 @@ int bpf__load(struct bpf_object *obj) return 0; } -int bpf__foreach_tev(struct bpf_object *obj, - bpf_prog_iter_callback_t func, - void *arg) +int bpf__foreach_event(struct bpf_object *obj, + bpf_prog_iter_callback_t func, + void *arg) { struct bpf_program *prog; int err; bpf_object__for_each_program(prog, obj) { + struct bpf_prog_priv *priv = bpf_program__priv(prog); struct probe_trace_event *tev; struct perf_probe_event *pev; - struct bpf_prog_priv *priv; int i, fd; - err = bpf_program__get_private(prog, - (void **)&priv); - if (err || !priv) { + if (IS_ERR(priv) || !priv) { pr_debug("bpf: failed to get private field\n"); return -BPF_LOADER_ERRNO__INTERNAL; } + if (priv->is_tp) { + fd = bpf_program__fd(prog); + err = (*func)(priv->sys_name, priv->evt_name, fd, arg); + if (err) { + pr_debug("bpf: tracepoint call back failed, stop iterate\n"); + return err; + } + continue; + } + pev = &priv->pev; for (i = 0; i < pev->ntevs; i++) { tev = &pev->tevs[i]; @@ -731,7 +783,7 @@ int bpf__foreach_tev(struct bpf_object *obj, return fd; } - err = (*func)(tev, fd, arg); + err = (*func)(tev->group, tev->event, fd, arg); if (err) { pr_debug("bpf: call back failed, stop iterate\n"); return err; @@ -897,15 +949,12 @@ bpf_map_priv__clone(struct bpf_map_priv *priv) static int bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op) { - struct bpf_map_priv *priv; - const char *map_name; - int err; + const char *map_name = bpf_map__name(map); + struct bpf_map_priv *priv = bpf_map__priv(map); - map_name = bpf_map__get_name(map); - err = bpf_map__get_private(map, (void **)&priv); - if (err) { + if (IS_ERR(priv)) { pr_debug("Failed to get private from map %s\n", map_name); - return err; + return PTR_ERR(priv); } if (!priv) { @@ -916,7 +965,7 @@ bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op) } INIT_LIST_HEAD(&priv->ops_list); - if (bpf_map__set_private(map, priv, bpf_map_priv__clear)) { + if (bpf_map__set_priv(map, priv, bpf_map_priv__clear)) { free(priv); return -BPF_LOADER_ERRNO__INTERNAL; } @@ -948,30 +997,26 @@ static int __bpf_map__config_value(struct bpf_map *map, struct parse_events_term *term) { - struct bpf_map_def def; struct bpf_map_op *op; - const char *map_name; - int err; + const char *map_name = bpf_map__name(map); + const struct bpf_map_def *def = bpf_map__def(map); - map_name = bpf_map__get_name(map); - - err = bpf_map__get_def(map, &def); - if (err) { + if (IS_ERR(def)) { pr_debug("Unable to get map definition from '%s'\n", map_name); return -BPF_LOADER_ERRNO__INTERNAL; } - if (def.type != BPF_MAP_TYPE_ARRAY) { + if (def->type != BPF_MAP_TYPE_ARRAY) { pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n", map_name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; } - if (def.key_size < sizeof(unsigned int)) { + if (def->key_size < sizeof(unsigned int)) { pr_debug("Map %s has incorrect key size\n", map_name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE; } - switch (def.value_size) { + switch (def->value_size) { case 1: case 2: case 4: @@ -1014,12 +1059,10 @@ __bpf_map__config_event(struct bpf_map *map, struct perf_evlist *evlist) { struct perf_evsel *evsel; - struct bpf_map_def def; + const struct bpf_map_def *def; struct bpf_map_op *op; - const char *map_name; - int err; + const char *map_name = bpf_map__name(map); - map_name = bpf_map__get_name(map); evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str); if (!evsel) { pr_debug("Event (for '%s') '%s' doesn't exist\n", @@ -1027,18 +1070,18 @@ __bpf_map__config_event(struct bpf_map *map, return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT; } - err = bpf_map__get_def(map, &def); - if (err) { + def = bpf_map__def(map); + if (IS_ERR(def)) { pr_debug("Unable to get map definition from '%s'\n", map_name); - return err; + return PTR_ERR(def); } /* * No need to check key_size and value_size: * kernel has already checked them. */ - if (def.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + if (def->type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", map_name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; @@ -1087,9 +1130,8 @@ config_map_indices_range_check(struct parse_events_term *term, const char *map_name) { struct parse_events_array *array = &term->array; - struct bpf_map_def def; + const struct bpf_map_def *def; unsigned int i; - int err; if (!array->nr_ranges) return 0; @@ -1099,8 +1141,8 @@ config_map_indices_range_check(struct parse_events_term *term, return -BPF_LOADER_ERRNO__INTERNAL; } - err = bpf_map__get_def(map, &def); - if (err) { + def = bpf_map__def(map); + if (IS_ERR(def)) { pr_debug("ERROR: Unable to get map definition from '%s'\n", map_name); return -BPF_LOADER_ERRNO__INTERNAL; @@ -1111,7 +1153,7 @@ config_map_indices_range_check(struct parse_events_term *term, size_t length = array->ranges[i].length; unsigned int idx = start + length - 1; - if (idx >= def.max_entries) { + if (idx >= def->max_entries) { pr_debug("ERROR: index %d too large\n", idx); return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG; } @@ -1147,7 +1189,7 @@ bpf__obj_config_map(struct bpf_object *obj, goto out; } - map = bpf_object__get_map_by_name(obj, map_name); + map = bpf_object__find_map_by_name(obj, map_name); if (!map) { pr_debug("ERROR: Map %s doesn't exist\n", map_name); err = -BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST; @@ -1204,14 +1246,14 @@ out: } typedef int (*map_config_func_t)(const char *name, int map_fd, - struct bpf_map_def *pdef, + const struct bpf_map_def *pdef, struct bpf_map_op *op, void *pkey, void *arg); static int foreach_key_array_all(map_config_func_t func, void *arg, const char *name, - int map_fd, struct bpf_map_def *pdef, + int map_fd, const struct bpf_map_def *pdef, struct bpf_map_op *op) { unsigned int i; @@ -1231,7 +1273,7 @@ foreach_key_array_all(map_config_func_t func, static int foreach_key_array_ranges(map_config_func_t func, void *arg, const char *name, int map_fd, - struct bpf_map_def *pdef, + const struct bpf_map_def *pdef, struct bpf_map_op *op) { unsigned int i, j; @@ -1261,15 +1303,12 @@ bpf_map_config_foreach_key(struct bpf_map *map, void *arg) { int err, map_fd; - const char *name; struct bpf_map_op *op; - struct bpf_map_def def; - struct bpf_map_priv *priv; + const struct bpf_map_def *def; + const char *name = bpf_map__name(map); + struct bpf_map_priv *priv = bpf_map__priv(map); - name = bpf_map__get_name(map); - - err = bpf_map__get_private(map, (void **)&priv); - if (err) { + if (IS_ERR(priv)) { pr_debug("ERROR: failed to get private from map %s\n", name); return -BPF_LOADER_ERRNO__INTERNAL; } @@ -1278,29 +1317,29 @@ bpf_map_config_foreach_key(struct bpf_map *map, return 0; } - err = bpf_map__get_def(map, &def); - if (err) { + def = bpf_map__def(map); + if (IS_ERR(def)) { pr_debug("ERROR: failed to get definition from map %s\n", name); return -BPF_LOADER_ERRNO__INTERNAL; } - map_fd = bpf_map__get_fd(map); + map_fd = bpf_map__fd(map); if (map_fd < 0) { pr_debug("ERROR: failed to get fd from map %s\n", name); return map_fd; } list_for_each_entry(op, &priv->ops_list, list) { - switch (def.type) { + switch (def->type) { case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PERF_EVENT_ARRAY: switch (op->key_type) { case BPF_MAP_KEY_ALL: err = foreach_key_array_all(func, arg, name, - map_fd, &def, op); + map_fd, def, op); break; case BPF_MAP_KEY_RANGES: err = foreach_key_array_ranges(func, arg, name, - map_fd, &def, + map_fd, def, op); break; default: @@ -1410,7 +1449,7 @@ apply_config_evsel_for_key(const char *name, int map_fd, void *pkey, static int apply_obj_config_map_for_key(const char *name, int map_fd, - struct bpf_map_def *pdef __maybe_unused, + const struct bpf_map_def *pdef, struct bpf_map_op *op, void *pkey, void *arg __maybe_unused) { @@ -1475,9 +1514,9 @@ int bpf__apply_obj_config(void) #define bpf__for_each_stdout_map(pos, obj, objtmp) \ bpf__for_each_map(pos, obj, objtmp) \ - if (bpf_map__get_name(pos) && \ + if (bpf_map__name(pos) && \ (strcmp("__bpf_stdout__", \ - bpf_map__get_name(pos)) == 0)) + bpf_map__name(pos)) == 0)) int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused) { @@ -1489,10 +1528,9 @@ int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused) bool need_init = false; bpf__for_each_stdout_map(map, obj, tmp) { - struct bpf_map_priv *priv; + struct bpf_map_priv *priv = bpf_map__priv(map); - err = bpf_map__get_private(map, (void **)&priv); - if (err) + if (IS_ERR(priv)) return -BPF_LOADER_ERRNO__INTERNAL; /* @@ -1520,10 +1558,9 @@ int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused) } bpf__for_each_stdout_map(map, obj, tmp) { - struct bpf_map_priv *priv; + struct bpf_map_priv *priv = bpf_map__priv(map); - err = bpf_map__get_private(map, (void **)&priv); - if (err) + if (IS_ERR(priv)) return -BPF_LOADER_ERRNO__INTERNAL; if (priv) continue; @@ -1533,7 +1570,7 @@ int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused) if (!priv) return -ENOMEM; - err = bpf_map__set_private(map, priv, bpf_map_priv__clear); + err = bpf_map__set_priv(map, priv, bpf_map_priv__clear); if (err) { bpf_map_priv__clear(map, priv); return err; @@ -1607,7 +1644,7 @@ bpf_loader_strerror(int err, char *buf, size_t size) snprintf(buf, size, "Unknown bpf loader error %d", err); else snprintf(buf, size, "%s", - strerror_r(err, sbuf, sizeof(sbuf))); + str_error_r(err, sbuf, sizeof(sbuf))); buf[size - 1] = '\0'; return -1; @@ -1677,7 +1714,7 @@ int bpf__strerror_load(struct bpf_object *obj, { bpf__strerror_head(err, buf, size); case LIBBPF_ERRNO__KVER: { - unsigned int obj_kver = bpf_object__get_kversion(obj); + unsigned int obj_kver = bpf_object__kversion(obj); unsigned int real_kver; if (fetch_kernel_version(&real_kver, NULL, 0)) { diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index 941e17275aa7..f2b737b225f2 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -46,7 +46,7 @@ struct bpf_object; struct parse_events_term; #define PERF_BPF_PROBE_GROUP "perf_bpf_probe" -typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev, +typedef int (*bpf_prog_iter_callback_t)(const char *group, const char *event, int fd, void *arg); #ifdef HAVE_LIBBPF_SUPPORT @@ -67,8 +67,8 @@ int bpf__strerror_probe(struct bpf_object *obj, int err, int bpf__load(struct bpf_object *obj); int bpf__strerror_load(struct bpf_object *obj, int err, char *buf, size_t size); -int bpf__foreach_tev(struct bpf_object *obj, - bpf_prog_iter_callback_t func, void *arg); +int bpf__foreach_event(struct bpf_object *obj, + bpf_prog_iter_callback_t func, void *arg); int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term, struct perf_evlist *evlist, int *error_pos); @@ -107,9 +107,9 @@ static inline int bpf__unprobe(struct bpf_object *obj __maybe_unused) { return 0 static inline int bpf__load(struct bpf_object *obj __maybe_unused) { return 0; } static inline int -bpf__foreach_tev(struct bpf_object *obj __maybe_unused, - bpf_prog_iter_callback_t func __maybe_unused, - void *arg __maybe_unused) +bpf__foreach_event(struct bpf_object *obj __maybe_unused, + bpf_prog_iter_callback_t func __maybe_unused, + void *arg __maybe_unused) { return 0; } diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 67e5966503b2..5651f3c12f93 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -17,6 +17,7 @@ #include "tool.h" #include "header.h" #include "vdso.h" +#include "probe-file.h" static bool no_buildid_cache; @@ -144,7 +145,28 @@ static int asnprintf(char **strp, size_t size, const char *fmt, ...) return ret; } -static char *build_id__filename(const char *sbuild_id, char *bf, size_t size) +char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf, + size_t size) +{ + bool retry_old = true; + + snprintf(bf, size, "%s/%s/%s/kallsyms", + buildid_dir, DSO__NAME_KALLSYMS, sbuild_id); +retry: + if (!access(bf, F_OK)) + return bf; + if (retry_old) { + /* Try old style kallsyms cache */ + snprintf(bf, size, "%s/%s/%s", + buildid_dir, DSO__NAME_KALLSYMS, sbuild_id); + retry_old = false; + goto retry; + } + + return NULL; +} + +char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size) { char *tmp = bf; int ret = asnprintf(&bf, size, "%s/.build-id/%.2s/%s", buildid_dir, @@ -154,23 +176,107 @@ static char *build_id__filename(const char *sbuild_id, char *bf, size_t size) return bf; } +char *build_id_cache__origname(const char *sbuild_id) +{ + char *linkname; + char buf[PATH_MAX]; + char *ret = NULL, *p; + size_t offs = 5; /* == strlen("../..") */ + + linkname = build_id_cache__linkname(sbuild_id, NULL, 0); + if (!linkname) + return NULL; + + if (readlink(linkname, buf, PATH_MAX) < 0) + goto out; + /* The link should be "../..<origpath>/<sbuild_id>" */ + p = strrchr(buf, '/'); /* Cut off the "/<sbuild_id>" */ + if (p && (p > buf + offs)) { + *p = '\0'; + if (buf[offs + 1] == '[') + offs++; /* + * This is a DSO name, like [kernel.kallsyms]. + * Skip the first '/', since this is not the + * cache of a regular file. + */ + ret = strdup(buf + offs); /* Skip "../..[/]" */ + } +out: + free(linkname); + return ret; +} + +/* Check if the given build_id cache is valid on current running system */ +static bool build_id_cache__valid_id(char *sbuild_id) +{ + char real_sbuild_id[SBUILD_ID_SIZE] = ""; + char *pathname; + int ret = 0; + bool result = false; + + pathname = build_id_cache__origname(sbuild_id); + if (!pathname) + return false; + + if (!strcmp(pathname, DSO__NAME_KALLSYMS)) + ret = sysfs__sprintf_build_id("/", real_sbuild_id); + else if (pathname[0] == '/') + ret = filename__sprintf_build_id(pathname, real_sbuild_id); + else + ret = -EINVAL; /* Should we support other special DSO cache? */ + if (ret >= 0) + result = (strcmp(sbuild_id, real_sbuild_id) == 0); + free(pathname); + + return result; +} + +static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso) +{ + return is_kallsyms ? "kallsyms" : (is_vdso ? "vdso" : "elf"); +} + char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size) { - char build_id_hex[SBUILD_ID_SIZE]; + bool is_kallsyms = dso__is_kallsyms((struct dso *)dso); + bool is_vdso = dso__is_vdso((struct dso *)dso); + char sbuild_id[SBUILD_ID_SIZE]; + char *linkname; + bool alloc = (bf == NULL); + int ret; if (!dso->has_build_id) return NULL; - build_id__sprintf(dso->build_id, sizeof(dso->build_id), build_id_hex); - return build_id__filename(build_id_hex, bf, size); + build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); + linkname = build_id_cache__linkname(sbuild_id, NULL, 0); + if (!linkname) + return NULL; + + /* Check if old style build_id cache */ + if (is_regular_file(linkname)) + ret = asnprintf(&bf, size, "%s", linkname); + else + ret = asnprintf(&bf, size, "%s/%s", linkname, + build_id_cache__basename(is_kallsyms, is_vdso)); + if (ret < 0 || (!alloc && size < (unsigned int)ret)) + bf = NULL; + free(linkname); + + return bf; } bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size) { - char *id_name, *ch; + char *id_name = NULL, *ch; struct stat sb; + char sbuild_id[SBUILD_ID_SIZE]; - id_name = dso__build_id_filename(dso, bf, size); + if (!dso->has_build_id) + goto err; + + build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); + id_name = build_id_cache__linkname(sbuild_id, NULL, 0); if (!id_name) goto err; if (access(id_name, F_OK)) @@ -194,18 +300,14 @@ bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size) if (ch - 3 < bf) goto err; + free(id_name); return strncmp(".ko", ch - 3, 3) == 0; err: - /* - * If dso__build_id_filename work, get id_name again, - * because id_name points to bf and is broken. - */ - if (id_name) - id_name = dso__build_id_filename(dso, bf, size); pr_err("Invalid build id: %s\n", id_name ? : dso->long_name ? : dso->short_name ? : "[unknown]"); + free(id_name); return false; } @@ -340,8 +442,132 @@ void disable_buildid_cache(void) no_buildid_cache = true; } -static char *build_id_cache__dirname_from_path(const char *name, - bool is_kallsyms, bool is_vdso) +static bool lsdir_bid_head_filter(const char *name __maybe_unused, + struct dirent *d __maybe_unused) +{ + return (strlen(d->d_name) == 2) && + isxdigit(d->d_name[0]) && isxdigit(d->d_name[1]); +} + +static bool lsdir_bid_tail_filter(const char *name __maybe_unused, + struct dirent *d __maybe_unused) +{ + int i = 0; + while (isxdigit(d->d_name[i]) && i < SBUILD_ID_SIZE - 3) + i++; + return (i == SBUILD_ID_SIZE - 3) && (d->d_name[i] == '\0'); +} + +struct strlist *build_id_cache__list_all(bool validonly) +{ + struct strlist *toplist, *linklist = NULL, *bidlist; + struct str_node *nd, *nd2; + char *topdir, *linkdir = NULL; + char sbuild_id[SBUILD_ID_SIZE]; + + /* for filename__ functions */ + if (validonly) + symbol__init(NULL); + + /* Open the top-level directory */ + if (asprintf(&topdir, "%s/.build-id/", buildid_dir) < 0) + return NULL; + + bidlist = strlist__new(NULL, NULL); + if (!bidlist) + goto out; + + toplist = lsdir(topdir, lsdir_bid_head_filter); + if (!toplist) { + pr_debug("Error in lsdir(%s): %d\n", topdir, errno); + /* If there is no buildid cache, return an empty list */ + if (errno == ENOENT) + goto out; + goto err_out; + } + + strlist__for_each_entry(nd, toplist) { + if (asprintf(&linkdir, "%s/%s", topdir, nd->s) < 0) + goto err_out; + /* Open the lower-level directory */ + linklist = lsdir(linkdir, lsdir_bid_tail_filter); + if (!linklist) { + pr_debug("Error in lsdir(%s): %d\n", linkdir, errno); + goto err_out; + } + strlist__for_each_entry(nd2, linklist) { + if (snprintf(sbuild_id, SBUILD_ID_SIZE, "%s%s", + nd->s, nd2->s) != SBUILD_ID_SIZE - 1) + goto err_out; + if (validonly && !build_id_cache__valid_id(sbuild_id)) + continue; + if (strlist__add(bidlist, sbuild_id) < 0) + goto err_out; + } + strlist__delete(linklist); + zfree(&linkdir); + } + +out_free: + strlist__delete(toplist); +out: + free(topdir); + + return bidlist; + +err_out: + strlist__delete(linklist); + zfree(&linkdir); + strlist__delete(bidlist); + bidlist = NULL; + goto out_free; +} + +static bool str_is_build_id(const char *maybe_sbuild_id, size_t len) +{ + size_t i; + + for (i = 0; i < len; i++) { + if (!isxdigit(maybe_sbuild_id[i])) + return false; + } + return true; +} + +/* Return the valid complete build-id */ +char *build_id_cache__complement(const char *incomplete_sbuild_id) +{ + struct strlist *bidlist; + struct str_node *nd, *cand = NULL; + char *sbuild_id = NULL; + size_t len = strlen(incomplete_sbuild_id); + + if (len >= SBUILD_ID_SIZE || + !str_is_build_id(incomplete_sbuild_id, len)) + return NULL; + + bidlist = build_id_cache__list_all(true); + if (!bidlist) + return NULL; + + strlist__for_each_entry(nd, bidlist) { + if (strncmp(nd->s, incomplete_sbuild_id, len) != 0) + continue; + if (cand) { /* Error: There are more than 2 candidates. */ + cand = NULL; + break; + } + cand = nd; + } + if (cand) + sbuild_id = strdup(cand->s); + strlist__delete(bidlist); + + return sbuild_id; +} + +char *build_id_cache__cachedir(const char *sbuild_id, const char *name, + bool is_kallsyms, bool is_vdso) { char *realname = (char *)name, *filename; bool slash = is_kallsyms || is_vdso; @@ -352,8 +578,9 @@ static char *build_id_cache__dirname_from_path(const char *name, return NULL; } - if (asprintf(&filename, "%s%s%s", buildid_dir, slash ? "/" : "", - is_vdso ? DSO__NAME_VDSO : realname) < 0) + if (asprintf(&filename, "%s%s%s%s%s", buildid_dir, slash ? "/" : "", + is_vdso ? DSO__NAME_VDSO : realname, + sbuild_id ? "/" : "", sbuild_id ?: "") < 0) filename = NULL; if (!slash) @@ -368,7 +595,7 @@ int build_id_cache__list_build_ids(const char *pathname, char *dir_name; int ret = 0; - dir_name = build_id_cache__dirname_from_path(pathname, false, false); + dir_name = build_id_cache__cachedir(NULL, pathname, false, false); if (!dir_name) return -ENOMEM; @@ -380,12 +607,36 @@ int build_id_cache__list_build_ids(const char *pathname, return ret; } +#if defined(HAVE_LIBELF_SUPPORT) && defined(HAVE_GELF_GETNOTE_SUPPORT) +static int build_id_cache__add_sdt_cache(const char *sbuild_id, + const char *realname) +{ + struct probe_cache *cache; + int ret; + + cache = probe_cache__new(sbuild_id); + if (!cache) + return -1; + + ret = probe_cache__scan_sdt(cache, realname); + if (ret >= 0) { + pr_debug("Found %d SDTs in %s\n", ret, realname); + if (probe_cache__commit(cache) < 0) + ret = -1; + } + probe_cache__delete(cache); + return ret; +} +#else +#define build_id_cache__add_sdt_cache(sbuild_id, realname) (0) +#endif + int build_id_cache__add_s(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso) { const size_t size = PATH_MAX; char *realname = NULL, *filename = NULL, *dir_name = NULL, - *linkname = zalloc(size), *targetname, *tmp; + *linkname = zalloc(size), *tmp; int err = -1; if (!is_kallsyms) { @@ -394,14 +645,22 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, goto out_free; } - dir_name = build_id_cache__dirname_from_path(name, is_kallsyms, is_vdso); + dir_name = build_id_cache__cachedir(sbuild_id, name, + is_kallsyms, is_vdso); if (!dir_name) goto out_free; + /* Remove old style build-id cache */ + if (is_regular_file(dir_name)) + if (unlink(dir_name)) + goto out_free; + if (mkdir_p(dir_name, 0755)) goto out_free; - if (asprintf(&filename, "%s/%s", dir_name, sbuild_id) < 0) { + /* Save the allocated buildid dirname */ + if (asprintf(&filename, "%s/%s", dir_name, + build_id_cache__basename(is_kallsyms, is_vdso)) < 0) { filename = NULL; goto out_free; } @@ -415,7 +674,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, goto out_free; } - if (!build_id__filename(sbuild_id, linkname, size)) + if (!build_id_cache__linkname(sbuild_id, linkname, size)) goto out_free; tmp = strrchr(linkname, '/'); *tmp = '\0'; @@ -424,11 +683,16 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, goto out_free; *tmp = '/'; - targetname = filename + strlen(buildid_dir) - 5; - memcpy(targetname, "../..", 5); + tmp = dir_name + strlen(buildid_dir) - 5; + memcpy(tmp, "../..", 5); - if (symlink(targetname, linkname) == 0) + if (symlink(tmp, linkname) == 0) err = 0; + + /* Update SDT cache : error is just warned */ + if (build_id_cache__add_sdt_cache(sbuild_id, realname) < 0) + pr_debug("Failed to update/scan SDT cache for %s\n", realname); + out_free: if (!is_kallsyms) free(realname); @@ -452,7 +716,7 @@ static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size, bool build_id_cache__cached(const char *sbuild_id) { bool ret = false; - char *filename = build_id__filename(sbuild_id, NULL, 0); + char *filename = build_id_cache__linkname(sbuild_id, NULL, 0); if (filename && !access(filename, F_OK)) ret = true; @@ -471,7 +735,7 @@ int build_id_cache__remove_s(const char *sbuild_id) if (filename == NULL || linkname == NULL) goto out_free; - if (!build_id__filename(sbuild_id, linkname, size)) + if (!build_id_cache__linkname(sbuild_id, linkname, size)) goto out_free; if (access(linkname, F_OK)) @@ -489,7 +753,7 @@ int build_id_cache__remove_s(const char *sbuild_id) tmp = strrchr(linkname, '/') + 1; snprintf(tmp, size - (tmp - linkname), "%s", filename); - if (unlink(linkname)) + if (rm_rf(linkname)) goto out_free; err = 0; @@ -501,7 +765,7 @@ out_free: static int dso__cache_build_id(struct dso *dso, struct machine *machine) { - bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; + bool is_kallsyms = dso__is_kallsyms(dso); bool is_vdso = dso__is_vdso(dso); const char *name = dso->long_name; char nm[PATH_MAX]; diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index 64af3e20610d..d27990610f9f 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -14,6 +14,8 @@ struct dso; int build_id__sprintf(const u8 *build_id, int len, char *bf); int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id); int filename__sprintf_build_id(const char *pathname, char *sbuild_id); +char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf, + size_t size); char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size); bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size); @@ -28,6 +30,12 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits); int perf_session__write_buildid_table(struct perf_session *session, int fd); int perf_session__cache_build_ids(struct perf_session *session); +char *build_id_cache__origname(const char *sbuild_id); +char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size); +char *build_id_cache__cachedir(const char *sbuild_id, const char *name, + bool is_kallsyms, bool is_vdso); +struct strlist *build_id_cache__list_all(bool validonly); +char *build_id_cache__complement(const char *incomplete_sbuild_id); int build_id_cache__list_build_ids(const char *pathname, struct strlist **result); bool build_id_cache__cached(const char *sbuild_id); diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 0d814bb74661..512c0c83fbc6 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -1,40 +1,20 @@ #ifndef __PERF_CACHE_H #define __PERF_CACHE_H -#include <stdbool.h> -#include "util.h" #include "strbuf.h" #include <subcmd/pager.h> -#include "../perf.h" #include "../ui/ui.h" #include <linux/string.h> #define CMD_EXEC_PATH "--exec-path" -#define CMD_PERF_DIR "--perf-dir=" -#define CMD_WORK_TREE "--work-tree=" #define CMD_DEBUGFS_DIR "--debugfs-dir=" -#define PERF_DIR_ENVIRONMENT "PERF_DIR" -#define PERF_WORK_TREE_ENVIRONMENT "PERF_WORK_TREE" #define EXEC_PATH_ENVIRONMENT "PERF_EXEC_PATH" -#define DEFAULT_PERF_DIR_ENVIRONMENT ".perf" #define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR" #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR" #define PERF_PAGER_ENVIRONMENT "PERF_PAGER" -extern const char *config_exclusive_filename; - -typedef int (*config_fn_t)(const char *, const char *, void *); -int perf_default_config(const char *, const char *, void *); -int perf_config(config_fn_t fn, void *); -int perf_config_int(const char *, const char *); -u64 perf_config_u64(const char *, const char *); -int perf_config_bool(const char *, const char *); -int config_error_nonbool(const char *); -const char *perf_config_dirname(const char *, const char *); -const char *perf_etc_perfconfig(void); - char *alias_lookup(const char *alias); int split_cmdline(char *cmdline, const char ***argv); @@ -45,9 +25,6 @@ static inline int is_absolute_path(const char *path) return path[0] == '/'; } -char *strip_path_suffix(const char *path, const char *suffix); - char *mkpath(const char *fmt, ...) __attribute__((format (printf, 1, 2))); -char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2))); #endif /* __PERF_CACHE_H */ diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 65e2a4f7cb4e..13e75549c440 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -94,6 +94,7 @@ struct callchain_param { enum perf_call_graph_mode record_mode; u32 dump_size; enum chain_mode mode; + u16 max_stack; u32 print_limit; double min_percent; sort_chain_func_t sort; @@ -105,6 +106,7 @@ struct callchain_param { }; extern struct callchain_param callchain_param; +extern struct callchain_param callchain_param_default; struct callchain_list { u64 ip; diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 90aa1b46b2e5..8fdee24725a7 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -81,7 +81,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str) /* * check if cgrp is already defined, if so we reuse it */ - evlist__for_each(evlist, counter) { + evlist__for_each_entry(evlist, counter) { cgrp = counter->cgrp; if (!cgrp) continue; @@ -110,7 +110,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str) * if add cgroup N, then need to find event N */ n = 0; - evlist__for_each(evlist, counter) { + evlist__for_each_entry(evlist, counter) { if (n == nr_cgroups) goto found; n++; diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index 2babddaa2481..f0dcd0ee0afa 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -4,18 +4,24 @@ #include "cloexec.h" #include "asm/bug.h" #include "debug.h" +#include <unistd.h> +#include <asm/unistd.h> +#include <sys/syscall.h> static unsigned long flag = PERF_FLAG_FD_CLOEXEC; -#ifdef __GLIBC_PREREQ -#if !__GLIBC_PREREQ(2, 6) int __weak sched_getcpu(void) { +#ifdef __NR_getcpu + unsigned cpu; + int err = syscall(__NR_getcpu, &cpu, NULL, NULL); + if (!err) + return cpu; +#else errno = ENOSYS; +#endif return -1; } -#endif -#endif static int perf_flag_probe(void) { @@ -58,7 +64,7 @@ static int perf_flag_probe(void) WARN_ONCE(err != EINVAL && err != EBUSY, "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n", - err, strerror_r(err, sbuf, sizeof(sbuf))); + err, str_error_r(err, sbuf, sizeof(sbuf))); /* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */ while (1) { @@ -76,7 +82,7 @@ static int perf_flag_probe(void) if (WARN_ONCE(fd < 0 && err != EBUSY, "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n", - err, strerror_r(err, sbuf, sizeof(sbuf)))) + err, str_error_r(err, sbuf, sizeof(sbuf)))) return -1; return 0; diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index 43e84aa27e4a..dbbf89b050a5 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -1,7 +1,11 @@ #include <linux/kernel.h> #include "cache.h" +#include "config.h" +#include <stdlib.h> +#include <stdio.h> #include "color.h" #include <math.h> +#include <unistd.h> int perf_use_color_default = -1; diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index dad7d8272168..18dae745034f 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -26,6 +26,7 @@ static FILE *config_file; static const char *config_file_name; static int config_linenr; static int config_file_eof; +static struct perf_config_set *config_set; const char *config_exclusive_filename; @@ -275,7 +276,8 @@ static int perf_parse_file(config_fn_t fn, void *data) break; } } - die("bad config file line %d in %s", config_linenr, config_file_name); + pr_err("bad config file line %d in %s\n", config_linenr, config_file_name); + return -1; } static int parse_unit_factor(const char *end, unsigned long *val) @@ -371,7 +373,7 @@ int perf_config_bool(const char *name, const char *value) return !!perf_config_bool_or_int(name, value, &discard); } -const char *perf_config_dirname(const char *name, const char *value) +static const char *perf_config_dirname(const char *name, const char *value) { if (!name) return NULL; @@ -477,54 +479,6 @@ static int perf_config_global(void) return !perf_env_bool("PERF_CONFIG_NOGLOBAL", 0); } -int perf_config(config_fn_t fn, void *data) -{ - int ret = 0, found = 0; - const char *home = NULL; - - /* Setting $PERF_CONFIG makes perf read _only_ the given config file. */ - if (config_exclusive_filename) - return perf_config_from_file(fn, config_exclusive_filename, data); - if (perf_config_system() && !access(perf_etc_perfconfig(), R_OK)) { - ret += perf_config_from_file(fn, perf_etc_perfconfig(), - data); - found += 1; - } - - home = getenv("HOME"); - if (perf_config_global() && home) { - char *user_config = strdup(mkpath("%s/.perfconfig", home)); - struct stat st; - - if (user_config == NULL) { - warning("Not enough memory to process %s/.perfconfig, " - "ignoring it.", home); - goto out; - } - - if (stat(user_config, &st) < 0) - goto out_free; - - if (st.st_uid && (st.st_uid != geteuid())) { - warning("File %s not owned by current user or root, " - "ignoring it.", user_config); - goto out_free; - } - - if (!st.st_size) - goto out_free; - - ret += perf_config_from_file(fn, user_config, data); - found += 1; -out_free: - free(user_config); - } -out: - if (found == 0) - return -1; - return ret; -} - static struct perf_config_section *find_section(struct list_head *sections, const char *section_name) { @@ -609,8 +563,12 @@ static int collect_config(const char *var, const char *value, struct perf_config_section *section = NULL; struct perf_config_item *item = NULL; struct perf_config_set *set = perf_config_set; - struct list_head *sections = &set->sections; + struct list_head *sections; + + if (set == NULL) + return -1; + sections = &set->sections; key = ptr = strdup(var); if (!key) { pr_debug("%s: strdup failed\n", __func__); @@ -641,22 +599,115 @@ static int collect_config(const char *var, const char *value, out_free: free(key); - perf_config_set__delete(set); return -1; } +static int perf_config_set__init(struct perf_config_set *set) +{ + int ret = -1; + const char *home = NULL; + + /* Setting $PERF_CONFIG makes perf read _only_ the given config file. */ + if (config_exclusive_filename) + return perf_config_from_file(collect_config, config_exclusive_filename, set); + if (perf_config_system() && !access(perf_etc_perfconfig(), R_OK)) { + if (perf_config_from_file(collect_config, perf_etc_perfconfig(), set) < 0) + goto out; + } + + home = getenv("HOME"); + if (perf_config_global() && home) { + char *user_config = strdup(mkpath("%s/.perfconfig", home)); + struct stat st; + + if (user_config == NULL) { + warning("Not enough memory to process %s/.perfconfig, " + "ignoring it.", home); + goto out; + } + + if (stat(user_config, &st) < 0) + goto out_free; + + if (st.st_uid && (st.st_uid != geteuid())) { + warning("File %s not owned by current user or root, " + "ignoring it.", user_config); + goto out_free; + } + + if (!st.st_size) + goto out_free; + + ret = perf_config_from_file(collect_config, user_config, set); + +out_free: + free(user_config); + } +out: + return ret; +} + struct perf_config_set *perf_config_set__new(void) { struct perf_config_set *set = zalloc(sizeof(*set)); if (set) { INIT_LIST_HEAD(&set->sections); - perf_config(collect_config, set); + if (perf_config_set__init(set) < 0) { + perf_config_set__delete(set); + set = NULL; + } } return set; } +int perf_config(config_fn_t fn, void *data) +{ + int ret = 0; + char key[BUFSIZ]; + struct perf_config_section *section; + struct perf_config_item *item; + + if (config_set == NULL) + return -1; + + perf_config_set__for_each_entry(config_set, section, item) { + char *value = item->value; + + if (value) { + scnprintf(key, sizeof(key), "%s.%s", + section->name, item->name); + ret = fn(key, value, data); + if (ret < 0) { + pr_err("Error: wrong config key-value pair %s=%s\n", + key, value); + break; + } + } + } + + return ret; +} + +void perf_config__init(void) +{ + if (config_set == NULL) + config_set = perf_config_set__new(); +} + +void perf_config__exit(void) +{ + perf_config_set__delete(config_set); + config_set = NULL; +} + +void perf_config__refresh(void) +{ + perf_config__exit(); + perf_config__init(); +} + static void perf_config_item__delete(struct perf_config_item *item) { zfree(&item->name); @@ -693,6 +744,9 @@ static void perf_config_set__purge(struct perf_config_set *set) void perf_config_set__delete(struct perf_config_set *set) { + if (set == NULL) + return; + perf_config_set__purge(set); free(set); } diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h index 22ec626ac718..6f813d46045e 100644 --- a/tools/perf/util/config.h +++ b/tools/perf/util/config.h @@ -20,7 +20,47 @@ struct perf_config_set { struct list_head sections; }; +extern const char *config_exclusive_filename; + +typedef int (*config_fn_t)(const char *, const char *, void *); +int perf_default_config(const char *, const char *, void *); +int perf_config(config_fn_t fn, void *); +int perf_config_int(const char *, const char *); +u64 perf_config_u64(const char *, const char *); +int perf_config_bool(const char *, const char *); +int config_error_nonbool(const char *); +const char *perf_etc_perfconfig(void); + struct perf_config_set *perf_config_set__new(void); void perf_config_set__delete(struct perf_config_set *set); +void perf_config__init(void); +void perf_config__exit(void); +void perf_config__refresh(void); + +/** + * perf_config_sections__for_each - iterate thru all the sections + * @list: list_head instance to iterate + * @section: struct perf_config_section iterator + */ +#define perf_config_sections__for_each_entry(list, section) \ + list_for_each_entry(section, list, node) + +/** + * perf_config_items__for_each - iterate thru all the items + * @list: list_head instance to iterate + * @item: struct perf_config_item iterator + */ +#define perf_config_items__for_each_entry(list, item) \ + list_for_each_entry(item, list, node) + +/** + * perf_config_set__for_each - iterate thru all the config section-item pairs + * @set: evlist instance to iterate + * @section: struct perf_config_section iterator + * @item: struct perf_config_item iterator + */ +#define perf_config_set__for_each_entry(set, section, item) \ + perf_config_sections__for_each_entry(&set->sections, section) \ + perf_config_items__for_each_entry(§ion->items, item) #endif /* __PERF_CONFIG_H */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 02d801670f30..2c0b52264a46 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -236,13 +236,12 @@ struct cpu_map *cpu_map__new_data(struct cpu_map_data *data) size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp) { - int i; - size_t printed = fprintf(fp, "%d cpu%s: ", - map->nr, map->nr > 1 ? "s" : ""); - for (i = 0; i < map->nr; ++i) - printed += fprintf(fp, "%s%d", i ? ", " : "", map->map[i]); +#define BUFSIZE 1024 + char buf[BUFSIZE]; - return printed + fprintf(fp, "\n"); + cpu_map__snprint(map, buf, sizeof(buf)); + return fprintf(fp, "%s\n", buf); +#undef BUFSIZE } struct cpu_map *cpu_map__dummy_new(void) @@ -590,12 +589,65 @@ int cpu__setup_cpunode_map(void) bool cpu_map__has(struct cpu_map *cpus, int cpu) { + return cpu_map__idx(cpus, cpu) != -1; +} + +int cpu_map__idx(struct cpu_map *cpus, int cpu) +{ int i; for (i = 0; i < cpus->nr; ++i) { if (cpus->map[i] == cpu) - return true; + return i; + } + + return -1; +} + +int cpu_map__cpu(struct cpu_map *cpus, int idx) +{ + return cpus->map[idx]; +} + +size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size) +{ + int i, cpu, start = -1; + bool first = true; + size_t ret = 0; + +#define COMMA first ? "" : "," + + for (i = 0; i < map->nr + 1; i++) { + bool last = i == map->nr; + + cpu = last ? INT_MAX : map->map[i]; + + if (start == -1) { + start = i; + if (last) { + ret += snprintf(buf + ret, size - ret, + "%s%d", COMMA, + map->map[i]); + } + } else if (((i - start) != (cpu - map->map[start])) || last) { + int end = i - 1; + + if (start == end) { + ret += snprintf(buf + ret, size - ret, + "%s%d", COMMA, + map->map[start]); + } else { + ret += snprintf(buf + ret, size - ret, + "%s%d-%d", COMMA, + map->map[start], map->map[end]); + } + first = false; + start = i; + } } - return false; +#undef COMMA + + pr_debug("cpumask list: %s\n", buf); + return ret; } diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 1a0a35073ce1..06bd689f5989 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -19,6 +19,7 @@ struct cpu_map *cpu_map__empty_new(int nr); struct cpu_map *cpu_map__dummy_new(void); struct cpu_map *cpu_map__new_data(struct cpu_map_data *data); struct cpu_map *cpu_map__read(FILE *file); +size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size); size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp); int cpu_map__get_socket_id(int cpu); int cpu_map__get_socket(struct cpu_map *map, int idx, void *data); @@ -67,5 +68,7 @@ int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, int (*f)(struct cpu_map *map, int cpu, void *data), void *data); +int cpu_map__cpu(struct cpu_map *cpus, int idx); bool cpu_map__has(struct cpu_map *cpus, int cpu); +int cpu_map__idx(struct cpu_map *cpus, int cpu); #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index bbf69d248ec5..4f979bb27b6c 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -26,6 +26,7 @@ #include "evlist.h" #include "evsel.h" #include "machine.h" +#include "config.h" #define pr_N(n, fmt, ...) \ eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__) @@ -68,6 +69,9 @@ struct ctf_writer { }; struct bt_ctf_field_type *array[6]; } data; + struct bt_ctf_event_class *comm_class; + struct bt_ctf_event_class *exit_class; + struct bt_ctf_event_class *fork_class; }; struct convert { @@ -76,6 +80,7 @@ struct convert { u64 events_size; u64 events_count; + u64 non_sample_count; /* Ordered events configured queue size. */ u64 queue_size; @@ -140,6 +145,36 @@ FUNC_VALUE_SET(s64) FUNC_VALUE_SET(u64) __FUNC_VALUE_SET(u64_hex, u64) +static int string_set_value(struct bt_ctf_field *field, const char *string); +static __maybe_unused int +value_set_string(struct ctf_writer *cw, struct bt_ctf_event *event, + const char *name, const char *string) +{ + struct bt_ctf_field_type *type = cw->data.string; + struct bt_ctf_field *field; + int ret = 0; + + field = bt_ctf_field_create(type); + if (!field) { + pr_err("failed to create a field %s\n", name); + return -1; + } + + ret = string_set_value(field, string); + if (ret) { + pr_err("failed to set value %s\n", name); + goto err_put_field; + } + + ret = bt_ctf_event_set_payload(event, name, field); + if (ret) + pr_err("failed to set payload %s\n", name); + +err_put_field: + bt_ctf_field_put(field); + return ret; +} + static struct bt_ctf_field_type* get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field) { @@ -204,6 +239,44 @@ static unsigned long long adjust_signedness(unsigned long long value_int, int si return (value_int & value_mask) | ~value_mask; } +static int string_set_value(struct bt_ctf_field *field, const char *string) +{ + char *buffer = NULL; + size_t len = strlen(string), i, p; + int err; + + for (i = p = 0; i < len; i++, p++) { + if (isprint(string[i])) { + if (!buffer) + continue; + buffer[p] = string[i]; + } else { + char numstr[5]; + + snprintf(numstr, sizeof(numstr), "\\x%02x", + (unsigned int)(string[i]) & 0xff); + + if (!buffer) { + buffer = zalloc(i + (len - i) * 4 + 2); + if (!buffer) { + pr_err("failed to set unprintable string '%s'\n", string); + return bt_ctf_field_string_set_value(field, "UNPRINTABLE-STRING"); + } + if (i > 0) + strncpy(buffer, string, i); + } + strncat(buffer + p, numstr, 4); + p += 3; + } + } + + if (!buffer) + return bt_ctf_field_string_set_value(field, string); + err = bt_ctf_field_string_set_value(field, buffer); + free(buffer); + return err; +} + static int add_tracepoint_field_value(struct ctf_writer *cw, struct bt_ctf_event_class *event_class, struct bt_ctf_event *event, @@ -270,8 +343,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw, } if (flags & FIELD_IS_STRING) - ret = bt_ctf_field_string_set_value(field, - data + offset + i * len); + ret = string_set_value(field, data + offset + i * len); else { unsigned long long value_int; @@ -694,6 +766,72 @@ static int process_sample_event(struct perf_tool *tool, return cs ? 0 : -1; } +#define __NON_SAMPLE_SET_FIELD(_name, _type, _field) \ +do { \ + ret = value_set_##_type(cw, event, #_field, _event->_name._field);\ + if (ret) \ + return -1; \ +} while(0) + +#define __FUNC_PROCESS_NON_SAMPLE(_name, body) \ +static int process_##_name##_event(struct perf_tool *tool, \ + union perf_event *_event, \ + struct perf_sample *sample, \ + struct machine *machine) \ +{ \ + struct convert *c = container_of(tool, struct convert, tool);\ + struct ctf_writer *cw = &c->writer; \ + struct bt_ctf_event_class *event_class = cw->_name##_class;\ + struct bt_ctf_event *event; \ + struct ctf_stream *cs; \ + int ret; \ + \ + c->non_sample_count++; \ + c->events_size += _event->header.size; \ + event = bt_ctf_event_create(event_class); \ + if (!event) { \ + pr_err("Failed to create an CTF event\n"); \ + return -1; \ + } \ + \ + bt_ctf_clock_set_time(cw->clock, sample->time); \ + body \ + cs = ctf_stream(cw, 0); \ + if (cs) { \ + if (is_flush_needed(cs)) \ + ctf_stream__flush(cs); \ + \ + cs->count++; \ + bt_ctf_stream_append_event(cs->stream, event); \ + } \ + bt_ctf_event_put(event); \ + \ + return perf_event__process_##_name(tool, _event, sample, machine);\ +} + +__FUNC_PROCESS_NON_SAMPLE(comm, + __NON_SAMPLE_SET_FIELD(comm, u32, pid); + __NON_SAMPLE_SET_FIELD(comm, u32, tid); + __NON_SAMPLE_SET_FIELD(comm, string, comm); +) +__FUNC_PROCESS_NON_SAMPLE(fork, + __NON_SAMPLE_SET_FIELD(fork, u32, pid); + __NON_SAMPLE_SET_FIELD(fork, u32, ppid); + __NON_SAMPLE_SET_FIELD(fork, u32, tid); + __NON_SAMPLE_SET_FIELD(fork, u32, ptid); + __NON_SAMPLE_SET_FIELD(fork, u64, time); +) + +__FUNC_PROCESS_NON_SAMPLE(exit, + __NON_SAMPLE_SET_FIELD(fork, u32, pid); + __NON_SAMPLE_SET_FIELD(fork, u32, ppid); + __NON_SAMPLE_SET_FIELD(fork, u32, tid); + __NON_SAMPLE_SET_FIELD(fork, u32, ptid); + __NON_SAMPLE_SET_FIELD(fork, u64, time); +) +#undef __NON_SAMPLE_SET_FIELD +#undef __FUNC_PROCESS_NON_SAMPLE + /* If dup < 0, add a prefix. Else, add _dupl_X suffix. */ static char *change_name(char *name, char *orig_name, int dup) { @@ -960,7 +1098,7 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session) struct perf_evsel *evsel; int ret; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { ret = add_event(cw, evsel); if (ret) return ret; @@ -968,12 +1106,86 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session) return 0; } +#define __NON_SAMPLE_ADD_FIELD(t, n) \ + do { \ + pr2(" field '%s'\n", #n); \ + if (bt_ctf_event_class_add_field(event_class, cw->data.t, #n)) {\ + pr_err("Failed to add field '%s';\n", #n);\ + return -1; \ + } \ + } while(0) + +#define __FUNC_ADD_NON_SAMPLE_EVENT_CLASS(_name, body) \ +static int add_##_name##_event(struct ctf_writer *cw) \ +{ \ + struct bt_ctf_event_class *event_class; \ + int ret; \ + \ + pr("Adding "#_name" event\n"); \ + event_class = bt_ctf_event_class_create("perf_" #_name);\ + if (!event_class) \ + return -1; \ + body \ + \ + ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class);\ + if (ret) { \ + pr("Failed to add event class '"#_name"' into stream.\n");\ + return ret; \ + } \ + \ + cw->_name##_class = event_class; \ + bt_ctf_event_class_put(event_class); \ + return 0; \ +} + +__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(comm, + __NON_SAMPLE_ADD_FIELD(u32, pid); + __NON_SAMPLE_ADD_FIELD(u32, tid); + __NON_SAMPLE_ADD_FIELD(string, comm); +) + +__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(fork, + __NON_SAMPLE_ADD_FIELD(u32, pid); + __NON_SAMPLE_ADD_FIELD(u32, ppid); + __NON_SAMPLE_ADD_FIELD(u32, tid); + __NON_SAMPLE_ADD_FIELD(u32, ptid); + __NON_SAMPLE_ADD_FIELD(u64, time); +) + +__FUNC_ADD_NON_SAMPLE_EVENT_CLASS(exit, + __NON_SAMPLE_ADD_FIELD(u32, pid); + __NON_SAMPLE_ADD_FIELD(u32, ppid); + __NON_SAMPLE_ADD_FIELD(u32, tid); + __NON_SAMPLE_ADD_FIELD(u32, ptid); + __NON_SAMPLE_ADD_FIELD(u64, time); +) + +#undef __NON_SAMPLE_ADD_FIELD +#undef __FUNC_ADD_NON_SAMPLE_EVENT_CLASS + +static int setup_non_sample_events(struct ctf_writer *cw, + struct perf_session *session __maybe_unused) +{ + int ret; + + ret = add_comm_event(cw); + if (ret) + return ret; + ret = add_exit_event(cw); + if (ret) + return ret; + ret = add_fork_event(cw); + if (ret) + return ret; + return 0; +} + static void cleanup_events(struct perf_session *session) { struct perf_evlist *evlist = session->evlist; struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { struct evsel_priv *priv; priv = evsel->priv; @@ -1236,13 +1448,14 @@ static int convert__config(const char *var, const char *value, void *cb) return 0; } -int bt_convert__perf2ctf(const char *input, const char *path, bool force) +int bt_convert__perf2ctf(const char *input, const char *path, + struct perf_data_convert_opts *opts) { struct perf_session *session; struct perf_data_file file = { .path = input, .mode = PERF_DATA_MODE_READ, - .force = force, + .force = opts->force, }; struct convert c = { .tool = { @@ -1262,6 +1475,12 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force) struct ctf_writer *cw = &c.writer; int err = -1; + if (opts->all) { + c.tool.comm = process_comm_event; + c.tool.exit = process_exit_event; + c.tool.fork = process_fork_event; + } + perf_config(convert__config, &c); /* CTF writer */ @@ -1286,6 +1505,9 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force) if (setup_events(cw, session)) goto free_session; + if (opts->all && setup_non_sample_events(cw, session)) + goto free_session; + if (setup_streams(cw, session)) goto free_session; @@ -1300,10 +1522,15 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force) file.path, path); fprintf(stderr, - "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples) ]\n", + "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples", (double) c.events_size / 1024.0 / 1024.0, c.events_count); + if (!c.non_sample_count) + fprintf(stderr, ") ]\n"); + else + fprintf(stderr, ", %" PRIu64 " non-samples) ]\n", c.non_sample_count); + cleanup_events(session); perf_session__delete(session); ctf_writer__cleanup(cw); diff --git a/tools/perf/util/data-convert-bt.h b/tools/perf/util/data-convert-bt.h index 4c204342a9d8..9a3b587f76c1 100644 --- a/tools/perf/util/data-convert-bt.h +++ b/tools/perf/util/data-convert-bt.h @@ -1,8 +1,10 @@ #ifndef __DATA_CONVERT_BT_H #define __DATA_CONVERT_BT_H +#include "data-convert.h" #ifdef HAVE_LIBBABELTRACE_SUPPORT -int bt_convert__perf2ctf(const char *input_name, const char *to_ctf, bool force); +int bt_convert__perf2ctf(const char *input_name, const char *to_ctf, + struct perf_data_convert_opts *opts); #endif /* HAVE_LIBBABELTRACE_SUPPORT */ #endif /* __DATA_CONVERT_BT_H */ diff --git a/tools/perf/util/data-convert.h b/tools/perf/util/data-convert.h new file mode 100644 index 000000000000..5314962fe95b --- /dev/null +++ b/tools/perf/util/data-convert.h @@ -0,0 +1,9 @@ +#ifndef __DATA_CONVERT_H +#define __DATA_CONVERT_H + +struct perf_data_convert_opts { + bool force; + bool all; +}; + +#endif /* __DATA_CONVERT_H */ diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index be83516155ee..60bfc9ca1e22 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -57,7 +57,7 @@ static int open_file_read(struct perf_data_file *file) int err = errno; pr_err("failed to open %s: %s", file->path, - strerror_r(err, sbuf, sizeof(sbuf))); + str_error_r(err, sbuf, sizeof(sbuf))); if (err == ENOENT && !strcmp(file->path, "perf.data")) pr_err(" (try 'perf record' first)"); pr_err("\n"); @@ -99,7 +99,7 @@ static int open_file_write(struct perf_data_file *file) if (fd < 0) pr_err("failed to open %s : %s\n", file->path, - strerror_r(errno, sbuf, sizeof(sbuf))); + str_error_r(errno, sbuf, sizeof(sbuf))); return fd; } diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index c9a6dc173e74..b0c2b5c5d337 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -233,17 +233,6 @@ int db_export__symbol(struct db_export *dbe, struct symbol *sym, return 0; } -static struct thread *get_main_thread(struct machine *machine, struct thread *thread) -{ - if (thread->pid_ == thread->tid) - return thread__get(thread); - - if (thread->pid_ == -1) - return NULL; - - return machine__find_thread(machine, thread->pid_, thread->pid_); -} - static int db_ids_from_al(struct db_export *dbe, struct addr_location *al, u64 *dso_db_id, u64 *sym_db_id, u64 *offset) { @@ -382,7 +371,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, if (err) return err; - main_thread = get_main_thread(al->machine, thread); + main_thread = thread__main_thread(al->machine, thread); if (main_thread) comm = machine__thread_exec_comm(al->machine, main_thread); diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index 14bafda79eda..d242adc3d5a2 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -38,7 +38,7 @@ extern int debug_data_convert; #define pr_oe_time(t, fmt, ...) pr_time_N(1, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__) #define pr_oe_time2(t, fmt, ...) pr_time_N(2, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__) -#define STRERR_BUFSIZE 128 /* For the buffer size of strerror_r */ +#define STRERR_BUFSIZE 128 /* For the buffer size of str_error_r */ int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); void trace_event(union perf_event *event); diff --git a/tools/perf/util/demangle-rust.c b/tools/perf/util/demangle-rust.c new file mode 100644 index 000000000000..f9dafa888c06 --- /dev/null +++ b/tools/perf/util/demangle-rust.c @@ -0,0 +1,269 @@ +#include <string.h> +#include "util.h" +#include "debug.h" + +#include "demangle-rust.h" + +/* + * Mangled Rust symbols look like this: + * + * _$LT$std..sys..fd..FileDesc$u20$as$u20$core..ops..Drop$GT$::drop::hc68340e1baa4987a + * + * The original symbol is: + * + * <std::sys::fd::FileDesc as core::ops::Drop>::drop + * + * The last component of the path is a 64-bit hash in lowercase hex, prefixed + * with "h". Rust does not have a global namespace between crates, an illusion + * which Rust maintains by using the hash to distinguish things that would + * otherwise have the same symbol. + * + * Any path component not starting with a XID_Start character is prefixed with + * "_". + * + * The following escape sequences are used: + * + * "," => $C$ + * "@" => $SP$ + * "*" => $BP$ + * "&" => $RF$ + * "<" => $LT$ + * ">" => $GT$ + * "(" => $LP$ + * ")" => $RP$ + * " " => $u20$ + * "'" => $u27$ + * "[" => $u5b$ + * "]" => $u5d$ + * "~" => $u7e$ + * + * A double ".." means "::" and a single "." means "-". + * + * The only characters allowed in the mangled symbol are a-zA-Z0-9 and _.:$ + */ + +static const char *hash_prefix = "::h"; +static const size_t hash_prefix_len = 3; +static const size_t hash_len = 16; + +static bool is_prefixed_hash(const char *start); +static bool looks_like_rust(const char *sym, size_t len); +static bool unescape(const char **in, char **out, const char *seq, char value); + +/* + * INPUT: + * sym: symbol that has been through BFD-demangling + * + * This function looks for the following indicators: + * + * 1. The hash must consist of "h" followed by 16 lowercase hex digits. + * + * 2. As a sanity check, the hash must use between 5 and 15 of the 16 possible + * hex digits. This is true of 99.9998% of hashes so once in your life you + * may see a false negative. The point is to notice path components that + * could be Rust hashes but are probably not, like "haaaaaaaaaaaaaaaa". In + * this case a false positive (non-Rust symbol has an important path + * component removed because it looks like a Rust hash) is worse than a + * false negative (the rare Rust symbol is not demangled) so this sets the + * balance in favor of false negatives. + * + * 3. There must be no characters other than a-zA-Z0-9 and _.:$ + * + * 4. There must be no unrecognized $-sign sequences. + * + * 5. There must be no sequence of three or more dots in a row ("..."). + */ +bool +rust_is_mangled(const char *sym) +{ + size_t len, len_without_hash; + + if (!sym) + return false; + + len = strlen(sym); + if (len <= hash_prefix_len + hash_len) + /* Not long enough to contain "::h" + hash + something else */ + return false; + + len_without_hash = len - (hash_prefix_len + hash_len); + if (!is_prefixed_hash(sym + len_without_hash)) + return false; + + return looks_like_rust(sym, len_without_hash); +} + +/* + * A hash is the prefix "::h" followed by 16 lowercase hex digits. The hex + * digits must comprise between 5 and 15 (inclusive) distinct digits. + */ +static bool is_prefixed_hash(const char *str) +{ + const char *end; + bool seen[16]; + size_t i; + int count; + + if (strncmp(str, hash_prefix, hash_prefix_len)) + return false; + str += hash_prefix_len; + + memset(seen, false, sizeof(seen)); + for (end = str + hash_len; str < end; str++) + if (*str >= '0' && *str <= '9') + seen[*str - '0'] = true; + else if (*str >= 'a' && *str <= 'f') + seen[*str - 'a' + 10] = true; + else + return false; + + /* Count how many distinct digits seen */ + count = 0; + for (i = 0; i < 16; i++) + if (seen[i]) + count++; + + return count >= 5 && count <= 15; +} + +static bool looks_like_rust(const char *str, size_t len) +{ + const char *end = str + len; + + while (str < end) + switch (*str) { + case '$': + if (!strncmp(str, "$C$", 3)) + str += 3; + else if (!strncmp(str, "$SP$", 4) + || !strncmp(str, "$BP$", 4) + || !strncmp(str, "$RF$", 4) + || !strncmp(str, "$LT$", 4) + || !strncmp(str, "$GT$", 4) + || !strncmp(str, "$LP$", 4) + || !strncmp(str, "$RP$", 4)) + str += 4; + else if (!strncmp(str, "$u20$", 5) + || !strncmp(str, "$u27$", 5) + || !strncmp(str, "$u5b$", 5) + || !strncmp(str, "$u5d$", 5) + || !strncmp(str, "$u7e$", 5)) + str += 5; + else + return false; + break; + case '.': + /* Do not allow three or more consecutive dots */ + if (!strncmp(str, "...", 3)) + return false; + /* Fall through */ + case 'a' ... 'z': + case 'A' ... 'Z': + case '0' ... '9': + case '_': + case ':': + str++; + break; + default: + return false; + } + + return true; +} + +/* + * INPUT: + * sym: symbol for which rust_is_mangled(sym) returns true + * + * The input is demangled in-place because the mangled name is always longer + * than the demangled one. + */ +void +rust_demangle_sym(char *sym) +{ + const char *in; + char *out; + const char *end; + + if (!sym) + return; + + in = sym; + out = sym; + end = sym + strlen(sym) - (hash_prefix_len + hash_len); + + while (in < end) + switch (*in) { + case '$': + if (!(unescape(&in, &out, "$C$", ',') + || unescape(&in, &out, "$SP$", '@') + || unescape(&in, &out, "$BP$", '*') + || unescape(&in, &out, "$RF$", '&') + || unescape(&in, &out, "$LT$", '<') + || unescape(&in, &out, "$GT$", '>') + || unescape(&in, &out, "$LP$", '(') + || unescape(&in, &out, "$RP$", ')') + || unescape(&in, &out, "$u20$", ' ') + || unescape(&in, &out, "$u27$", '\'') + || unescape(&in, &out, "$u5b$", '[') + || unescape(&in, &out, "$u5d$", ']') + || unescape(&in, &out, "$u7e$", '~'))) { + pr_err("demangle-rust: unexpected escape sequence"); + goto done; + } + break; + case '_': + /* + * If this is the start of a path component and the next + * character is an escape sequence, ignore the + * underscore. The mangler inserts an underscore to make + * sure the path component begins with a XID_Start + * character. + */ + if ((in == sym || in[-1] == ':') && in[1] == '$') + in++; + else + *out++ = *in++; + break; + case '.': + if (in[1] == '.') { + /* ".." becomes "::" */ + *out++ = ':'; + *out++ = ':'; + in += 2; + } else { + /* "." becomes "-" */ + *out++ = '-'; + in++; + } + break; + case 'a' ... 'z': + case 'A' ... 'Z': + case '0' ... '9': + case ':': + *out++ = *in++; + break; + default: + pr_err("demangle-rust: unexpected character '%c' in symbol\n", + *in); + goto done; + } + +done: + *out = '\0'; +} + +static bool unescape(const char **in, char **out, const char *seq, char value) +{ + size_t len = strlen(seq); + + if (strncmp(*in, seq, len)) + return false; + + **out = value; + + *in += len; + *out += 1; + + return true; +} diff --git a/tools/perf/util/demangle-rust.h b/tools/perf/util/demangle-rust.h new file mode 100644 index 000000000000..7b41ead7e0dd --- /dev/null +++ b/tools/perf/util/demangle-rust.h @@ -0,0 +1,7 @@ +#ifndef __PERF_DEMANGLE_RUST +#define __PERF_DEMANGLE_RUST 1 + +bool rust_is_mangled(const char *str); +void rust_demangle_sym(char *str); + +#endif /* __PERF_DEMANGLE_RUST */ diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 5d286f5d7906..774f6ec884d5 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -335,7 +335,7 @@ static int do_open(char *name) return fd; pr_debug("dso open failed: %s\n", - strerror_r(errno, sbuf, sizeof(sbuf))); + str_error_r(errno, sbuf, sizeof(sbuf))); if (!dso__data_open_cnt || errno != EMFILE) break; @@ -442,17 +442,27 @@ static rlim_t get_fd_limit(void) return limit; } -static bool may_cache_fd(void) +static rlim_t fd_limit; + +/* + * Used only by tests/dso-data.c to reset the environment + * for tests. I dont expect we should change this during + * standard runtime. + */ +void reset_fd_limit(void) { - static rlim_t limit; + fd_limit = 0; +} - if (!limit) - limit = get_fd_limit(); +static bool may_cache_fd(void) +{ + if (!fd_limit) + fd_limit = get_fd_limit(); - if (limit == RLIM_INFINITY) + if (fd_limit == RLIM_INFINITY) return true; - return limit > (rlim_t) dso__data_open_cnt; + return fd_limit > (rlim_t) dso__data_open_cnt; } /* @@ -776,7 +786,7 @@ static int data_file_size(struct dso *dso, struct machine *machine) if (fstat(dso->data.fd, &st) < 0) { ret = -errno; pr_err("dso cache fstat failed: %s\n", - strerror_r(errno, sbuf, sizeof(sbuf))); + str_error_r(errno, sbuf, sizeof(sbuf))); dso->data.status = DSO_DATA_STATUS_ERROR; goto out; } @@ -1356,7 +1366,7 @@ int dso__strerror_load(struct dso *dso, char *buf, size_t buflen) BUG_ON(buflen == 0); if (errnum >= 0) { - const char *err = strerror_r(errnum, buf, buflen); + const char *err = str_error_r(errnum, buf, buflen); if (err != buf) scnprintf(buf, buflen, "%s", err); diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 0953280629cf..ecc4bbd3f82e 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -4,6 +4,7 @@ #include <linux/atomic.h> #include <linux/types.h> #include <linux/rbtree.h> +#include <sys/types.h> #include <stdbool.h> #include <pthread.h> #include <linux/types.h> @@ -349,10 +350,17 @@ static inline bool dso__is_kcore(struct dso *dso) dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE; } +static inline bool dso__is_kallsyms(struct dso *dso) +{ + return dso->kernel && dso->long_name[0] != '/'; +} + void dso__free_a2l(struct dso *dso); enum dso_type dso__type(struct dso *dso, struct machine *machine); int dso__strerror_load(struct dso *dso, char *buf, size_t buflen); +void reset_fd_limit(void); + #endif /* __PERF_DSO */ diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 49a11d9d8b8f..bb964e86b09d 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -18,10 +18,13 @@ void perf_env__exit(struct perf_env *env) zfree(&env->cmdline_argv); zfree(&env->sibling_cores); zfree(&env->sibling_threads); - zfree(&env->numa_nodes); zfree(&env->pmu_mappings); zfree(&env->cpu); + for (i = 0; i < env->nr_numa_nodes; i++) + cpu_map__put(env->numa_nodes[i].map); + zfree(&env->numa_nodes); + for (i = 0; i < env->caches_cnt; i++) cpu_cache_level__free(&env->caches[i]); zfree(&env->caches); diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 56cffb60a0b4..b164dfd2dcbf 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -2,6 +2,7 @@ #define __PERF_ENV_H #include <linux/types.h> +#include "cpumap.h" struct cpu_topology_map { int socket_id; @@ -18,6 +19,13 @@ struct cpu_cache_level { char *map; }; +struct numa_node { + u32 node; + u64 mem_total; + u64 mem_free; + struct cpu_map *map; +}; + struct perf_env { char *hostname; char *os_release; @@ -40,11 +48,11 @@ struct perf_env { const char **cmdline_argv; char *sibling_cores; char *sibling_threads; - char *numa_nodes; char *pmu_mappings; struct cpu_topology_map *cpu; struct cpu_cache_level *caches; int caches_cnt; + struct numa_node *numa_nodes; }; extern struct perf_env perf_env; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index f6fcc6832949..e20438b784be 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -673,6 +673,8 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, int err; union perf_event *event; + if (symbol_conf.kptr_restrict) + return -1; if (map == NULL) return -1; @@ -1090,7 +1092,7 @@ size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp) struct cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data); size_t ret; - ret = fprintf(fp, " nr: "); + ret = fprintf(fp, ": "); if (cpus) ret += cpu_map__fprintf(cpus, fp); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index e82ba90cc969..2a40b8e1def7 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -15,6 +15,7 @@ #include "evlist.h" #include "evsel.h" #include "debug.h" +#include "asm/bug.h" #include <unistd.h> #include "parse-events.h" @@ -27,8 +28,8 @@ #include <linux/log2.h> #include <linux/err.h> -static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx); -static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx); +static void perf_mmap__munmap(struct perf_mmap *map); +static void perf_mmap__put(struct perf_mmap *map); #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) #define SID(e, x, y) xyarray__entry(e->sample_id, x, y) @@ -44,7 +45,7 @@ void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, perf_evlist__set_maps(evlist, cpus, threads); fdarray__init(&evlist->pollfd, 64); evlist->workload.pid = -1; - evlist->backward = false; + evlist->bkw_mmap_state = BKW_MMAP_NOTREADY; } struct perf_evlist *perf_evlist__new(void) @@ -100,7 +101,7 @@ static void perf_evlist__update_id_pos(struct perf_evlist *evlist) { struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) + evlist__for_each_entry(evlist, evsel) perf_evsel__calc_id_pos(evsel); perf_evlist__set_id_pos(evlist); @@ -110,7 +111,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist) { struct perf_evsel *pos, *n; - evlist__for_each_safe(evlist, n, pos) { + evlist__for_each_entry_safe(evlist, n, pos) { list_del_init(&pos->node); pos->evlist = NULL; perf_evsel__delete(pos); @@ -122,11 +123,15 @@ static void perf_evlist__purge(struct perf_evlist *evlist) void perf_evlist__exit(struct perf_evlist *evlist) { zfree(&evlist->mmap); + zfree(&evlist->backward_mmap); fdarray__exit(&evlist->pollfd); } void perf_evlist__delete(struct perf_evlist *evlist) { + if (evlist == NULL) + return; + perf_evlist__munmap(evlist); perf_evlist__close(evlist); cpu_map__put(evlist->cpus); @@ -161,7 +166,7 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist) { struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) + evlist__for_each_entry(evlist, evsel) __perf_evlist__propagate_maps(evlist, evsel); } @@ -190,7 +195,7 @@ void perf_evlist__splice_list_tail(struct perf_evlist *evlist, { struct perf_evsel *evsel, *temp; - __evlist__for_each_safe(list, temp, evsel) { + __evlist__for_each_entry_safe(list, temp, evsel) { list_del_init(&evsel->node); perf_evlist__add(evlist, evsel); } @@ -205,7 +210,7 @@ void __perf_evlist__set_leader(struct list_head *list) leader->nr_members = evsel->idx - leader->idx + 1; - __evlist__for_each(list, evsel) { + __evlist__for_each_entry(list, evsel) { evsel->leader = leader; } } @@ -296,7 +301,7 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist, return 0; out_delete_partial_list: - __evlist__for_each_safe(&head, n, evsel) + __evlist__for_each_entry_safe(&head, n, evsel) perf_evsel__delete(evsel); return -1; } @@ -317,7 +322,7 @@ perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) { struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel->attr.type == PERF_TYPE_TRACEPOINT && (int)evsel->attr.config == id) return evsel; @@ -332,7 +337,7 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, { struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) && (strcmp(evsel->name, name) == 0)) return evsel; @@ -367,7 +372,7 @@ void perf_evlist__disable(struct perf_evlist *evlist) { struct perf_evsel *pos; - evlist__for_each(evlist, pos) { + evlist__for_each_entry(evlist, pos) { if (!perf_evsel__is_group_leader(pos) || !pos->fd) continue; perf_evsel__disable(pos); @@ -380,7 +385,7 @@ void perf_evlist__enable(struct perf_evlist *evlist) { struct perf_evsel *pos; - evlist__for_each(evlist, pos) { + evlist__for_each_entry(evlist, pos) { if (!perf_evsel__is_group_leader(pos) || !pos->fd) continue; perf_evsel__enable(pos); @@ -448,7 +453,7 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) int nfds = 0; struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel->system_wide) nfds += nr_cpus; else @@ -462,15 +467,16 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) return 0; } -static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx) +static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, + struct perf_mmap *map, short revent) { - int pos = fdarray__add(&evlist->pollfd, fd, POLLIN | POLLERR | POLLHUP); + int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP); /* * Save the idx so that when we filter out fds POLLHUP'ed we can * close the associated evlist->mmap[] entry. */ if (pos >= 0) { - evlist->pollfd.priv[pos].idx = idx; + evlist->pollfd.priv[pos].ptr = map; fcntl(fd, F_SETFL, O_NONBLOCK); } @@ -480,20 +486,22 @@ static int __perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, int idx int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd) { - return __perf_evlist__add_pollfd(evlist, fd, -1); + return __perf_evlist__add_pollfd(evlist, fd, NULL, POLLIN); } -static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd) +static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd, + void *arg __maybe_unused) { - struct perf_evlist *evlist = container_of(fda, struct perf_evlist, pollfd); + struct perf_mmap *map = fda->priv[fd].ptr; - perf_evlist__mmap_put(evlist, fda->priv[fd].idx); + if (map) + perf_mmap__put(map); } int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask) { return fdarray__filter(&evlist->pollfd, revents_and_mask, - perf_evlist__munmap_filtered); + perf_evlist__munmap_filtered, NULL); } int perf_evlist__poll(struct perf_evlist *evlist, int timeout) @@ -647,8 +655,8 @@ static int perf_evlist__event2id(struct perf_evlist *evlist, return 0; } -static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, - union perf_event *event) +struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, + union perf_event *event) { struct perf_evsel *first = perf_evlist__first(evlist); struct hlist_head *head; @@ -684,8 +692,11 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value) { int i; + if (!evlist->backward_mmap) + return 0; + for (i = 0; i < evlist->nr_mmaps; i++) { - int fd = evlist->mmap[i].fd; + int fd = evlist->backward_mmap[i].fd; int err; if (fd < 0) @@ -697,12 +708,12 @@ static int perf_evlist__set_paused(struct perf_evlist *evlist, bool value) return 0; } -int perf_evlist__pause(struct perf_evlist *evlist) +static int perf_evlist__pause(struct perf_evlist *evlist) { return perf_evlist__set_paused(evlist, true); } -int perf_evlist__resume(struct perf_evlist *evlist) +static int perf_evlist__resume(struct perf_evlist *evlist) { return perf_evlist__set_paused(evlist, false); } @@ -777,9 +788,8 @@ broken_event: return event; } -union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) +union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messup) { - struct perf_mmap *md = &evlist->mmap[idx]; u64 head; u64 old = md->prev; @@ -791,13 +801,12 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) head = perf_mmap__read_head(md); - return perf_mmap__read(md, evlist->overwrite, old, head, &md->prev); + return perf_mmap__read(md, check_messup, old, head, &md->prev); } union perf_event * -perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx) +perf_mmap__read_backward(struct perf_mmap *md) { - struct perf_mmap *md = &evlist->mmap[idx]; u64 head, end; u64 start = md->prev; @@ -832,9 +841,38 @@ perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx) return perf_mmap__read(md, false, start, end, &md->prev); } -void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx) +union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx) +{ + struct perf_mmap *md = &evlist->mmap[idx]; + + /* + * Check messup is required for forward overwritable ring buffer: + * memory pointed by md->prev can be overwritten in this case. + * No need for read-write ring buffer: kernel stop outputting when + * it hit md->prev (perf_mmap__consume()). + */ + return perf_mmap__read_forward(md, evlist->overwrite); +} + +union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx) { struct perf_mmap *md = &evlist->mmap[idx]; + + /* + * No need to check messup for backward ring buffer: + * We can always read arbitrary long data from a backward + * ring buffer unless we forget to pause it before reading. + */ + return perf_mmap__read_backward(md); +} + +union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) +{ + return perf_evlist__mmap_read_forward(evlist, idx); +} + +void perf_mmap__read_catchup(struct perf_mmap *md) +{ u64 head; if (!atomic_read(&md->refcnt)) @@ -844,36 +882,44 @@ void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx) md->prev = head; } +void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx) +{ + perf_mmap__read_catchup(&evlist->mmap[idx]); +} + static bool perf_mmap__empty(struct perf_mmap *md) { return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base; } -static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx) +static void perf_mmap__get(struct perf_mmap *map) { - atomic_inc(&evlist->mmap[idx].refcnt); + atomic_inc(&map->refcnt); } -static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx) +static void perf_mmap__put(struct perf_mmap *md) { - BUG_ON(atomic_read(&evlist->mmap[idx].refcnt) == 0); + BUG_ON(md->base && atomic_read(&md->refcnt) == 0); - if (atomic_dec_and_test(&evlist->mmap[idx].refcnt)) - __perf_evlist__munmap(evlist, idx); + if (atomic_dec_and_test(&md->refcnt)) + perf_mmap__munmap(md); } -void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) +void perf_mmap__consume(struct perf_mmap *md, bool overwrite) { - struct perf_mmap *md = &evlist->mmap[idx]; - - if (!evlist->overwrite) { + if (!overwrite) { u64 old = md->prev; perf_mmap__write_tail(md, old); } if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md)) - perf_evlist__mmap_put(evlist, idx); + perf_mmap__put(md); +} + +void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) +{ + perf_mmap__consume(&evlist->mmap[idx], evlist->overwrite); } int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused, @@ -904,41 +950,52 @@ void __weak auxtrace_mmap_params__set_idx( { } -static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx) +static void perf_mmap__munmap(struct perf_mmap *map) { - if (evlist->mmap[idx].base != NULL) { - munmap(evlist->mmap[idx].base, evlist->mmap_len); - evlist->mmap[idx].base = NULL; - evlist->mmap[idx].fd = -1; - atomic_set(&evlist->mmap[idx].refcnt, 0); + if (map->base != NULL) { + munmap(map->base, perf_mmap__mmap_len(map)); + map->base = NULL; + map->fd = -1; + atomic_set(&map->refcnt, 0); } - auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap); + auxtrace_mmap__munmap(&map->auxtrace_mmap); } -void perf_evlist__munmap(struct perf_evlist *evlist) +static void perf_evlist__munmap_nofree(struct perf_evlist *evlist) { int i; - if (evlist->mmap == NULL) - return; + if (evlist->mmap) + for (i = 0; i < evlist->nr_mmaps; i++) + perf_mmap__munmap(&evlist->mmap[i]); - for (i = 0; i < evlist->nr_mmaps; i++) - __perf_evlist__munmap(evlist, i); + if (evlist->backward_mmap) + for (i = 0; i < evlist->nr_mmaps; i++) + perf_mmap__munmap(&evlist->backward_mmap[i]); +} +void perf_evlist__munmap(struct perf_evlist *evlist) +{ + perf_evlist__munmap_nofree(evlist); zfree(&evlist->mmap); + zfree(&evlist->backward_mmap); } -static int perf_evlist__alloc_mmap(struct perf_evlist *evlist) +static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist) { int i; + struct perf_mmap *map; evlist->nr_mmaps = cpu_map__nr(evlist->cpus); if (cpu_map__empty(evlist->cpus)) evlist->nr_mmaps = thread_map__nr(evlist->threads); - evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap)); + map = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap)); + if (!map) + return NULL; + for (i = 0; i < evlist->nr_mmaps; i++) - evlist->mmap[i].fd = -1; - return evlist->mmap != NULL ? 0 : -ENOMEM; + map[i].fd = -1; + return map; } struct mmap_params { @@ -947,8 +1004,8 @@ struct mmap_params { struct auxtrace_mmap_params auxtrace_mp; }; -static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx, - struct mmap_params *mp, int fd) +static int perf_mmap__mmap(struct perf_mmap *map, + struct mmap_params *mp, int fd) { /* * The last one will be done at perf_evlist__mmap_consume(), so that we @@ -963,35 +1020,61 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx, * evlist layer can't just drop it when filtering events in * perf_evlist__filter_pollfd(). */ - atomic_set(&evlist->mmap[idx].refcnt, 2); - evlist->mmap[idx].prev = 0; - evlist->mmap[idx].mask = mp->mask; - evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot, - MAP_SHARED, fd, 0); - if (evlist->mmap[idx].base == MAP_FAILED) { + atomic_set(&map->refcnt, 2); + map->prev = 0; + map->mask = mp->mask; + map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot, + MAP_SHARED, fd, 0); + if (map->base == MAP_FAILED) { pr_debug2("failed to mmap perf event ring buffer, error %d\n", errno); - evlist->mmap[idx].base = NULL; + map->base = NULL; return -1; } - evlist->mmap[idx].fd = fd; + map->fd = fd; - if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap, - &mp->auxtrace_mp, evlist->mmap[idx].base, fd)) + if (auxtrace_mmap__mmap(&map->auxtrace_mmap, + &mp->auxtrace_mp, map->base, fd)) return -1; return 0; } +static bool +perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused, + struct perf_evsel *evsel) +{ + if (evsel->attr.write_backward) + return false; + return true; +} + static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, struct mmap_params *mp, int cpu, - int thread, int *output) + int thread, int *_output, int *_output_backward) { struct perf_evsel *evsel; + int revent; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { + struct perf_mmap *maps = evlist->mmap; + int *output = _output; int fd; + if (evsel->attr.write_backward) { + output = _output_backward; + maps = evlist->backward_mmap; + + if (!maps) { + maps = perf_evlist__alloc_mmap(evlist); + if (!maps) + return -1; + evlist->backward_mmap = maps; + if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY) + perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); + } + } + if (evsel->system_wide && thread) continue; @@ -999,15 +1082,18 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, if (*output == -1) { *output = fd; - if (__perf_evlist__mmap(evlist, idx, mp, *output) < 0) + + if (perf_mmap__mmap(&maps[idx], mp, *output) < 0) return -1; } else { if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) return -1; - perf_evlist__mmap_get(evlist, idx); + perf_mmap__get(&maps[idx]); } + revent = perf_evlist__should_poll(evlist, evsel) ? POLLIN : 0; + /* * The system_wide flag causes a selected event to be opened * always without a pid. Consequently it will never get a @@ -1016,8 +1102,8 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx, * Therefore don't add it for polling. */ if (!evsel->system_wide && - __perf_evlist__add_pollfd(evlist, fd, idx) < 0) { - perf_evlist__mmap_put(evlist, idx); + __perf_evlist__add_pollfd(evlist, fd, &maps[idx], revent) < 0) { + perf_mmap__put(&maps[idx]); return -1; } @@ -1043,13 +1129,14 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, pr_debug2("perf event ring buffer mmapped per cpu\n"); for (cpu = 0; cpu < nr_cpus; cpu++) { int output = -1; + int output_backward = -1; auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu, true); for (thread = 0; thread < nr_threads; thread++) { if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu, - thread, &output)) + thread, &output, &output_backward)) goto out_unmap; } } @@ -1057,8 +1144,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, return 0; out_unmap: - for (cpu = 0; cpu < nr_cpus; cpu++) - __perf_evlist__munmap(evlist, cpu); + perf_evlist__munmap_nofree(evlist); return -1; } @@ -1071,20 +1157,20 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, pr_debug2("perf event ring buffer mmapped per thread\n"); for (thread = 0; thread < nr_threads; thread++) { int output = -1; + int output_backward = -1; auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread, false); if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread, - &output)) + &output, &output_backward)) goto out_unmap; } return 0; out_unmap: - for (thread = 0; thread < nr_threads; thread++) - __perf_evlist__munmap(evlist, thread); + perf_evlist__munmap_nofree(evlist); return -1; } @@ -1217,7 +1303,9 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, .prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), }; - if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0) + if (!evlist->mmap) + evlist->mmap = perf_evlist__alloc_mmap(evlist); + if (!evlist->mmap) return -ENOMEM; if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0) @@ -1231,7 +1319,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len, auxtrace_pages, auxtrace_overwrite); - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && evsel->sample_id == NULL && perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0) @@ -1307,7 +1395,7 @@ void __perf_evlist__set_sample_bit(struct perf_evlist *evlist, { struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) + evlist__for_each_entry(evlist, evsel) __perf_evsel__set_sample_bit(evsel, bit); } @@ -1316,7 +1404,7 @@ void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist, { struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) + evlist__for_each_entry(evlist, evsel) __perf_evsel__reset_sample_bit(evsel, bit); } @@ -1327,7 +1415,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **e const int ncpus = cpu_map__nr(evlist->cpus), nthreads = thread_map__nr(evlist->threads); - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel->filter == NULL) continue; @@ -1350,7 +1438,7 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter) struct perf_evsel *evsel; int err = 0; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel->attr.type != PERF_TYPE_TRACEPOINT) continue; @@ -1404,7 +1492,7 @@ bool perf_evlist__valid_sample_type(struct perf_evlist *evlist) if (evlist->id_pos < 0 || evlist->is_pos < 0) return false; - evlist__for_each(evlist, pos) { + evlist__for_each_entry(evlist, pos) { if (pos->id_pos != evlist->id_pos || pos->is_pos != evlist->is_pos) return false; @@ -1420,7 +1508,7 @@ u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist) if (evlist->combined_sample_type) return evlist->combined_sample_type; - evlist__for_each(evlist, evsel) + evlist__for_each_entry(evlist, evsel) evlist->combined_sample_type |= evsel->attr.sample_type; return evlist->combined_sample_type; @@ -1437,7 +1525,7 @@ u64 perf_evlist__combined_branch_type(struct perf_evlist *evlist) struct perf_evsel *evsel; u64 branch_type = 0; - evlist__for_each(evlist, evsel) + evlist__for_each_entry(evlist, evsel) branch_type |= evsel->attr.branch_sample_type; return branch_type; } @@ -1448,7 +1536,7 @@ bool perf_evlist__valid_read_format(struct perf_evlist *evlist) u64 read_format = first->attr.read_format; u64 sample_type = first->attr.sample_type; - evlist__for_each(evlist, pos) { + evlist__for_each_entry(evlist, pos) { if (read_format != pos->attr.read_format) return false; } @@ -1505,7 +1593,7 @@ bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist) { struct perf_evsel *first = perf_evlist__first(evlist), *pos = first; - evlist__for_each_continue(evlist, pos) { + evlist__for_each_entry_continue(evlist, pos) { if (first->attr.sample_id_all != pos->attr.sample_id_all) return false; } @@ -1532,7 +1620,7 @@ void perf_evlist__close(struct perf_evlist *evlist) int nthreads = thread_map__nr(evlist->threads); int n; - evlist__for_each_reverse(evlist, evsel) { + evlist__for_each_entry_reverse(evlist, evsel) { n = evsel->cpus ? evsel->cpus->nr : ncpus; perf_evsel__close(evsel, n, nthreads); } @@ -1586,7 +1674,7 @@ int perf_evlist__open(struct perf_evlist *evlist) perf_evlist__update_id_pos(evlist); - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { err = perf_evsel__open(evsel, evsel->cpus, evsel->threads); if (err < 0) goto out_err; @@ -1747,7 +1835,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp) struct perf_evsel *evsel; size_t printed = 0; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { printed += fprintf(fp, "%s%s", evsel->idx ? ", " : "", perf_evsel__name(evsel)); } @@ -1759,7 +1847,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size) { int printed, value; - char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf)); + char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf)); switch (err) { case EACCES: @@ -1811,7 +1899,7 @@ out_default: int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size) { - char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf)); + char sbuf[STRERR_BUFSIZE], *emsg = str_error_r(err, sbuf, sizeof(sbuf)); int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0; switch (err) { @@ -1849,7 +1937,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist, if (move_evsel == perf_evlist__first(evlist)) return; - evlist__for_each_safe(evlist, n, evsel) { + evlist__for_each_entry_safe(evlist, n, evsel) { if (evsel->leader == move_evsel->leader) list_move_tail(&evsel->node, &move); } @@ -1865,7 +1953,7 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist, if (tracking_evsel->tracking) return; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel != tracking_evsel) evsel->tracking = false; } @@ -1879,7 +1967,7 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, { struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (!evsel->name) continue; if (strcmp(str, evsel->name) == 0) @@ -1888,3 +1976,61 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, return NULL; } + +void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, + enum bkw_mmap_state state) +{ + enum bkw_mmap_state old_state = evlist->bkw_mmap_state; + enum action { + NONE, + PAUSE, + RESUME, + } action = NONE; + + if (!evlist->backward_mmap) + return; + + switch (old_state) { + case BKW_MMAP_NOTREADY: { + if (state != BKW_MMAP_RUNNING) + goto state_err;; + break; + } + case BKW_MMAP_RUNNING: { + if (state != BKW_MMAP_DATA_PENDING) + goto state_err; + action = PAUSE; + break; + } + case BKW_MMAP_DATA_PENDING: { + if (state != BKW_MMAP_EMPTY) + goto state_err; + break; + } + case BKW_MMAP_EMPTY: { + if (state != BKW_MMAP_RUNNING) + goto state_err; + action = RESUME; + break; + } + default: + WARN_ONCE(1, "Shouldn't get there\n"); + } + + evlist->bkw_mmap_state = state; + + switch (action) { + case PAUSE: + perf_evlist__pause(evlist); + break; + case RESUME: + perf_evlist__resume(evlist); + break; + case NONE: + default: + break; + } + +state_err: + return; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index d740fb877ab6..4fd034f22d2f 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -35,6 +35,40 @@ struct perf_mmap { char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8))); }; +static inline size_t +perf_mmap__mmap_len(struct perf_mmap *map) +{ + return map->mask + 1 + page_size; +} + +/* + * State machine of bkw_mmap_state: + * + * .________________(forbid)_____________. + * | V + * NOTREADY --(0)--> RUNNING --(1)--> DATA_PENDING --(2)--> EMPTY + * ^ ^ | ^ | + * | |__(forbid)____/ |___(forbid)___/| + * | | + * \_________________(3)_______________/ + * + * NOTREADY : Backward ring buffers are not ready + * RUNNING : Backward ring buffers are recording + * DATA_PENDING : We are required to collect data from backward ring buffers + * EMPTY : We have collected data from backward ring buffers. + * + * (0): Setup backward ring buffer + * (1): Pause ring buffers for reading + * (2): Read from ring buffers + * (3): Resume ring buffers for recording + */ +enum bkw_mmap_state { + BKW_MMAP_NOTREADY, + BKW_MMAP_RUNNING, + BKW_MMAP_DATA_PENDING, + BKW_MMAP_EMPTY, +}; + struct perf_evlist { struct list_head entries; struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; @@ -44,17 +78,18 @@ struct perf_evlist { bool overwrite; bool enabled; bool has_user_cpus; - bool backward; size_t mmap_len; int id_pos; int is_pos; u64 combined_sample_type; + enum bkw_mmap_state bkw_mmap_state; struct { int cork_fd; pid_t pid; } workload; struct fdarray pollfd; struct perf_mmap *mmap; + struct perf_mmap *backward_mmap; struct thread_map *threads; struct cpu_map *cpus; struct perf_evsel *selected; @@ -129,16 +164,24 @@ struct perf_evsel *perf_evlist__id2evsel_strict(struct perf_evlist *evlist, struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id); +void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state); + +union perf_event *perf_mmap__read_forward(struct perf_mmap *map, bool check_messup); +union perf_event *perf_mmap__read_backward(struct perf_mmap *map); + +void perf_mmap__read_catchup(struct perf_mmap *md); +void perf_mmap__consume(struct perf_mmap *md, bool overwrite); + union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx); +union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, + int idx); union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx); void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx); void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); -int perf_evlist__pause(struct perf_evlist *evlist); -int perf_evlist__resume(struct perf_evlist *evlist); int perf_evlist__open(struct perf_evlist *evlist); void perf_evlist__close(struct perf_evlist *evlist); @@ -249,70 +292,70 @@ void perf_evlist__to_front(struct perf_evlist *evlist, struct perf_evsel *move_evsel); /** - * __evlist__for_each - iterate thru all the evsels + * __evlist__for_each_entry - iterate thru all the evsels * @list: list_head instance to iterate * @evsel: struct evsel iterator */ -#define __evlist__for_each(list, evsel) \ +#define __evlist__for_each_entry(list, evsel) \ list_for_each_entry(evsel, list, node) /** - * evlist__for_each - iterate thru all the evsels + * evlist__for_each_entry - iterate thru all the evsels * @evlist: evlist instance to iterate * @evsel: struct evsel iterator */ -#define evlist__for_each(evlist, evsel) \ - __evlist__for_each(&(evlist)->entries, evsel) +#define evlist__for_each_entry(evlist, evsel) \ + __evlist__for_each_entry(&(evlist)->entries, evsel) /** - * __evlist__for_each_continue - continue iteration thru all the evsels + * __evlist__for_each_entry_continue - continue iteration thru all the evsels * @list: list_head instance to iterate * @evsel: struct evsel iterator */ -#define __evlist__for_each_continue(list, evsel) \ +#define __evlist__for_each_entry_continue(list, evsel) \ list_for_each_entry_continue(evsel, list, node) /** - * evlist__for_each_continue - continue iteration thru all the evsels + * evlist__for_each_entry_continue - continue iteration thru all the evsels * @evlist: evlist instance to iterate * @evsel: struct evsel iterator */ -#define evlist__for_each_continue(evlist, evsel) \ - __evlist__for_each_continue(&(evlist)->entries, evsel) +#define evlist__for_each_entry_continue(evlist, evsel) \ + __evlist__for_each_entry_continue(&(evlist)->entries, evsel) /** - * __evlist__for_each_reverse - iterate thru all the evsels in reverse order + * __evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order * @list: list_head instance to iterate * @evsel: struct evsel iterator */ -#define __evlist__for_each_reverse(list, evsel) \ +#define __evlist__for_each_entry_reverse(list, evsel) \ list_for_each_entry_reverse(evsel, list, node) /** - * evlist__for_each_reverse - iterate thru all the evsels in reverse order + * evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order * @evlist: evlist instance to iterate * @evsel: struct evsel iterator */ -#define evlist__for_each_reverse(evlist, evsel) \ - __evlist__for_each_reverse(&(evlist)->entries, evsel) +#define evlist__for_each_entry_reverse(evlist, evsel) \ + __evlist__for_each_entry_reverse(&(evlist)->entries, evsel) /** - * __evlist__for_each_safe - safely iterate thru all the evsels + * __evlist__for_each_entry_safe - safely iterate thru all the evsels * @list: list_head instance to iterate * @tmp: struct evsel temp iterator * @evsel: struct evsel iterator */ -#define __evlist__for_each_safe(list, tmp, evsel) \ +#define __evlist__for_each_entry_safe(list, tmp, evsel) \ list_for_each_entry_safe(evsel, tmp, list, node) /** - * evlist__for_each_safe - safely iterate thru all the evsels + * evlist__for_each_entry_safe - safely iterate thru all the evsels * @evlist: evlist instance to iterate * @evsel: struct evsel iterator * @tmp: struct evsel temp iterator */ -#define evlist__for_each_safe(evlist, tmp, evsel) \ - __evlist__for_each_safe(&(evlist)->entries, tmp, evsel) +#define evlist__for_each_entry_safe(evlist, tmp, evsel) \ + __evlist__for_each_entry_safe(&(evlist)->entries, tmp, evsel) void perf_evlist__set_tracking_event(struct perf_evlist *evlist, struct perf_evsel *tracking_evsel); @@ -321,4 +364,7 @@ void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr); struct perf_evsel * perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str); + +struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist, + union perf_event *event); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 5d7037ef7d3b..8c54df61fe64 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -200,6 +200,24 @@ void perf_evsel__set_sample_id(struct perf_evsel *evsel, evsel->attr.read_format |= PERF_FORMAT_ID; } +/** + * perf_evsel__is_function_event - Return whether given evsel is a function + * trace event + * + * @evsel - evsel selector to be tested + * + * Return %true if event is function trace event + */ +bool perf_evsel__is_function_event(struct perf_evsel *evsel) +{ +#define FUNCTION_EVENT "ftrace:function" + + return evsel->name && + !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT)); + +#undef FUNCTION_EVENT +} + void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr, int idx) { @@ -572,6 +590,8 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel, perf_evsel__set_sample_bit(evsel, CALLCHAIN); + attr->sample_max_stack = param->max_stack; + if (param->record_mode == CALLCHAIN_LBR) { if (!opts->branch_stack) { if (attr->exclude_user) { @@ -635,7 +655,8 @@ static void apply_config_terms(struct perf_evsel *evsel, struct perf_event_attr *attr = &evsel->attr; struct callchain_param param; u32 dump_size = 0; - char *callgraph_buf = NULL; + int max_stack = 0; + const char *callgraph_buf = NULL; /* callgraph default */ param.record_mode = callchain_param.record_mode; @@ -662,6 +683,9 @@ static void apply_config_terms(struct perf_evsel *evsel, case PERF_EVSEL__CONFIG_TERM_STACK_USER: dump_size = term->val.stack_user; break; + case PERF_EVSEL__CONFIG_TERM_MAX_STACK: + max_stack = term->val.max_stack; + break; case PERF_EVSEL__CONFIG_TERM_INHERIT: /* * attr->inherit should has already been set by @@ -671,13 +695,21 @@ static void apply_config_terms(struct perf_evsel *evsel, */ attr->inherit = term->val.inherit ? 1 : 0; break; + case PERF_EVSEL__CONFIG_TERM_OVERWRITE: + attr->write_backward = term->val.overwrite ? 1 : 0; + break; default: break; } } /* User explicitly set per-event callgraph, clear the old setting and reset. */ - if ((callgraph_buf != NULL) || (dump_size > 0)) { + if ((callgraph_buf != NULL) || (dump_size > 0) || max_stack) { + if (max_stack) { + param.max_stack = max_stack; + if (callgraph_buf == NULL) + callgraph_buf = "fp"; + } /* parse callgraph parameters */ if (callgraph_buf != NULL) { @@ -747,6 +779,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1; attr->inherit = !opts->no_inherit; + attr->write_backward = opts->overwrite ? 1 : 0; perf_evsel__set_sample_bit(evsel, IP); perf_evsel__set_sample_bit(evsel, TID); @@ -1329,6 +1362,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, PRINT_ATTRf(clockid, p_signed); PRINT_ATTRf(sample_regs_intr, p_hex); PRINT_ATTRf(aux_watermark, p_unsigned); + PRINT_ATTRf(sample_max_stack, p_unsigned); return ret; } @@ -1347,6 +1381,9 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, int pid = -1, err; enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE; + if (perf_missing_features.write_backward && evsel->attr.write_backward) + return -EINVAL; + if (evsel->system_wide) nthreads = 1; else @@ -1377,8 +1414,6 @@ fallback_missing_features: if (perf_missing_features.lbr_flags) evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS | PERF_SAMPLE_BRANCH_NO_CYCLES); - if (perf_missing_features.write_backward) - evsel->attr.write_backward = false; retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; @@ -1441,12 +1476,6 @@ retry_open: err = -EINVAL; goto out_close; } - - if (evsel->overwrite && - perf_missing_features.write_backward) { - err = -EINVAL; - goto out_close; - } } } @@ -1484,7 +1513,10 @@ try_fallback: * Must probe features in the order they were added to the * perf_event_attr interface. */ - if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) { + if (!perf_missing_features.write_backward && evsel->attr.write_backward) { + perf_missing_features.write_backward = true; + goto out_close; + } else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) { perf_missing_features.clockid_wrong = true; goto fallback_missing_features; } else if (!perf_missing_features.clockid && evsel->attr.use_clockid) { @@ -1509,12 +1541,7 @@ try_fallback: PERF_SAMPLE_BRANCH_NO_FLAGS))) { perf_missing_features.lbr_flags = true; goto fallback_missing_features; - } else if (!perf_missing_features.write_backward && - evsel->attr.write_backward) { - perf_missing_features.write_backward = true; - goto fallback_missing_features; } - out_close: do { while (--thread >= 0) { @@ -2239,17 +2266,11 @@ void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample, return sample->raw_data + offset; } -u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, - const char *name) +u64 format_field__intval(struct format_field *field, struct perf_sample *sample, + bool needs_swap) { - struct format_field *field = perf_evsel__field(evsel, name); - void *ptr; u64 value; - - if (!field) - return 0; - - ptr = sample->raw_data + field->offset; + void *ptr = sample->raw_data + field->offset; switch (field->size) { case 1: @@ -2267,7 +2288,7 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, return 0; } - if (!evsel->needs_swap) + if (!needs_swap) return value; switch (field->size) { @@ -2284,6 +2305,17 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, return 0; } +u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, + const char *name) +{ + struct format_field *field = perf_evsel__field(evsel, name); + + if (!field) + return 0; + + return field ? format_field__intval(field, sample, evsel->needs_swap) : 0; +} + bool perf_evsel__fallback(struct perf_evsel *evsel, int err, char *msg, size_t msgsize) { @@ -2372,6 +2404,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "No such device - did you specify an out-of-range profile CPU?"); break; case EOPNOTSUPP: + if (evsel->attr.sample_period != 0) + return scnprintf(msg, size, "%s", + "PMU Hardware doesn't support sampling/overflow-interrupts."); if (evsel->attr.precise_ip) return scnprintf(msg, size, "%s", "\'precise\' request may not be supported. Try removing 'p' modifier."); @@ -2389,6 +2424,8 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "We found oprofile daemon running, please stop it and try again."); break; case EINVAL: + if (evsel->attr.write_backward && perf_missing_features.write_backward) + return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel."); if (perf_missing_features.clockid) return scnprintf(msg, size, "clockid feature not supported."); if (perf_missing_features.clockid_wrong) @@ -2402,6 +2439,13 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n" "/bin/dmesg may provide additional information.\n" "No CONFIG_PERF_EVENTS=y kernel support configured?", - err, strerror_r(err, sbuf, sizeof(sbuf)), + err, str_error_r(err, sbuf, sizeof(sbuf)), perf_evsel__name(evsel)); } + +char *perf_evsel__env_arch(struct perf_evsel *evsel) +{ + if (evsel && evsel->evlist && evsel->evlist->env) + return evsel->evlist->env->arch; + return NULL; +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index c1f10159804c..8a4a6c9f1480 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -44,6 +44,8 @@ enum { PERF_EVSEL__CONFIG_TERM_CALLGRAPH, PERF_EVSEL__CONFIG_TERM_STACK_USER, PERF_EVSEL__CONFIG_TERM_INHERIT, + PERF_EVSEL__CONFIG_TERM_MAX_STACK, + PERF_EVSEL__CONFIG_TERM_OVERWRITE, PERF_EVSEL__CONFIG_TERM_MAX, }; @@ -56,7 +58,9 @@ struct perf_evsel_config_term { bool time; char *callgraph; u64 stack_user; + int max_stack; bool inherit; + bool overwrite; } val; }; @@ -112,7 +116,6 @@ struct perf_evsel { bool tracking; bool per_pkg; bool precise_max; - bool overwrite; /* parse modifier helper */ int exclude_GH; int nr_members; @@ -259,6 +262,8 @@ static inline char *perf_evsel__strval(struct perf_evsel *evsel, struct format_field; +u64 format_field__intval(struct format_field *field, struct perf_sample *sample, bool needs_swap); + struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name); #define perf_evsel__match(evsel, t, c) \ @@ -351,23 +356,7 @@ static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel) return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1; } -/** - * perf_evsel__is_function_event - Return whether given evsel is a function - * trace event - * - * @evsel - evsel selector to be tested - * - * Return %true if event is function trace event - */ -static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel) -{ -#define FUNCTION_EVENT "ftrace:function" - - return evsel->name && - !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT)); - -#undef FUNCTION_EVENT -} +bool perf_evsel__is_function_event(struct perf_evsel *evsel); static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel) { @@ -431,4 +420,6 @@ typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *); int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, attr__fprintf_f attr__fprintf, void *priv); +char *perf_evsel__env_arch(struct perf_evsel *evsel); + #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/group.h b/tools/perf/util/group.h new file mode 100644 index 000000000000..116debe7a995 --- /dev/null +++ b/tools/perf/util/group.h @@ -0,0 +1,7 @@ +#ifndef GROUP_H +#define GROUP_H 1 + +bool arch_topdown_check_group(bool *warn); +void arch_topdown_group_warn(void); + +#endif diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 08852dde1378..8f0db4007282 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -336,7 +336,7 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused, if (ret < 0) return ret; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { ret = do_write(fd, &evsel->attr, sz); if (ret < 0) return ret; @@ -801,7 +801,7 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused, if (ret < 0) return ret; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1) { const char *name = evsel->group_name ?: "{anon_group}"; @@ -1306,42 +1306,19 @@ static void print_total_mem(struct perf_header *ph, int fd __maybe_unused, static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused, FILE *fp) { - u32 nr, c, i; - char *str, *tmp; - uint64_t mem_total, mem_free; - - /* nr nodes */ - nr = ph->env.nr_numa_nodes; - str = ph->env.numa_nodes; - - for (i = 0; i < nr; i++) { - /* node number */ - c = strtoul(str, &tmp, 0); - if (*tmp != ':') - goto error; - - str = tmp + 1; - mem_total = strtoull(str, &tmp, 0); - if (*tmp != ':') - goto error; + int i; + struct numa_node *n; - str = tmp + 1; - mem_free = strtoull(str, &tmp, 0); - if (*tmp != ':') - goto error; + for (i = 0; i < ph->env.nr_numa_nodes; i++) { + n = &ph->env.numa_nodes[i]; fprintf(fp, "# node%u meminfo : total = %"PRIu64" kB," " free = %"PRIu64" kB\n", - c, mem_total, mem_free); + n->node, n->mem_total, n->mem_free); - str = tmp + 1; - fprintf(fp, "# node%u cpu list : %s\n", c, str); - - str += strlen(str) + 1; + fprintf(fp, "# node%u cpu list : ", n->node); + cpu_map__fprintf(n->map, fp); } - return; -error: - fprintf(fp, "# numa topology : not available\n"); } static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp) @@ -1425,7 +1402,7 @@ static void print_group_desc(struct perf_header *ph, int fd __maybe_unused, session = container_of(ph, struct perf_session, header); - evlist__for_each(session->evlist, evsel) { + evlist__for_each_entry(session->evlist, evsel) { if (perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1) { fprintf(fp, "# group: %s{%s", evsel->group_name ?: "", @@ -1703,7 +1680,7 @@ perf_evlist__find_by_index(struct perf_evlist *evlist, int idx) { struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel->idx == idx) return evsel; } @@ -1906,11 +1883,10 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse struct perf_header *ph, int fd, void *data __maybe_unused) { + struct numa_node *nodes, *n; ssize_t ret; - u32 nr, node, i; + u32 nr, i; char *str; - uint64_t mem_total, mem_free; - struct strbuf sb; /* nr nodes */ ret = readn(fd, &nr, sizeof(nr)); @@ -1921,47 +1897,47 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse nr = bswap_32(nr); ph->env.nr_numa_nodes = nr; - if (strbuf_init(&sb, 256) < 0) - return -1; + nodes = zalloc(sizeof(*nodes) * nr); + if (!nodes) + return -ENOMEM; for (i = 0; i < nr; i++) { + n = &nodes[i]; + /* node number */ - ret = readn(fd, &node, sizeof(node)); - if (ret != sizeof(node)) + ret = readn(fd, &n->node, sizeof(u32)); + if (ret != sizeof(n->node)) goto error; - ret = readn(fd, &mem_total, sizeof(u64)); + ret = readn(fd, &n->mem_total, sizeof(u64)); if (ret != sizeof(u64)) goto error; - ret = readn(fd, &mem_free, sizeof(u64)); + ret = readn(fd, &n->mem_free, sizeof(u64)); if (ret != sizeof(u64)) goto error; if (ph->needs_swap) { - node = bswap_32(node); - mem_total = bswap_64(mem_total); - mem_free = bswap_64(mem_free); + n->node = bswap_32(n->node); + n->mem_total = bswap_64(n->mem_total); + n->mem_free = bswap_64(n->mem_free); } - if (strbuf_addf(&sb, "%u:%"PRIu64":%"PRIu64":", - node, mem_total, mem_free) < 0) - goto error; - str = do_read_string(fd, ph); if (!str) goto error; - /* include a NULL character at the end */ - if (strbuf_add(&sb, str, strlen(str) + 1) < 0) + n->map = cpu_map__new(str); + if (!n->map) goto error; + free(str); } - ph->env.numa_nodes = strbuf_detach(&sb, NULL); + ph->env.numa_nodes = nodes; return 0; error: - strbuf_release(&sb); + free(nodes); return -1; } @@ -2075,7 +2051,7 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused, session->evlist->nr_groups = nr_groups; i = nr = 0; - evlist__for_each(session->evlist, evsel) { + evlist__for_each_entry(session->evlist, evsel) { if (evsel->idx == (int) desc[i].leader_idx) { evsel->leader = evsel; /* {anon_group} is a dummy name */ @@ -2383,7 +2359,7 @@ int perf_session__write_header(struct perf_session *session, lseek(fd, sizeof(f_header), SEEK_SET); - evlist__for_each(session->evlist, evsel) { + evlist__for_each_entry(session->evlist, evsel) { evsel->id_offset = lseek(fd, 0, SEEK_CUR); err = do_write(fd, evsel->id, evsel->ids * sizeof(u64)); if (err < 0) { @@ -2394,7 +2370,7 @@ int perf_session__write_header(struct perf_session *session, attr_offset = lseek(fd, 0, SEEK_CUR); - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { f_attr = (struct perf_file_attr){ .attr = evsel->attr, .ids = { @@ -2828,7 +2804,7 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist, { struct perf_evsel *pos; - evlist__for_each(evlist, pos) { + evlist__for_each_entry(evlist, pos) { if (pos->attr.type == PERF_TYPE_TRACEPOINT && perf_evsel__prepare_tracepoint_event(pos, pevent)) return -1; @@ -3127,7 +3103,7 @@ int perf_event__synthesize_attrs(struct perf_tool *tool, struct perf_evsel *evsel; int err = 0; - evlist__for_each(session->evlist, evsel) { + evlist__for_each_entry(session->evlist, evsel) { err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids, evsel->id, process); if (err) { diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c index d62ccaeeadd6..2821f8d77e52 100644 --- a/tools/perf/util/help-unknown-cmd.c +++ b/tools/perf/util/help-unknown-cmd.c @@ -1,4 +1,6 @@ #include "cache.h" +#include "config.h" +#include <stdio.h> #include <subcmd/help.h> #include "../builtin.h" #include "levenshtein.h" diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index d1f19e0012d4..a18d142cdca3 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -79,7 +79,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) len = thread__comm_len(h->thread); if (hists__new_col_len(hists, HISTC_COMM, len)) - hists__set_col_len(hists, HISTC_THREAD, len + 6); + hists__set_col_len(hists, HISTC_THREAD, len + 8); if (h->ms.map) { len = dso__name_len(h->ms.map->dso); @@ -352,86 +352,114 @@ void hists__delete_entries(struct hists *hists) * histogram, sorted on item, collects periods */ -static struct hist_entry *hist_entry__new(struct hist_entry *template, - bool sample_self) +static int hist_entry__init(struct hist_entry *he, + struct hist_entry *template, + bool sample_self) { - size_t callchain_size = 0; - struct hist_entry *he; + *he = *template; - if (symbol_conf.use_callchain) - callchain_size = sizeof(struct callchain_root); + if (symbol_conf.cumulate_callchain) { + he->stat_acc = malloc(sizeof(he->stat)); + if (he->stat_acc == NULL) + return -ENOMEM; + memcpy(he->stat_acc, &he->stat, sizeof(he->stat)); + if (!sample_self) + memset(&he->stat, 0, sizeof(he->stat)); + } - he = zalloc(sizeof(*he) + callchain_size); + map__get(he->ms.map); - if (he != NULL) { - *he = *template; + if (he->branch_info) { + /* + * This branch info is (a part of) allocated from + * sample__resolve_bstack() and will be freed after + * adding new entries. So we need to save a copy. + */ + he->branch_info = malloc(sizeof(*he->branch_info)); + if (he->branch_info == NULL) { + map__zput(he->ms.map); + free(he->stat_acc); + return -ENOMEM; + } + + memcpy(he->branch_info, template->branch_info, + sizeof(*he->branch_info)); + + map__get(he->branch_info->from.map); + map__get(he->branch_info->to.map); + } - if (symbol_conf.cumulate_callchain) { - he->stat_acc = malloc(sizeof(he->stat)); - if (he->stat_acc == NULL) { - free(he); - return NULL; + if (he->mem_info) { + map__get(he->mem_info->iaddr.map); + map__get(he->mem_info->daddr.map); + } + + if (symbol_conf.use_callchain) + callchain_init(he->callchain); + + if (he->raw_data) { + he->raw_data = memdup(he->raw_data, he->raw_size); + + if (he->raw_data == NULL) { + map__put(he->ms.map); + if (he->branch_info) { + map__put(he->branch_info->from.map); + map__put(he->branch_info->to.map); + free(he->branch_info); + } + if (he->mem_info) { + map__put(he->mem_info->iaddr.map); + map__put(he->mem_info->daddr.map); } - memcpy(he->stat_acc, &he->stat, sizeof(he->stat)); - if (!sample_self) - memset(&he->stat, 0, sizeof(he->stat)); + free(he->stat_acc); + return -ENOMEM; } + } + INIT_LIST_HEAD(&he->pairs.node); + thread__get(he->thread); - map__get(he->ms.map); + if (!symbol_conf.report_hierarchy) + he->leaf = true; - if (he->branch_info) { - /* - * This branch info is (a part of) allocated from - * sample__resolve_bstack() and will be freed after - * adding new entries. So we need to save a copy. - */ - he->branch_info = malloc(sizeof(*he->branch_info)); - if (he->branch_info == NULL) { - map__zput(he->ms.map); - free(he->stat_acc); - free(he); - return NULL; - } + return 0; +} - memcpy(he->branch_info, template->branch_info, - sizeof(*he->branch_info)); +static void *hist_entry__zalloc(size_t size) +{ + return zalloc(size + sizeof(struct hist_entry)); +} - map__get(he->branch_info->from.map); - map__get(he->branch_info->to.map); - } +static void hist_entry__free(void *ptr) +{ + free(ptr); +} - if (he->mem_info) { - map__get(he->mem_info->iaddr.map); - map__get(he->mem_info->daddr.map); - } +static struct hist_entry_ops default_ops = { + .new = hist_entry__zalloc, + .free = hist_entry__free, +}; - if (symbol_conf.use_callchain) - callchain_init(he->callchain); +static struct hist_entry *hist_entry__new(struct hist_entry *template, + bool sample_self) +{ + struct hist_entry_ops *ops = template->ops; + size_t callchain_size = 0; + struct hist_entry *he; + int err = 0; - if (he->raw_data) { - he->raw_data = memdup(he->raw_data, he->raw_size); + if (!ops) + ops = template->ops = &default_ops; - if (he->raw_data == NULL) { - map__put(he->ms.map); - if (he->branch_info) { - map__put(he->branch_info->from.map); - map__put(he->branch_info->to.map); - free(he->branch_info); - } - if (he->mem_info) { - map__put(he->mem_info->iaddr.map); - map__put(he->mem_info->daddr.map); - } - free(he->stat_acc); - free(he); - return NULL; - } - } - INIT_LIST_HEAD(&he->pairs.node); - thread__get(he->thread); + if (symbol_conf.use_callchain) + callchain_size = sizeof(struct callchain_root); - if (!symbol_conf.report_hierarchy) - he->leaf = true; + he = ops->new(callchain_size); + if (he) { + err = hist_entry__init(he, template, sample_self); + if (err) { + ops->free(he); + he = NULL; + } } return he; @@ -531,13 +559,15 @@ out: return he; } -struct hist_entry *__hists__add_entry(struct hists *hists, - struct addr_location *al, - struct symbol *sym_parent, - struct branch_info *bi, - struct mem_info *mi, - struct perf_sample *sample, - bool sample_self) +static struct hist_entry* +__hists__add_entry(struct hists *hists, + struct addr_location *al, + struct symbol *sym_parent, + struct branch_info *bi, + struct mem_info *mi, + struct perf_sample *sample, + bool sample_self, + struct hist_entry_ops *ops) { struct hist_entry entry = { .thread = al->thread, @@ -564,11 +594,37 @@ struct hist_entry *__hists__add_entry(struct hists *hists, .transaction = sample->transaction, .raw_data = sample->raw_data, .raw_size = sample->raw_size, + .ops = ops, }; return hists__findnew_entry(hists, &entry, al, sample_self); } +struct hist_entry *hists__add_entry(struct hists *hists, + struct addr_location *al, + struct symbol *sym_parent, + struct branch_info *bi, + struct mem_info *mi, + struct perf_sample *sample, + bool sample_self) +{ + return __hists__add_entry(hists, al, sym_parent, bi, mi, + sample, sample_self, NULL); +} + +struct hist_entry *hists__add_entry_ops(struct hists *hists, + struct hist_entry_ops *ops, + struct addr_location *al, + struct symbol *sym_parent, + struct branch_info *bi, + struct mem_info *mi, + struct perf_sample *sample, + bool sample_self) +{ + return __hists__add_entry(hists, al, sym_parent, bi, mi, + sample, sample_self, ops); +} + static int iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused, struct addr_location *al __maybe_unused) @@ -622,8 +678,8 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al */ sample->period = cost; - he = __hists__add_entry(hists, al, iter->parent, NULL, mi, - sample, true); + he = hists__add_entry(hists, al, iter->parent, NULL, mi, + sample, true); if (!he) return -ENOMEM; @@ -727,8 +783,8 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a sample->period = 1; sample->weight = bi->flags.cycles ? bi->flags.cycles : 1; - he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL, - sample, true); + he = hists__add_entry(hists, al, iter->parent, &bi[i], NULL, + sample, true); if (he == NULL) return -ENOMEM; @@ -764,8 +820,8 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location struct perf_sample *sample = iter->sample; struct hist_entry *he; - he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, - sample, true); + he = hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, + sample, true); if (he == NULL) return -ENOMEM; @@ -825,8 +881,8 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter, struct hist_entry *he; int err = 0; - he = __hists__add_entry(hists, al, iter->parent, NULL, NULL, - sample, true); + he = hists__add_entry(hists, al, iter->parent, NULL, NULL, + sample, true); if (he == NULL) return -ENOMEM; @@ -900,8 +956,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, } } - he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, - sample, false); + he = hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, + sample, false); if (he == NULL) return -ENOMEM; @@ -1043,6 +1099,8 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) void hist_entry__delete(struct hist_entry *he) { + struct hist_entry_ops *ops = he->ops; + thread__zput(he->thread); map__zput(he->ms.map); @@ -1067,7 +1125,7 @@ void hist_entry__delete(struct hist_entry *he) free_callchain(he->callchain); free(he->trace_output); free(he->raw_data); - free(he); + ops->free(he); } /* @@ -1081,7 +1139,7 @@ int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp, struct perf_hpp_fmt *fmt, int printed) { if (!list_is_last(&fmt->list, &he->hists->hpp_list->fields)) { - const int width = fmt->width(fmt, hpp, hists_to_evsel(he->hists)); + const int width = fmt->width(fmt, hpp, he->hists); if (printed < width) { advance_hpp(hpp, printed); printed = scnprintf(hpp->buf, hpp->size, "%-*s", width - printed, " "); @@ -2199,7 +2257,7 @@ size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp) struct perf_evsel *pos; size_t ret = 0; - evlist__for_each(evlist, pos) { + evlist__for_each_entry(evlist, pos) { ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos)); ret += events_stats__fprintf(&evsel__hists(pos)->stats, fp); } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 7b54ccf1b737..49aa4fac148f 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -10,6 +10,7 @@ #include "ui/progress.h" struct hist_entry; +struct hist_entry_ops; struct addr_location; struct symbol; @@ -120,13 +121,23 @@ extern const struct hist_iter_ops hist_iter_branch; extern const struct hist_iter_ops hist_iter_mem; extern const struct hist_iter_ops hist_iter_cumulative; -struct hist_entry *__hists__add_entry(struct hists *hists, - struct addr_location *al, - struct symbol *parent, - struct branch_info *bi, - struct mem_info *mi, - struct perf_sample *sample, - bool sample_self); +struct hist_entry *hists__add_entry(struct hists *hists, + struct addr_location *al, + struct symbol *parent, + struct branch_info *bi, + struct mem_info *mi, + struct perf_sample *sample, + bool sample_self); + +struct hist_entry *hists__add_entry_ops(struct hists *hists, + struct hist_entry_ops *ops, + struct addr_location *al, + struct symbol *sym_parent, + struct branch_info *bi, + struct mem_info *mi, + struct perf_sample *sample, + bool sample_self); + int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, int max_stack_depth, void *arg); @@ -159,7 +170,8 @@ void events_stats__inc(struct events_stats *stats, u32 type); size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, - int max_cols, float min_pcnt, FILE *fp); + int max_cols, float min_pcnt, FILE *fp, + bool use_callchain); size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp); void hists__filter_by_dso(struct hists *hists); @@ -214,9 +226,9 @@ struct perf_hpp { struct perf_hpp_fmt { const char *name; int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, - struct perf_evsel *evsel); + struct hists *hists); int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, - struct perf_evsel *evsel); + struct hists *hists); int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he); int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/perf/util/include/asm/alternative-asm.h deleted file mode 100644 index 3a3a0f16456a..000000000000 --- a/tools/perf/util/include/asm/alternative-asm.h +++ /dev/null @@ -1,9 +0,0 @@ -#ifndef _PERF_ASM_ALTERNATIVE_ASM_H -#define _PERF_ASM_ALTERNATIVE_ASM_H - -/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ - -#define altinstruction_entry # -#define ALTERNATIVE_2 # - -#endif diff --git a/tools/perf/util/include/asm/byteorder.h b/tools/perf/util/include/asm/byteorder.h deleted file mode 100644 index 2a9bdc066307..000000000000 --- a/tools/perf/util/include/asm/byteorder.h +++ /dev/null @@ -1,2 +0,0 @@ -#include <asm/types.h> -#include "../../../../include/uapi/linux/swab.h" diff --git a/tools/perf/util/include/asm/unistd_32.h b/tools/perf/util/include/asm/unistd_32.h deleted file mode 100644 index 8b137891791f..000000000000 --- a/tools/perf/util/include/asm/unistd_32.h +++ /dev/null @@ -1 +0,0 @@ - diff --git a/tools/perf/util/include/asm/unistd_64.h b/tools/perf/util/include/asm/unistd_64.h deleted file mode 100644 index 8b137891791f..000000000000 --- a/tools/perf/util/include/asm/unistd_64.h +++ /dev/null @@ -1 +0,0 @@ - diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h deleted file mode 100644 index c10a35e1afb8..000000000000 --- a/tools/perf/util/include/linux/const.h +++ /dev/null @@ -1 +0,0 @@ -#include "../../../../include/uapi/linux/const.h" diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index 9df996085563..749e6f2e37ca 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -422,7 +422,8 @@ static int intel_bts_get_branch_type(struct intel_bts_queue *btsq, } static int intel_bts_process_buffer(struct intel_bts_queue *btsq, - struct auxtrace_buffer *buffer) + struct auxtrace_buffer *buffer, + struct thread *thread) { struct branch *branch; size_t sz, bsz = sizeof(struct branch); @@ -444,6 +445,12 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq, if (!branch->from && !branch->to) continue; intel_bts_get_branch_type(btsq, branch); + if (btsq->bts->synth_opts.thread_stack) + thread_stack__event(thread, btsq->sample_flags, + le64_to_cpu(branch->from), + le64_to_cpu(branch->to), + btsq->intel_pt_insn.length, + buffer->buffer_nr + 1); if (filter && !(filter & btsq->sample_flags)) continue; err = intel_bts_synth_branch_sample(btsq, branch); @@ -507,12 +514,13 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp) goto out_put; } - if (!btsq->bts->synth_opts.callchain && thread && + if (!btsq->bts->synth_opts.callchain && + !btsq->bts->synth_opts.thread_stack && thread && (!old_buffer || btsq->bts->sampling_mode || (btsq->bts->snapshot_mode && !buffer->consecutive))) thread_stack__set_trace_nr(thread, buffer->buffer_nr + 1); - err = intel_bts_process_buffer(btsq, buffer); + err = intel_bts_process_buffer(btsq, buffer, thread); auxtrace_buffer__drop_data(buffer); @@ -777,7 +785,7 @@ static int intel_bts_synth_events(struct intel_bts *bts, u64 id; int err; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel->attr.type == bts->pmu_type && evsel->ids) { found = true; break; @@ -905,10 +913,14 @@ int intel_bts_process_auxtrace_info(union perf_event *event, if (dump_trace) return 0; - if (session->itrace_synth_opts && session->itrace_synth_opts->set) + if (session->itrace_synth_opts && session->itrace_synth_opts->set) { bts->synth_opts = *session->itrace_synth_opts; - else + } else { itrace_synth_opts__set_default(&bts->synth_opts); + if (session->itrace_synth_opts) + bts->synth_opts.thread_stack = + session->itrace_synth_opts->thread_stack; + } if (bts->synth_opts.calls) bts->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC | diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index 0611d619a42e..9b742ea8bfe8 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -7,8 +7,11 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table $(call rule_mkdir) @$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@ +# Busybox's diff doesn't have -I, avoid warning in the case + $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c - @(test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \ + @(diff -I 2>&1 | grep -q 'option requires an argument' && \ + test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \ diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null && \ diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null && \ diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \ diff --git a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk index 517567347aac..54e961659514 100644 --- a/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk +++ b/tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk @@ -72,12 +72,14 @@ BEGIN { lprefix_expr = "\\((66|F2|F3)\\)" max_lprefix = 4 - # All opcodes starting with lower-case 'v' or with (v1) superscript + # All opcodes starting with lower-case 'v', 'k' or with (v1) superscript # accepts VEX prefix - vexok_opcode_expr = "^v.*" + vexok_opcode_expr = "^[vk].*" vexok_expr = "\\(v1\\)" # All opcodes with (v) superscript supports *only* VEX prefix vexonly_expr = "\\(v\\)" + # All opcodes with (ev) superscript supports *only* EVEX prefix + evexonly_expr = "\\(ev\\)" prefix_expr = "\\(Prefix\\)" prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ" @@ -95,6 +97,7 @@ BEGIN { prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ" prefix_num["VEX+1byte"] = "INAT_PFX_VEX2" prefix_num["VEX+2byte"] = "INAT_PFX_VEX3" + prefix_num["EVEX"] = "INAT_PFX_EVEX" clear_vars() } @@ -319,7 +322,9 @@ function convert_operands(count,opnd, i,j,imm,mod) flags = add_flags(flags, "INAT_MODRM") # check VEX codes - if (match(ext, vexonly_expr)) + if (match(ext, evexonly_expr)) + flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY") + else if (match(ext, vexonly_expr)) flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY") else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr)) flags = add_flags(flags, "INAT_VEXOK") diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h index 611645e903a8..125ecd2a300d 100644 --- a/tools/perf/util/intel-pt-decoder/inat.h +++ b/tools/perf/util/intel-pt-decoder/inat.h @@ -48,6 +48,7 @@ /* AVX VEX prefixes */ #define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */ #define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */ +#define INAT_PFX_EVEX 15 /* EVEX prefix */ #define INAT_LSTPFX_MAX 3 #define INAT_LGCPFX_MAX 11 @@ -89,6 +90,7 @@ #define INAT_VARIANT (1 << (INAT_FLAG_OFFS + 4)) #define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5)) #define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6)) +#define INAT_EVEXONLY (1 << (INAT_FLAG_OFFS + 7)) /* Attribute making macros for attribute tables */ #define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS) #define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS) @@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr) static inline int inat_is_vex_prefix(insn_attr_t attr) { attr &= INAT_PFX_MASK; - return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3; + return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 || + attr == INAT_PFX_EVEX; +} + +static inline int inat_is_evex_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX; } static inline int inat_is_vex3_prefix(insn_attr_t attr) @@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr) static inline int inat_must_vex(insn_attr_t attr) { - return attr & INAT_VEXONLY; + return attr & (INAT_VEXONLY | INAT_EVEXONLY); +} + +static inline int inat_must_evex(insn_attr_t attr) +{ + return attr & INAT_EVEXONLY; } #endif diff --git a/tools/perf/util/intel-pt-decoder/insn.c b/tools/perf/util/intel-pt-decoder/insn.c index 9f26eae6c9f0..ca983e2bea8b 100644 --- a/tools/perf/util/intel-pt-decoder/insn.c +++ b/tools/perf/util/intel-pt-decoder/insn.c @@ -155,14 +155,24 @@ found: /* * In 32-bits mode, if the [7:6] bits (mod bits of * ModRM) on the second byte are not 11b, it is - * LDS or LES. + * LDS or LES or BOUND. */ if (X86_MODRM_MOD(b2) != 3) goto vex_end; } insn->vex_prefix.bytes[0] = b; insn->vex_prefix.bytes[1] = b2; - if (inat_is_vex3_prefix(attr)) { + if (inat_is_evex_prefix(attr)) { + b2 = peek_nbyte_next(insn_byte_t, insn, 2); + insn->vex_prefix.bytes[2] = b2; + b2 = peek_nbyte_next(insn_byte_t, insn, 3); + insn->vex_prefix.bytes[3] = b2; + insn->vex_prefix.nbytes = 4; + insn->next_byte += 4; + if (insn->x86_64 && X86_VEX_W(b2)) + /* VEX.W overrides opnd_size */ + insn->opnd_bytes = 8; + } else if (inat_is_vex3_prefix(attr)) { b2 = peek_nbyte_next(insn_byte_t, insn, 2); insn->vex_prefix.bytes[2] = b2; insn->vex_prefix.nbytes = 3; @@ -221,7 +231,9 @@ void insn_get_opcode(struct insn *insn) m = insn_vex_m_bits(insn); p = insn_vex_p_bits(insn); insn->attr = inat_get_avx_attribute(op, m, p); - if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr)) + if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) || + (!inat_accept_vex(insn->attr) && + !inat_is_group(insn->attr))) insn->attr = 0; /* This instruction is bad */ goto end; /* VEX has only 1 byte for opcode */ } diff --git a/tools/perf/util/intel-pt-decoder/insn.h b/tools/perf/util/intel-pt-decoder/insn.h index dd12da0f4593..e23578c7b1be 100644 --- a/tools/perf/util/intel-pt-decoder/insn.h +++ b/tools/perf/util/intel-pt-decoder/insn.h @@ -91,6 +91,7 @@ struct insn { #define X86_VEX_B(vex) ((vex) & 0x20) /* VEX3 Byte1 */ #define X86_VEX_L(vex) ((vex) & 0x04) /* VEX3 Byte2, VEX2 Byte1 */ /* VEX bit fields */ +#define X86_EVEX_M(vex) ((vex) & 0x03) /* EVEX Byte1 */ #define X86_VEX3_M(vex) ((vex) & 0x1f) /* VEX3 Byte1 */ #define X86_VEX2_M 1 /* VEX2.M always 1 */ #define X86_VEX_V(vex) (((vex) & 0x78) >> 3) /* VEX3 Byte2, VEX2 Byte1 */ @@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn) return (insn->vex_prefix.value != 0); } +static inline int insn_is_evex(struct insn *insn) +{ + if (!insn->prefixes.got) + insn_get_prefixes(insn); + return (insn->vex_prefix.nbytes == 4); +} + /* Ensure this instruction is decoded completely */ static inline int insn_complete(struct insn *insn) { @@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn) { if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */ return X86_VEX2_M; - else + else if (insn->vex_prefix.nbytes == 3) /* 3 bytes VEX */ return X86_VEX3_M(insn->vex_prefix.bytes[1]); + else /* EVEX */ + return X86_EVEX_M(insn->vex_prefix.bytes[1]); } static inline insn_byte_t insn_vex_p_bits(struct insn *insn) diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt index d388de72eaca..767be7c76034 100644 --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt +++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt @@ -13,12 +13,17 @@ # opcode: escape # escaped-name # EndTable # +# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix +# mnemonics that begin with lowercase 'k' accept a VEX prefix +# #<group maps> # GrpTable: GrpXXX # reg: mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...] # EndTable # # AVX Superscripts +# (ev): this opcode requires EVEX prefix. +# (evo): this opcode is changed by EVEX prefix (EVEX opcode) # (v): this opcode requires VEX prefix. # (v1): this opcode only supports 128bit VEX. # @@ -137,7 +142,7 @@ AVXcode: # 0x60 - 0x6f 60: PUSHA/PUSHAD (i64) 61: POPA/POPAD (i64) -62: BOUND Gv,Ma (i64) +62: BOUND Gv,Ma (i64) | EVEX (Prefix) 63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64) 64: SEG=FS (Prefix) 65: SEG=GS (Prefix) @@ -399,17 +404,17 @@ AVXcode: 1 3f: # 0x0f 0x40-0x4f 40: CMOVO Gv,Ev -41: CMOVNO Gv,Ev -42: CMOVB/C/NAE Gv,Ev +41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66) +42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66) 43: CMOVAE/NB/NC Gv,Ev -44: CMOVE/Z Gv,Ev -45: CMOVNE/NZ Gv,Ev -46: CMOVBE/NA Gv,Ev -47: CMOVA/NBE Gv,Ev +44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66) +45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66) +46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66) +47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66) 48: CMOVS Gv,Ev 49: CMOVNS Gv,Ev -4a: CMOVP/PE Gv,Ev -4b: CMOVNP/PO Gv,Ev +4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66) +4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk 4c: CMOVL/NGE Gv,Ev 4d: CMOVNL/GE Gv,Ev 4e: CMOVLE/NG Gv,Ev @@ -426,7 +431,7 @@ AVXcode: 1 58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1) 59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1) 5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1) -5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3) +5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3) 5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1) 5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1) 5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1) @@ -447,7 +452,7 @@ AVXcode: 1 6c: vpunpcklqdq Vx,Hx,Wx (66),(v1) 6d: vpunpckhqdq Vx,Hx,Wx (66),(v1) 6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1) -6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3) +6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev) # 0x0f 0x70-0x7f 70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1) 71: Grp12 (1A) @@ -458,14 +463,14 @@ AVXcode: 1 76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1) # Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX. 77: emms | vzeroupper | vzeroall -78: VMREAD Ey,Gy -79: VMWRITE Gy,Ey -7a: -7b: +78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev) +79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev) +7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev) +7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev) 7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2) 7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2) 7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1) -7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3) +7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev) # 0x0f 0x80-0x8f # Note: "forced64" is Intel CPU behavior (see comment about CALL insn). 80: JO Jz (f64) @@ -485,16 +490,16 @@ AVXcode: 1 8e: JLE/JNG Jz (f64) 8f: JNLE/JG Jz (f64) # 0x0f 0x90-0x9f -90: SETO Eb -91: SETNO Eb -92: SETB/C/NAE Eb -93: SETAE/NB/NC Eb +90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66) +91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66) +92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2) +93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2) 94: SETE/Z Eb 95: SETNE/NZ Eb 96: SETBE/NA Eb 97: SETA/NBE Eb -98: SETS Eb -99: SETNS Eb +98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66) +99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66) 9a: SETP/PE Eb 9b: SETNP/PO Eb 9c: SETL/NGE Eb @@ -564,11 +569,11 @@ d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1) d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1) d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1) da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1) -db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) +db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo) dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1) dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1) de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1) -df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) +df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo) # 0x0f 0xe0-0xef e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1) e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1) @@ -576,16 +581,16 @@ e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1) e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1) e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1) e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1) -e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2) +e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2) e7: movntq Mq,Pq | vmovntdq Mx,Vx (66) e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1) e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1) ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1) -eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) +eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo) ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1) ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1) ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1) -ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) +ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo) # 0x0f 0xf0-0xff f0: vlddqu Vx,Mx (F2) f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1) @@ -626,81 +631,105 @@ AVXcode: 2 0e: vtestps Vx,Wx (66),(v) 0f: vtestpd Vx,Wx (66),(v) # 0x0f 0x38 0x10-0x1f -10: pblendvb Vdq,Wdq (66) -11: -12: -13: vcvtph2ps Vx,Wx,Ib (66),(v) -14: blendvps Vdq,Wdq (66) -15: blendvpd Vdq,Wdq (66) -16: vpermps Vqq,Hqq,Wqq (66),(v) +10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev) +11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev) +12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev) +13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev) +14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo) +15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo) +16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo) 17: vptest Vx,Wx (66) 18: vbroadcastss Vx,Wd (66),(v) -19: vbroadcastsd Vqq,Wq (66),(v) -1a: vbroadcastf128 Vqq,Mdq (66),(v) -1b: +19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo) +1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo) +1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev) 1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1) 1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1) 1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1) -1f: +1f: vpabsq Vx,Wx (66),(ev) # 0x0f 0x38 0x20-0x2f -20: vpmovsxbw Vx,Ux/Mq (66),(v1) -21: vpmovsxbd Vx,Ux/Md (66),(v1) -22: vpmovsxbq Vx,Ux/Mw (66),(v1) -23: vpmovsxwd Vx,Ux/Mq (66),(v1) -24: vpmovsxwq Vx,Ux/Md (66),(v1) -25: vpmovsxdq Vx,Ux/Mq (66),(v1) -26: -27: -28: vpmuldq Vx,Hx,Wx (66),(v1) -29: vpcmpeqq Vx,Hx,Wx (66),(v1) -2a: vmovntdqa Vx,Mx (66),(v1) +20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev) +21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev) +22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev) +23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev) +24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev) +25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev) +26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev) +27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev) +28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev) +29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev) +2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev) 2b: vpackusdw Vx,Hx,Wx (66),(v1) -2c: vmaskmovps Vx,Hx,Mx (66),(v) -2d: vmaskmovpd Vx,Hx,Mx (66),(v) +2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo) +2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo) 2e: vmaskmovps Mx,Hx,Vx (66),(v) 2f: vmaskmovpd Mx,Hx,Vx (66),(v) # 0x0f 0x38 0x30-0x3f -30: vpmovzxbw Vx,Ux/Mq (66),(v1) -31: vpmovzxbd Vx,Ux/Md (66),(v1) -32: vpmovzxbq Vx,Ux/Mw (66),(v1) -33: vpmovzxwd Vx,Ux/Mq (66),(v1) -34: vpmovzxwq Vx,Ux/Md (66),(v1) -35: vpmovzxdq Vx,Ux/Mq (66),(v1) -36: vpermd Vqq,Hqq,Wqq (66),(v) +30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev) +31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev) +32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev) +33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev) +34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev) +35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev) +36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo) 37: vpcmpgtq Vx,Hx,Wx (66),(v1) -38: vpminsb Vx,Hx,Wx (66),(v1) -39: vpminsd Vx,Hx,Wx (66),(v1) -3a: vpminuw Vx,Hx,Wx (66),(v1) -3b: vpminud Vx,Hx,Wx (66),(v1) +38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev) +39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev) +3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev) +3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo) 3c: vpmaxsb Vx,Hx,Wx (66),(v1) -3d: vpmaxsd Vx,Hx,Wx (66),(v1) +3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo) 3e: vpmaxuw Vx,Hx,Wx (66),(v1) -3f: vpmaxud Vx,Hx,Wx (66),(v1) +3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo) # 0x0f 0x38 0x40-0x8f -40: vpmulld Vx,Hx,Wx (66),(v1) +40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo) 41: vphminposuw Vdq,Wdq (66),(v1) -42: -43: -44: +42: vgetexpps/d Vx,Wx (66),(ev) +43: vgetexpss/d Vx,Hx,Wx (66),(ev) +44: vplzcntd/q Vx,Wx (66),(ev) 45: vpsrlvd/q Vx,Hx,Wx (66),(v) -46: vpsravd Vx,Hx,Wx (66),(v) +46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo) 47: vpsllvd/q Vx,Hx,Wx (66),(v) -# Skip 0x48-0x57 +# Skip 0x48-0x4b +4c: vrcp14ps/d Vpd,Wpd (66),(ev) +4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev) +4e: vrsqrt14ps/d Vpd,Wpd (66),(ev) +4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev) +# Skip 0x50-0x57 58: vpbroadcastd Vx,Wx (66),(v) -59: vpbroadcastq Vx,Wx (66),(v) -5a: vbroadcasti128 Vqq,Mdq (66),(v) -# Skip 0x5b-0x77 +59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo) +5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo) +5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev) +# Skip 0x5c-0x63 +64: vpblendmd/q Vx,Hx,Wx (66),(ev) +65: vblendmps/d Vx,Hx,Wx (66),(ev) +66: vpblendmb/w Vx,Hx,Wx (66),(ev) +# Skip 0x67-0x74 +75: vpermi2b/w Vx,Hx,Wx (66),(ev) +76: vpermi2d/q Vx,Hx,Wx (66),(ev) +77: vpermi2ps/d Vx,Hx,Wx (66),(ev) 78: vpbroadcastb Vx,Wx (66),(v) 79: vpbroadcastw Vx,Wx (66),(v) -# Skip 0x7a-0x7f +7a: vpbroadcastb Vx,Rv (66),(ev) +7b: vpbroadcastw Vx,Rv (66),(ev) +7c: vpbroadcastd/q Vx,Rv (66),(ev) +7d: vpermt2b/w Vx,Hx,Wx (66),(ev) +7e: vpermt2d/q Vx,Hx,Wx (66),(ev) +7f: vpermt2ps/d Vx,Hx,Wx (66),(ev) 80: INVEPT Gy,Mdq (66) 81: INVPID Gy,Mdq (66) 82: INVPCID Gy,Mdq (66) +83: vpmultishiftqb Vx,Hx,Wx (66),(ev) +88: vexpandps/d Vpd,Wpd (66),(ev) +89: vpexpandd/q Vx,Wx (66),(ev) +8a: vcompressps/d Wx,Vx (66),(ev) +8b: vpcompressd/q Wx,Vx (66),(ev) 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v) +8d: vpermb/w Vx,Hx,Wx (66),(ev) 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v) # 0x0f 0x38 0x90-0xbf (FMA) -90: vgatherdd/q Vx,Hx,Wx (66),(v) -91: vgatherqd/q Vx,Hx,Wx (66),(v) +90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo) +91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo) 92: vgatherdps/d Vx,Hx,Wx (66),(v) 93: vgatherqps/d Vx,Hx,Wx (66),(v) 94: @@ -715,6 +744,10 @@ AVXcode: 2 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1) 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v) 9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1) +a0: vpscatterdd/q Wx,Vx (66),(ev) +a1: vpscatterqd/q Wx,Vx (66),(ev) +a2: vscatterdps/d Wx,Vx (66),(ev) +a3: vscatterqps/d Wx,Vx (66),(ev) a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v) a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v) a8: vfmadd213ps/d Vx,Hx,Wx (66),(v) @@ -725,6 +758,8 @@ ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v) ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1) ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v) af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1) +b4: vpmadd52luq Vx,Hx,Wx (66),(ev) +b5: vpmadd52huq Vx,Hx,Wx (66),(ev) b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v) b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v) b8: vfmadd231ps/d Vx,Hx,Wx (66),(v) @@ -736,12 +771,15 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1) be: vfnmsub231ps/d Vx,Hx,Wx (66),(v) bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1) # 0x0f 0x38 0xc0-0xff -c8: sha1nexte Vdq,Wdq +c4: vpconflictd/q Vx,Wx (66),(ev) +c6: Grp18 (1A) +c7: Grp19 (1A) +c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev) c9: sha1msg1 Vdq,Wdq -ca: sha1msg2 Vdq,Wdq -cb: sha256rnds2 Vdq,Wdq -cc: sha256msg1 Vdq,Wdq -cd: sha256msg2 Vdq,Wdq +ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev) +cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev) +cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev) +cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev) db: VAESIMC Vdq,Wdq (66),(v1) dc: VAESENC Vdq,Hdq,Wdq (66),(v1) dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1) @@ -763,15 +801,15 @@ AVXcode: 3 00: vpermq Vqq,Wqq,Ib (66),(v) 01: vpermpd Vqq,Wqq,Ib (66),(v) 02: vpblendd Vx,Hx,Wx,Ib (66),(v) -03: +03: valignd/q Vx,Hx,Wx,Ib (66),(ev) 04: vpermilps Vx,Wx,Ib (66),(v) 05: vpermilpd Vx,Wx,Ib (66),(v) 06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v) 07: -08: vroundps Vx,Wx,Ib (66) -09: vroundpd Vx,Wx,Ib (66) -0a: vroundss Vss,Wss,Ib (66),(v1) -0b: vroundsd Vsd,Wsd,Ib (66),(v1) +08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo) +09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo) +0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo) +0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo) 0c: vblendps Vx,Hx,Wx,Ib (66) 0d: vblendpd Vx,Hx,Wx,Ib (66) 0e: vpblendw Vx,Hx,Wx,Ib (66),(v1) @@ -780,26 +818,51 @@ AVXcode: 3 15: vpextrw Rd/Mw,Vdq,Ib (66),(v1) 16: vpextrd/q Ey,Vdq,Ib (66),(v1) 17: vextractps Ed,Vdq,Ib (66),(v1) -18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) -19: vextractf128 Wdq,Vqq,Ib (66),(v) +18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo) +19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo) +1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev) +1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev) 1d: vcvtps2ph Wx,Vx,Ib (66),(v) +1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev) +1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev) 20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1) 21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1) 22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1) -38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) -39: vextracti128 Wdq,Vqq,Ib (66),(v) +23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) +25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev) +26: vgetmantps/d Vx,Wx,Ib (66),(ev) +27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev) +30: kshiftrb/w Vk,Uk,Ib (66),(v) +31: kshiftrd/q Vk,Uk,Ib (66),(v) +32: kshiftlb/w Vk,Uk,Ib (66),(v) +33: kshiftld/q Vk,Uk,Ib (66),(v) +38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo) +39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo) +3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev) +3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev) +3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev) +3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev) 40: vdpps Vx,Hx,Wx,Ib (66) 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1) -42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) +42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo) +43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev) 44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1) 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v) 4a: vblendvps Vx,Hx,Wx,Lx (66),(v) 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v) 4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1) +50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev) +51: vrangess/d Vx,Hx,Wx,Ib (66),(ev) +54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev) +55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev) +56: vreduceps/d Vx,Wx,Ib (66),(ev) +57: vreducess/d Vx,Hx,Wx,Ib (66),(ev) 60: vpcmpestrm Vdq,Wdq,Ib (66),(v1) 61: vpcmpestri Vdq,Wdq,Ib (66),(v1) 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1) 63: vpcmpistri Vdq,Wdq,Ib (66),(v1) +66: vfpclassps/d Vk,Wx,Ib (66),(ev) +67: vfpclassss/d Vk,Wx,Ib (66),(ev) cc: sha1rnds4 Vdq,Wdq,Ib df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1) f0: RORX Gy,Ey,Ib (F2),(v) @@ -927,8 +990,10 @@ GrpTable: Grp12 EndTable GrpTable: Grp13 +0: vprord/q Hx,Wx,Ib (66),(ev) +1: vprold/q Hx,Wx,Ib (66),(ev) 2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1) -4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) +4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo) 6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1) EndTable @@ -947,7 +1012,7 @@ GrpTable: Grp15 4: XSAVE 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) -7: clflush | clflushopt (66) | sfence (11B) | pcommit (66),(11B) +7: clflush | clflushopt (66) | sfence (11B) EndTable GrpTable: Grp16 @@ -963,6 +1028,20 @@ GrpTable: Grp17 3: BLSI By,Ey (v) EndTable +GrpTable: Grp18 +1: vgatherpf0dps/d Wx (66),(ev) +2: vgatherpf1dps/d Wx (66),(ev) +5: vscatterpf0dps/d Wx (66),(ev) +6: vscatterpf1dps/d Wx (66),(ev) +EndTable + +GrpTable: Grp19 +1: vgatherpf0qps/d Wx (66),(ev) +2: vgatherpf1qps/d Wx (66),(ev) +5: vscatterpf0qps/d Wx (66),(ev) +6: vscatterpf1qps/d Wx (66),(ev) +EndTable + # AMD's Prefetch Group GrpTable: GrpP 0: PREFETCH diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 137196990012..551ff6f640be 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -39,6 +39,7 @@ #include "auxtrace.h" #include "tsc.h" #include "intel-pt.h" +#include "config.h" #include "intel-pt-decoder/intel-pt-log.h" #include "intel-pt-decoder/intel-pt-decoder.h" @@ -556,7 +557,7 @@ static bool intel_pt_exclude_kernel(struct intel_pt *pt) { struct perf_evsel *evsel; - evlist__for_each(pt->session->evlist, evsel) { + evlist__for_each_entry(pt->session->evlist, evsel) { if (intel_pt_get_config(pt, &evsel->attr, NULL) && !evsel->attr.exclude_kernel) return false; @@ -572,7 +573,7 @@ static bool intel_pt_return_compression(struct intel_pt *pt) if (!pt->noretcomp_bit) return true; - evlist__for_each(pt->session->evlist, evsel) { + evlist__for_each_entry(pt->session->evlist, evsel) { if (intel_pt_get_config(pt, &evsel->attr, &config) && (config & pt->noretcomp_bit)) return false; @@ -592,7 +593,7 @@ static unsigned int intel_pt_mtc_period(struct intel_pt *pt) for (shift = 0, config = pt->mtc_freq_bits; !(config & 1); shift++) config >>= 1; - evlist__for_each(pt->session->evlist, evsel) { + evlist__for_each_entry(pt->session->evlist, evsel) { if (intel_pt_get_config(pt, &evsel->attr, &config)) return (config & pt->mtc_freq_bits) >> shift; } @@ -608,7 +609,7 @@ static bool intel_pt_timeless_decoding(struct intel_pt *pt) if (!pt->tsc_bit || !pt->cap_user_time_zero) return true; - evlist__for_each(pt->session->evlist, evsel) { + evlist__for_each_entry(pt->session->evlist, evsel) { if (!(evsel->attr.sample_type & PERF_SAMPLE_TIME)) return true; if (intel_pt_get_config(pt, &evsel->attr, &config)) { @@ -625,7 +626,7 @@ static bool intel_pt_tracing_kernel(struct intel_pt *pt) { struct perf_evsel *evsel; - evlist__for_each(pt->session->evlist, evsel) { + evlist__for_each_entry(pt->session->evlist, evsel) { if (intel_pt_get_config(pt, &evsel->attr, NULL) && !evsel->attr.exclude_kernel) return true; @@ -642,7 +643,7 @@ static bool intel_pt_have_tsc(struct intel_pt *pt) if (!pt->tsc_bit) return false; - evlist__for_each(pt->session->evlist, evsel) { + evlist__for_each_entry(pt->session->evlist, evsel) { if (intel_pt_get_config(pt, &evsel->attr, &config)) { if (config & pt->tsc_bit) have_tsc = true; @@ -1233,7 +1234,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) if (!(state->type & INTEL_PT_BRANCH)) return 0; - if (pt->synth_opts.callchain) + if (pt->synth_opts.callchain || pt->synth_opts.thread_stack) thread_stack__event(ptq->thread, ptq->flags, state->from_ip, state->to_ip, ptq->insn_len, state->trace_nr); @@ -1850,7 +1851,7 @@ static int intel_pt_synth_events(struct intel_pt *pt, u64 id; int err; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel->attr.type == pt->pmu_type && evsel->ids) { found = true; break; @@ -1930,7 +1931,7 @@ static int intel_pt_synth_events(struct intel_pt *pt, pt->sample_transactions = true; pt->transactions_id = id; id += 1; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel->id && evsel->id[0] == pt->transactions_id) { if (evsel->name) zfree(&evsel->name); @@ -1968,7 +1969,7 @@ static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist) { struct perf_evsel *evsel; - evlist__for_each_reverse(evlist, evsel) { + evlist__for_each_entry_reverse(evlist, evsel) { const char *name = perf_evsel__name(evsel); if (!strcmp(name, "sched:sched_switch")) @@ -1982,7 +1983,7 @@ static bool intel_pt_find_switch(struct perf_evlist *evlist) { struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel->attr.context_switch) return true; } @@ -2136,6 +2137,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event, pt->synth_opts.branches = false; pt->synth_opts.callchain = true; } + if (session->itrace_synth_opts) + pt->synth_opts.thread_stack = + session->itrace_synth_opts->thread_stack; } if (pt->synth_opts.log) diff --git a/tools/perf/util/intlist.h b/tools/perf/util/intlist.h index aa6877d36858..020b9ca1b47e 100644 --- a/tools/perf/util/intlist.h +++ b/tools/perf/util/intlist.h @@ -57,21 +57,21 @@ static inline struct int_node *intlist__next(struct int_node *in) } /** - * intlist_for_each - iterate over a intlist + * intlist__for_each_entry - iterate over a intlist * @pos: the &struct int_node to use as a loop cursor. * @ilist: the &struct intlist for loop. */ -#define intlist__for_each(pos, ilist) \ +#define intlist__for_each_entry(pos, ilist) \ for (pos = intlist__first(ilist); pos; pos = intlist__next(pos)) /** - * intlist_for_each_safe - iterate over a intlist safe against removal of + * intlist__for_each_entry_safe - iterate over a intlist safe against removal of * int_node * @pos: the &struct int_node to use as a loop cursor. * @n: another &struct int_node to use as temporary storage. * @ilist: the &struct intlist for loop. */ -#define intlist__for_each_safe(pos, n, ilist) \ +#define intlist__for_each_entry_safe(pos, n, ilist) \ for (pos = intlist__first(ilist), n = intlist__next(pos); pos;\ pos = n, n = intlist__next(n)) #endif /* __PERF_INTLIST_H */ diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 86afe9618bb0..9f3305f6b6d5 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -108,7 +108,7 @@ jit_validate_events(struct perf_session *session) /* * check that all events use CLOCK_MONOTONIC */ - evlist__for_each(session->evlist, evsel) { + evlist__for_each_entry(session->evlist, evsel) { if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC) return -1; } diff --git a/tools/perf/util/levenshtein.c b/tools/perf/util/levenshtein.c index e521d1516df6..f616e4f65b67 100644 --- a/tools/perf/util/levenshtein.c +++ b/tools/perf/util/levenshtein.c @@ -1,5 +1,7 @@ -#include "cache.h" #include "levenshtein.h" +#include <errno.h> +#include <stdlib.h> +#include <string.h> /* * This function implements the Damerau-Levenshtein algorithm to diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c new file mode 100644 index 000000000000..6559bc586643 --- /dev/null +++ b/tools/perf/util/libunwind/arm64.c @@ -0,0 +1,40 @@ +/* + * This file setups defines to compile arch specific binary from the + * generic one. + * + * The function 'LIBUNWIND__ARCH_REG_ID' name is set according to arch + * name and the defination of this function is included directly from + * 'arch/arm64/util/unwind-libunwind.c', to make sure that this function + * is defined no matter what arch the host is. + * + * Finally, the arch specific unwind methods are exported which will + * be assigned to each arm64 thread. + */ + +#define REMOTE_UNWIND_LIBUNWIND + +/* Define arch specific functions & regs for libunwind, should be + * defined before including "unwind.h" + */ +#define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arm64_reg_id(regnum) +#define LIBUNWIND__ARCH_REG_IP PERF_REG_ARM64_PC +#define LIBUNWIND__ARCH_REG_SP PERF_REG_ARM64_SP + +#include "unwind.h" +#include "debug.h" +#include "libunwind-aarch64.h" +#include <../../../../arch/arm64/include/uapi/asm/perf_regs.h> +#include "../../arch/arm64/util/unwind-libunwind.c" + +/* NO_LIBUNWIND_DEBUG_FRAME is a feature flag for local libunwind, + * assign NO_LIBUNWIND_DEBUG_FRAME_AARCH64 to it for compiling arm64 + * unwind methods. + */ +#undef NO_LIBUNWIND_DEBUG_FRAME +#ifdef NO_LIBUNWIND_DEBUG_FRAME_AARCH64 +#define NO_LIBUNWIND_DEBUG_FRAME +#endif +#include "util/unwind-libunwind-local.c" + +struct unwind_libunwind_ops * +arm64_unwind_libunwind_ops = &_unwind_libunwind_ops; diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c new file mode 100644 index 000000000000..957ffff72428 --- /dev/null +++ b/tools/perf/util/libunwind/x86_32.c @@ -0,0 +1,43 @@ +/* + * This file setups defines to compile arch specific binary from the + * generic one. + * + * The function 'LIBUNWIND__ARCH_REG_ID' name is set according to arch + * name and the defination of this function is included directly from + * 'arch/x86/util/unwind-libunwind.c', to make sure that this function + * is defined no matter what arch the host is. + * + * Finally, the arch specific unwind methods are exported which will + * be assigned to each x86 thread. + */ + +#define REMOTE_UNWIND_LIBUNWIND + +/* Define arch specific functions & regs for libunwind, should be + * defined before including "unwind.h" + */ +#define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__x86_reg_id(regnum) +#define LIBUNWIND__ARCH_REG_IP PERF_REG_X86_IP +#define LIBUNWIND__ARCH_REG_SP PERF_REG_X86_SP + +#include "unwind.h" +#include "debug.h" +#include "libunwind-x86.h" +#include <../../../../arch/x86/include/uapi/asm/perf_regs.h> + +/* HAVE_ARCH_X86_64_SUPPORT is used in'arch/x86/util/unwind-libunwind.c' + * for x86_32, we undef it to compile code for x86_32 only. + */ +#undef HAVE_ARCH_X86_64_SUPPORT +#include "../../arch/x86/util/unwind-libunwind.c" + +/* Explicitly define NO_LIBUNWIND_DEBUG_FRAME, because non-ARM has no + * dwarf_find_debug_frame() function. + */ +#ifndef NO_LIBUNWIND_DEBUG_FRAME +#define NO_LIBUNWIND_DEBUG_FRAME +#endif +#include "util/unwind-libunwind-local.c" + +struct unwind_libunwind_ops * +x86_32_unwind_libunwind_ops = &_unwind_libunwind_ops; diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index 33071d6159bc..bf7216b8731d 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -3,11 +3,14 @@ * Copyright (C) 2015, Huawei Inc. */ +#include <errno.h> #include <limits.h> #include <stdio.h> #include <stdlib.h> #include "debug.h" #include "llvm-utils.h" +#include "config.h" +#include "util.h" #define CLANG_BPF_CMD_DEFAULT_TEMPLATE \ "$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\ @@ -42,6 +45,8 @@ int perf_llvm_config(const char *var, const char *value) llvm_param.kbuild_dir = strdup(value); else if (!strcmp(var, "kbuild-opts")) llvm_param.kbuild_opts = strdup(value); + else if (!strcmp(var, "dump-obj")) + llvm_param.dump_obj = !!perf_config_bool(var, value); else return -1; llvm_param.user_set_param = true; @@ -103,7 +108,7 @@ read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz) file = popen(cmd, "r"); if (!file) { pr_err("ERROR: unable to popen cmd: %s\n", - strerror_r(errno, serr, sizeof(serr))); + str_error_r(errno, serr, sizeof(serr))); return -EINVAL; } @@ -137,7 +142,7 @@ read_from_pipe(const char *cmd, void **p_buf, size_t *p_read_sz) if (ferror(file)) { pr_err("ERROR: error occurred when reading from pipe: %s\n", - strerror_r(errno, serr, sizeof(serr))); + str_error_r(errno, serr, sizeof(serr))); err = -EIO; goto errout; } @@ -326,6 +331,42 @@ get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts) pr_debug("include option is set to %s\n", *kbuild_include_opts); } +static void +dump_obj(const char *path, void *obj_buf, size_t size) +{ + char *obj_path = strdup(path); + FILE *fp; + char *p; + + if (!obj_path) { + pr_warning("WARNING: No enough memory, skip object dumping\n"); + return; + } + + p = strrchr(obj_path, '.'); + if (!p || (strcmp(p, ".c") != 0)) { + pr_warning("WARNING: invalid llvm source path: '%s', skip object dumping\n", + obj_path); + goto out; + } + + p[1] = 'o'; + fp = fopen(obj_path, "wb"); + if (!fp) { + pr_warning("WARNING: failed to open '%s': %s, skip object dumping\n", + obj_path, strerror(errno)); + goto out; + } + + pr_info("LLVM: dumping %s\n", obj_path); + if (fwrite(obj_buf, size, 1, fp) != 1) + pr_warning("WARNING: failed to write to file '%s': %s, skip object dumping\n", + obj_path, strerror(errno)); + fclose(fp); +out: + free(obj_path); +} + int llvm__compile_bpf(const char *path, void **p_obj_buf, size_t *p_obj_buf_sz) { @@ -343,7 +384,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, if (path[0] != '-' && realpath(path, abspath) == NULL) { err = errno; pr_err("ERROR: problems with path %s: %s\n", - path, strerror_r(err, serr, sizeof(serr))); + path, str_error_r(err, serr, sizeof(serr))); return -err; } @@ -371,7 +412,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, if (nr_cpus_avail <= 0) { pr_err( "WARNING:\tunable to get available CPUs in this system: %s\n" -" \tUse 128 instead.\n", strerror_r(errno, serr, sizeof(serr))); +" \tUse 128 instead.\n", str_error_r(errno, serr, sizeof(serr))); nr_cpus_avail = 128; } snprintf(nr_cpus_avail_str, sizeof(nr_cpus_avail_str), "%d", @@ -411,6 +452,10 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, free(kbuild_dir); free(kbuild_include_opts); + + if (llvm_param.dump_obj) + dump_obj(path, obj_buf, obj_buf_sz); + if (!p_obj_buf) free(obj_buf); else diff --git a/tools/perf/util/llvm-utils.h b/tools/perf/util/llvm-utils.h index 23b9a743fe72..9f501cef06a1 100644 --- a/tools/perf/util/llvm-utils.h +++ b/tools/perf/util/llvm-utils.h @@ -30,6 +30,11 @@ struct llvm_param { */ const char *kbuild_opts; /* + * Default is false. If set to true, write compiling result + * to object file. + */ + bool dump_obj; + /* * Default is false. If one of the above fields is set by user * explicitly then user_set_llvm is set to true. This is used * for perf test. If user doesn't set anything in .perfconfig diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b1772180c820..bc2cdbd09a25 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -138,8 +138,10 @@ void machine__exit(struct machine *machine) void machine__delete(struct machine *machine) { - machine__exit(machine); - free(machine); + if (machine) { + machine__exit(machine); + free(machine); + } } void machines__init(struct machines *machines) @@ -1353,11 +1355,16 @@ int machine__process_mmap2_event(struct machine *machine, if (map == NULL) goto out_problem_map; - thread__insert_map(thread, map); + ret = thread__insert_map(thread, map); + if (ret) + goto out_problem_insert; + thread__put(thread); map__put(map); return 0; +out_problem_insert: + map__put(map); out_problem_map: thread__put(thread); out_problem: @@ -1403,11 +1410,16 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event if (map == NULL) goto out_problem_map; - thread__insert_map(thread, map); + ret = thread__insert_map(thread, map); + if (ret) + goto out_problem_insert; + thread__put(thread); map__put(map); return 0; +out_problem_insert: + map__put(map); out_problem_map: thread__put(thread); out_problem: diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index b19bcd3b7128..728129ac653a 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -15,6 +15,7 @@ #include "debug.h" #include "machine.h" #include <linux/string.h> +#include "unwind.h" static void __maps__insert(struct maps *maps, struct map *map); @@ -311,6 +312,9 @@ int map__load(struct map *map, symbol_filter_t filter) pr_warning("%.*s was updated (is prelink enabled?). " "Restart the long running apps that use it!\n", (int)real_len, name); + } else if (filter) { + pr_warning("no symbols passed the given filter.\n"); + return -2; /* Empty but maybe by the filter */ } else { pr_warning("no symbols found in %s, maybe install " "a debug package?\n", name); @@ -744,9 +748,10 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map, /* * XXX This should not really _copy_ te maps, but refcount them. */ -int map_groups__clone(struct map_groups *mg, +int map_groups__clone(struct thread *thread, struct map_groups *parent, enum map_type type) { + struct map_groups *mg = thread->mg; int err = -ENOMEM; struct map *map; struct maps *maps = &parent->maps[type]; @@ -757,6 +762,11 @@ int map_groups__clone(struct map_groups *mg, struct map *new = map__clone(map); if (new == NULL) goto out_unlock; + + err = unwind__prepare_access(thread, new, NULL); + if (err) + goto out_unlock; + map_groups__insert(mg, new); map__put(new); } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 7309d64ce39e..d83396ceecba 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -194,7 +194,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp, symbol_filter_t filter); void map_groups__init(struct map_groups *mg, struct machine *machine); void map_groups__exit(struct map_groups *mg); -int map_groups__clone(struct map_groups *mg, +int map_groups__clone(struct thread *thread, struct map_groups *parent, enum map_type type); size_t map_groups__fprintf(struct map_groups *mg, FILE *fp); diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 75465f89a413..bbc368e7d1e4 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -10,18 +10,33 @@ #include "debug.h" #include "symbol.h" +unsigned int perf_mem_events__loads_ldlat = 30; + #define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s } struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { - E("ldlat-loads", "cpu/mem-loads,ldlat=30/P", "mem-loads"), + E("ldlat-loads", "cpu/mem-loads,ldlat=%u/P", "mem-loads"), E("ldlat-stores", "cpu/mem-stores/P", "mem-stores"), }; #undef E #undef E +static char mem_loads_name[100]; +static bool mem_loads_name__init; + char *perf_mem_events__name(int i) { + if (i == PERF_MEM_EVENTS__LOAD) { + if (!mem_loads_name__init) { + mem_loads_name__init = true; + scnprintf(mem_loads_name, sizeof(mem_loads_name), + perf_mem_events[i].name, + perf_mem_events__loads_ldlat); + } + return mem_loads_name; + } + return (char *)perf_mem_events[i].name; } diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h index 5d6d93066a6e..7f69bf9d789d 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -18,6 +18,7 @@ enum { }; extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX]; +extern unsigned int perf_mem_events__loads_ldlat; int perf_mem_events__parse(const char *str); int perf_mem_events__init(void); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index c6fd0479f4cd..6c913c3914fb 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -20,6 +20,7 @@ #include "pmu.h" #include "thread_map.h" #include "cpumap.h" +#include "probe-file.h" #include "asm/bug.h" #define MAX_NAME_LEN 100 @@ -436,7 +437,7 @@ int parse_events_add_cache(struct list_head *list, int *idx, } static void tracepoint_error(struct parse_events_error *e, int err, - char *sys, char *name) + const char *sys, const char *name) { char help[BUFSIZ]; @@ -466,7 +467,7 @@ static void tracepoint_error(struct parse_events_error *e, int err, } static int add_tracepoint(struct list_head *list, int *idx, - char *sys_name, char *evt_name, + const char *sys_name, const char *evt_name, struct parse_events_error *err, struct list_head *head_config) { @@ -491,7 +492,7 @@ static int add_tracepoint(struct list_head *list, int *idx, } static int add_tracepoint_multi_event(struct list_head *list, int *idx, - char *sys_name, char *evt_name, + const char *sys_name, const char *evt_name, struct parse_events_error *err, struct list_head *head_config) { @@ -533,7 +534,7 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx, } static int add_tracepoint_event(struct list_head *list, int *idx, - char *sys_name, char *evt_name, + const char *sys_name, const char *evt_name, struct parse_events_error *err, struct list_head *head_config) { @@ -545,7 +546,7 @@ static int add_tracepoint_event(struct list_head *list, int *idx, } static int add_tracepoint_multi_sys(struct list_head *list, int *idx, - char *sys_name, char *evt_name, + const char *sys_name, const char *evt_name, struct parse_events_error *err, struct list_head *head_config) { @@ -584,7 +585,7 @@ struct __add_bpf_event_param { struct list_head *head_config; }; -static int add_bpf_event(struct probe_trace_event *tev, int fd, +static int add_bpf_event(const char *group, const char *event, int fd, void *_param) { LIST_HEAD(new_evsels); @@ -595,27 +596,27 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd, int err; pr_debug("add bpf event %s:%s and attach bpf program %d\n", - tev->group, tev->event, fd); + group, event, fd); - err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, tev->group, - tev->event, evlist->error, + err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, group, + event, evlist->error, param->head_config); if (err) { struct perf_evsel *evsel, *tmp; pr_debug("Failed to add BPF event %s:%s\n", - tev->group, tev->event); + group, event); list_for_each_entry_safe(evsel, tmp, &new_evsels, node) { list_del(&evsel->node); perf_evsel__delete(evsel); } return err; } - pr_debug("adding %s:%s\n", tev->group, tev->event); + pr_debug("adding %s:%s\n", group, event); list_for_each_entry(pos, &new_evsels, node) { pr_debug("adding %s:%s to %p\n", - tev->group, tev->event, pos); + group, event, pos); pos->bpf_fd = fd; } list_splice(&new_evsels, list); @@ -661,7 +662,7 @@ int parse_events_load_bpf_obj(struct parse_events_evlist *data, goto errout; } - err = bpf__foreach_tev(obj, add_bpf_event, ¶m); + err = bpf__foreach_event(obj, add_bpf_event, ¶m); if (err) { snprintf(errbuf, sizeof(errbuf), "Attach events in BPF object failed"); @@ -900,6 +901,9 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = { [PARSE_EVENTS__TERM_TYPE_STACKSIZE] = "stack-size", [PARSE_EVENTS__TERM_TYPE_NOINHERIT] = "no-inherit", [PARSE_EVENTS__TERM_TYPE_INHERIT] = "inherit", + [PARSE_EVENTS__TERM_TYPE_MAX_STACK] = "max-stack", + [PARSE_EVENTS__TERM_TYPE_OVERWRITE] = "overwrite", + [PARSE_EVENTS__TERM_TYPE_NOOVERWRITE] = "no-overwrite", }; static bool config_term_shrinked; @@ -992,9 +996,18 @@ do { \ case PARSE_EVENTS__TERM_TYPE_NOINHERIT: CHECK_TYPE_VAL(NUM); break; + case PARSE_EVENTS__TERM_TYPE_OVERWRITE: + CHECK_TYPE_VAL(NUM); + break; + case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: + CHECK_TYPE_VAL(NUM); + break; case PARSE_EVENTS__TERM_TYPE_NAME: CHECK_TYPE_VAL(STR); break; + case PARSE_EVENTS__TERM_TYPE_MAX_STACK: + CHECK_TYPE_VAL(NUM); + break; default: err->str = strdup("unknown term"); err->idx = term->err_term; @@ -1040,6 +1053,9 @@ static int config_term_tracepoint(struct perf_event_attr *attr, case PARSE_EVENTS__TERM_TYPE_STACKSIZE: case PARSE_EVENTS__TERM_TYPE_INHERIT: case PARSE_EVENTS__TERM_TYPE_NOINHERIT: + case PARSE_EVENTS__TERM_TYPE_MAX_STACK: + case PARSE_EVENTS__TERM_TYPE_OVERWRITE: + case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: return config_term_common(attr, term, err); default: if (err) { @@ -1109,6 +1125,15 @@ do { \ case PARSE_EVENTS__TERM_TYPE_NOINHERIT: ADD_CONFIG_TERM(INHERIT, inherit, term->val.num ? 0 : 1); break; + case PARSE_EVENTS__TERM_TYPE_MAX_STACK: + ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num); + break; + case PARSE_EVENTS__TERM_TYPE_OVERWRITE: + ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 1 : 0); + break; + case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: + ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 0 : 1); + break; default: break; } @@ -1118,7 +1143,7 @@ do { \ } int parse_events_add_tracepoint(struct list_head *list, int *idx, - char *sys, char *event, + const char *sys, const char *event, struct parse_events_error *err, struct list_head *head_config) { @@ -1388,7 +1413,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) if (!add && get_event_modifier(&mod, str, NULL)) return -EINVAL; - __evlist__for_each(list, evsel) { + __evlist__for_each_entry(list, evsel) { if (add && get_event_modifier(&mod, str, evsel)) return -EINVAL; @@ -1414,7 +1439,7 @@ int parse_events_name(struct list_head *list, char *name) { struct perf_evsel *evsel; - __evlist__for_each(list, evsel) { + __evlist__for_each_entry(list, evsel) { if (!evsel->name) evsel->name = strdup(name); } @@ -1976,6 +2001,85 @@ static bool is_event_supported(u8 type, unsigned config) return ret; } +void print_sdt_events(const char *subsys_glob, const char *event_glob, + bool name_only) +{ + struct probe_cache *pcache; + struct probe_cache_entry *ent; + struct strlist *bidlist, *sdtlist; + struct strlist_config cfg = {.dont_dupstr = true}; + struct str_node *nd, *nd2; + char *buf, *path, *ptr = NULL; + bool show_detail = false; + int ret; + + sdtlist = strlist__new(NULL, &cfg); + if (!sdtlist) { + pr_debug("Failed to allocate new strlist for SDT\n"); + return; + } + bidlist = build_id_cache__list_all(true); + if (!bidlist) { + pr_debug("Failed to get buildids: %d\n", errno); + return; + } + strlist__for_each_entry(nd, bidlist) { + pcache = probe_cache__new(nd->s); + if (!pcache) + continue; + list_for_each_entry(ent, &pcache->entries, node) { + if (!ent->sdt) + continue; + if (subsys_glob && + !strglobmatch(ent->pev.group, subsys_glob)) + continue; + if (event_glob && + !strglobmatch(ent->pev.event, event_glob)) + continue; + ret = asprintf(&buf, "%s:%s@%s", ent->pev.group, + ent->pev.event, nd->s); + if (ret > 0) + strlist__add(sdtlist, buf); + } + probe_cache__delete(pcache); + } + strlist__delete(bidlist); + + strlist__for_each_entry(nd, sdtlist) { + buf = strchr(nd->s, '@'); + if (buf) + *(buf++) = '\0'; + if (name_only) { + printf("%s ", nd->s); + continue; + } + nd2 = strlist__next(nd); + if (nd2) { + ptr = strchr(nd2->s, '@'); + if (ptr) + *ptr = '\0'; + if (strcmp(nd->s, nd2->s) == 0) + show_detail = true; + } + if (show_detail) { + path = build_id_cache__origname(buf); + ret = asprintf(&buf, "%s@%s(%.12s)", nd->s, path, buf); + if (ret > 0) { + printf(" %-50s [%s]\n", buf, "SDT event"); + free(buf); + } + } else + printf(" %-50s [%s]\n", nd->s, "SDT event"); + if (nd2) { + if (strcmp(nd->s, nd2->s) != 0) + show_detail = false; + if (ptr) + *ptr = '@'; + } + } + strlist__delete(sdtlist); +} + int print_hwcache_events(const char *event_glob, bool name_only) { unsigned int type, op, i, evt_i = 0, evt_num = 0; @@ -2158,6 +2262,8 @@ void print_events(const char *event_glob, bool name_only) } print_tracepoint_events(NULL, NULL, name_only); + + print_sdt_events(NULL, NULL, name_only); } int parse_events__is_hardcoded_term(struct parse_events_term *term) @@ -2322,9 +2428,9 @@ static void config_terms_list(char *buf, size_t buf_sz) char *parse_events_formats_error_string(char *additional_terms) { char *str; - /* "branch_type" is the longest name */ + /* "no-overwrite" is the longest name */ char static_terms[__PARSE_EVENTS__TERM_TYPE_NR * - (sizeof("branch_type") - 1)]; + (sizeof("no-overwrite") - 1)]; config_terms_list(static_terms, sizeof(static_terms)); /* valid terms */ diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index d740c3ca9a1d..d1edbf8cc66a 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -68,6 +68,9 @@ enum { PARSE_EVENTS__TERM_TYPE_STACKSIZE, PARSE_EVENTS__TERM_TYPE_NOINHERIT, PARSE_EVENTS__TERM_TYPE_INHERIT, + PARSE_EVENTS__TERM_TYPE_MAX_STACK, + PARSE_EVENTS__TERM_TYPE_NOOVERWRITE, + PARSE_EVENTS__TERM_TYPE_OVERWRITE, __PARSE_EVENTS__TERM_TYPE_NR, }; @@ -133,7 +136,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add); int parse_events__modifier_group(struct list_head *list, char *event_mod); int parse_events_name(struct list_head *list, char *name); int parse_events_add_tracepoint(struct list_head *list, int *idx, - char *sys, char *event, + const char *sys, const char *event, struct parse_events_error *error, struct list_head *head_config); int parse_events_load_bpf(struct parse_events_evlist *data, @@ -182,6 +185,8 @@ void print_symbol_events(const char *event_glob, unsigned type, void print_tracepoint_events(const char *subsys_glob, const char *event_glob, bool name_only); int print_hwcache_events(const char *event_glob, bool name_only); +void print_sdt_events(const char *subsys_glob, const char *event_glob, + bool name_only); int is_valid_tracepoint(const char *event_string); int valid_event_mount(const char *eventfs); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 1477fbc78993..7a2519435da0 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -199,8 +199,11 @@ branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE time { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); } call-graph { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CALLGRAPH); } stack-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_STACKSIZE); } +max-stack { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_MAX_STACK); } inherit { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_INHERIT); } no-inherit { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); } +overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); } +no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); } , { return ','; } "/" { BEGIN(INITIAL); return '/'; } {name_minus} { return str(yyscanner, PE_NAME); } @@ -259,6 +262,7 @@ cycles-ct { return str(yyscanner, PE_KERNEL_PMU_EVENT); } cycles-t { return str(yyscanner, PE_KERNEL_PMU_EVENT); } mem-loads { return str(yyscanner, PE_KERNEL_PMU_EVENT); } mem-stores { return str(yyscanner, PE_KERNEL_PMU_EVENT); } +topdown-[a-z-]+ { return str(yyscanner, PE_KERNEL_PMU_EVENT); } L1-dcache|l1-d|l1d|L1-data | L1-icache|l1-i|l1i|L1-instruction | diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c index 3bf6bf82ff2d..7c7630be5a89 100644 --- a/tools/perf/util/path.c +++ b/tools/perf/util/path.c @@ -11,17 +11,13 @@ * which is what it's designed for. */ #include "cache.h" +#include "util.h" +#include <limits.h> static char bad_path[] = "/bad-path/"; /* - * Two hacks: + * One hack: */ - -static const char *get_perf_dir(void) -{ - return "."; -} - static char *get_pathname(void) { static char pathname_array[4][PATH_MAX]; @@ -54,60 +50,3 @@ char *mkpath(const char *fmt, ...) return bad_path; return cleanup_path(pathname); } - -char *perf_path(const char *fmt, ...) -{ - const char *perf_dir = get_perf_dir(); - char *pathname = get_pathname(); - va_list args; - unsigned len; - - len = strlen(perf_dir); - if (len > PATH_MAX-100) - return bad_path; - memcpy(pathname, perf_dir, len); - if (len && perf_dir[len-1] != '/') - pathname[len++] = '/'; - va_start(args, fmt); - len += vsnprintf(pathname + len, PATH_MAX - len, fmt, args); - va_end(args); - if (len >= PATH_MAX) - return bad_path; - return cleanup_path(pathname); -} - -/* strip arbitrary amount of directory separators at end of path */ -static inline int chomp_trailing_dir_sep(const char *path, int len) -{ - while (len && is_dir_sep(path[len - 1])) - len--; - return len; -} - -/* - * If path ends with suffix (complete path components), returns the - * part before suffix (sans trailing directory separators). - * Otherwise returns NULL. - */ -char *strip_path_suffix(const char *path, const char *suffix) -{ - int path_len = strlen(path), suffix_len = strlen(suffix); - - while (suffix_len) { - if (!path_len) - return NULL; - - if (is_dir_sep(path[path_len - 1])) { - if (!is_dir_sep(suffix[suffix_len - 1])) - return NULL; - path_len = chomp_trailing_dir_sep(path, path_len); - suffix_len = chomp_trailing_dir_sep(suffix, suffix_len); - } - else if (path[--path_len] != suffix[--suffix_len]) - return NULL; - } - - if (path_len && !is_dir_sep(path[path_len - 1])) - return NULL; - return strndup(path, chomp_trailing_dir_sep(path, path_len)); -} diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 74401a20106d..953dc1ab2ed7 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -67,7 +67,6 @@ int e_snprintf(char *str, size_t size, const char *format, ...) return ret; } -static char *synthesize_perf_probe_point(struct perf_probe_point *pp); static struct machine *host_machine; /* Initialize symbol maps and path of vmlinux/modules */ @@ -103,10 +102,8 @@ out: void exit_probe_symbol_maps(void) { - if (host_machine) { - machine__delete(host_machine); - host_machine = NULL; - } + machine__delete(host_machine); + host_machine = NULL; symbol__exit(); } @@ -471,7 +468,7 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent) err = kernel_get_module_dso(module, &dso); if (err < 0) { if (!dso || dso->load_errno == 0) { - if (!strerror_r(-err, reason, STRERR_BUFSIZE)) + if (!str_error_r(-err, reason, STRERR_BUFSIZE)) strcpy(reason, "(unknown)"); } else dso__strerror_load(dso, reason, STRERR_BUFSIZE); @@ -809,7 +806,7 @@ static int __show_one_line(FILE *fp, int l, bool skip, bool show_num) error: if (ferror(fp)) { pr_warning("File read error: %s\n", - strerror_r(errno, sbuf, sizeof(sbuf))); + str_error_r(errno, sbuf, sizeof(sbuf))); return -1; } return 0; @@ -889,7 +886,7 @@ static int __show_line_range(struct line_range *lr, const char *module, fp = fopen(lr->path, "r"); if (fp == NULL) { pr_warning("Failed to open %s: %s\n", lr->path, - strerror_r(errno, sbuf, sizeof(sbuf))); + str_error_r(errno, sbuf, sizeof(sbuf))); return -errno; } /* Skip to starting line number */ @@ -899,7 +896,7 @@ static int __show_line_range(struct line_range *lr, const char *module, goto end; } - intlist__for_each(ln, lr->line_list) { + intlist__for_each_entry(ln, lr->line_list) { for (; ln->i > l; l++) { ret = show_one_line(fp, l - lr->offset); if (ret < 0) @@ -983,7 +980,7 @@ static int show_available_vars_at(struct debuginfo *dinfo, zfree(&vl->point.symbol); nvars = 0; if (vl->vars) { - strlist__for_each(node, vl->vars) { + strlist__for_each_entry(node, vl->vars) { var = strchr(node->s, '\t') + 1; if (strfilter__compare(_filter, var)) { fprintf(stdout, "\t\t%s\n", node->s); @@ -1200,6 +1197,34 @@ err: return err; } +static int parse_perf_probe_event_name(char **arg, struct perf_probe_event *pev) +{ + char *ptr; + + ptr = strchr(*arg, ':'); + if (ptr) { + *ptr = '\0'; + if (!pev->sdt && !is_c_func_name(*arg)) + goto ng_name; + pev->group = strdup(*arg); + if (!pev->group) + return -ENOMEM; + *arg = ptr + 1; + } else + pev->group = NULL; + if (!pev->sdt && !is_c_func_name(*arg)) { +ng_name: + semantic_error("%s is bad for event name -it must " + "follow C symbol-naming rule.\n", *arg); + return -EINVAL; + } + pev->event = strdup(*arg); + if (pev->event == NULL) + return -ENOMEM; + + return 0; +} + /* Parse probepoint definition. */ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) { @@ -1207,33 +1232,64 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) char *ptr, *tmp; char c, nc = 0; bool file_spec = false; + int ret; + /* * <Syntax> - * perf probe [EVENT=]SRC[:LN|;PTN] - * perf probe [EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT] - * - * TODO:Group name support + * perf probe [GRP:][EVENT=]SRC[:LN|;PTN] + * perf probe [GRP:][EVENT=]FUNC[@SRC][+OFFS|%return|:LN|;PAT] + * perf probe %[GRP:]SDT_EVENT */ if (!arg) return -EINVAL; + /* + * If the probe point starts with '%', + * or starts with "sdt_" and has a ':' but no '=', + * then it should be a SDT/cached probe point. + */ + if (arg[0] == '%' || + (!strncmp(arg, "sdt_", 4) && + !!strchr(arg, ':') && !strchr(arg, '='))) { + pev->sdt = true; + if (arg[0] == '%') + arg++; + } + ptr = strpbrk(arg, ";=@+%"); + if (pev->sdt) { + if (ptr) { + if (*ptr != '@') { + semantic_error("%s must be an SDT name.\n", + arg); + return -EINVAL; + } + /* This must be a target file name or build id */ + tmp = build_id_cache__complement(ptr + 1); + if (tmp) { + pev->target = build_id_cache__origname(tmp); + free(tmp); + } else + pev->target = strdup(ptr + 1); + if (!pev->target) + return -ENOMEM; + *ptr = '\0'; + } + ret = parse_perf_probe_event_name(&arg, pev); + if (ret == 0) { + if (asprintf(&pev->point.function, "%%%s", pev->event) < 0) + ret = -errno; + } + return ret; + } + if (ptr && *ptr == '=') { /* Event name */ *ptr = '\0'; tmp = ptr + 1; - if (strchr(arg, ':')) { - semantic_error("Group name is not supported yet.\n"); - return -ENOTSUP; - } - if (!is_c_func_name(arg)) { - semantic_error("%s is bad for event name -it must " - "follow C symbol-naming rule.\n", arg); - return -EINVAL; - } - pev->event = strdup(arg); - if (pev->event == NULL) - return -ENOMEM; - pev->group = NULL; + ret = parse_perf_probe_event_name(&arg, pev); + if (ret < 0) + return ret; + arg = tmp; } @@ -1545,7 +1601,9 @@ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev) return true; for (i = 0; i < pev->nargs; i++) - if (is_c_varname(pev->args[i].var)) + if (is_c_varname(pev->args[i].var) || + !strcmp(pev->args[i].var, "$params") || + !strcmp(pev->args[i].var, "$vars")) return true; return false; @@ -1603,6 +1661,11 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev) p = strchr(argv[1], ':'); if (p) { tp->module = strndup(argv[1], p - argv[1]); + if (!tp->module) { + ret = -ENOMEM; + goto out; + } + tev->uprobes = (tp->module[0] == '/'); p++; } else p = argv[1]; @@ -1712,7 +1775,7 @@ out: } /* Compose only probe point (not argument) */ -static char *synthesize_perf_probe_point(struct perf_probe_point *pp) +char *synthesize_perf_probe_point(struct perf_probe_point *pp) { struct strbuf buf; char *tmp, *ret = NULL; @@ -1751,30 +1814,36 @@ out: return ret; } -#if 0 char *synthesize_perf_probe_command(struct perf_probe_event *pev) { - char *buf; - int i, len, ret; + struct strbuf buf; + char *tmp, *ret = NULL; + int i; - buf = synthesize_perf_probe_point(&pev->point); - if (!buf) + if (strbuf_init(&buf, 64)) return NULL; + if (pev->event) + if (strbuf_addf(&buf, "%s:%s=", pev->group ?: PERFPROBE_GROUP, + pev->event) < 0) + goto out; + + tmp = synthesize_perf_probe_point(&pev->point); + if (!tmp || strbuf_addstr(&buf, tmp) < 0) + goto out; + free(tmp); - len = strlen(buf); for (i = 0; i < pev->nargs; i++) { - ret = e_snprintf(&buf[len], MAX_CMDLEN - len, " %s", - pev->args[i].name); - if (ret <= 0) { - free(buf); - return NULL; - } - len += ret; + tmp = synthesize_perf_probe_arg(pev->args + i); + if (!tmp || strbuf_addf(&buf, " %s", tmp) < 0) + goto out; + free(tmp); } - return buf; + ret = strbuf_detach(&buf, NULL); +out: + strbuf_release(&buf); + return ret; } -#endif static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref, struct strbuf *buf, int depth) @@ -2026,6 +2095,79 @@ void clear_perf_probe_event(struct perf_probe_event *pev) memset(pev, 0, sizeof(*pev)); } +#define strdup_or_goto(str, label) \ +({ char *__p = NULL; if (str && !(__p = strdup(str))) goto label; __p; }) + +static int perf_probe_point__copy(struct perf_probe_point *dst, + struct perf_probe_point *src) +{ + dst->file = strdup_or_goto(src->file, out_err); + dst->function = strdup_or_goto(src->function, out_err); + dst->lazy_line = strdup_or_goto(src->lazy_line, out_err); + dst->line = src->line; + dst->retprobe = src->retprobe; + dst->offset = src->offset; + return 0; + +out_err: + clear_perf_probe_point(dst); + return -ENOMEM; +} + +static int perf_probe_arg__copy(struct perf_probe_arg *dst, + struct perf_probe_arg *src) +{ + struct perf_probe_arg_field *field, **ppfield; + + dst->name = strdup_or_goto(src->name, out_err); + dst->var = strdup_or_goto(src->var, out_err); + dst->type = strdup_or_goto(src->type, out_err); + + field = src->field; + ppfield = &(dst->field); + while (field) { + *ppfield = zalloc(sizeof(*field)); + if (!*ppfield) + goto out_err; + (*ppfield)->name = strdup_or_goto(field->name, out_err); + (*ppfield)->index = field->index; + (*ppfield)->ref = field->ref; + field = field->next; + ppfield = &((*ppfield)->next); + } + return 0; +out_err: + return -ENOMEM; +} + +int perf_probe_event__copy(struct perf_probe_event *dst, + struct perf_probe_event *src) +{ + int i; + + dst->event = strdup_or_goto(src->event, out_err); + dst->group = strdup_or_goto(src->group, out_err); + dst->target = strdup_or_goto(src->target, out_err); + dst->uprobes = src->uprobes; + + if (perf_probe_point__copy(&dst->point, &src->point) < 0) + goto out_err; + + dst->args = zalloc(sizeof(struct perf_probe_arg) * src->nargs); + if (!dst->args) + goto out_err; + dst->nargs = src->nargs; + + for (i = 0; i < src->nargs; i++) + if (perf_probe_arg__copy(&dst->args[i], &src->args[i]) < 0) + goto out_err; + return 0; + +out_err: + clear_perf_probe_event(dst); + return -ENOMEM; +} + void clear_probe_trace_event(struct probe_trace_event *tev) { struct probe_trace_arg_ref *ref, *next; @@ -2253,7 +2395,7 @@ static int __show_perf_probe_events(int fd, bool is_kprobe, if (!rawlist) return -ENOMEM; - strlist__for_each(ent, rawlist) { + strlist__for_each_entry(ent, rawlist) { ret = parse_probe_trace_command(ent->s, &tev); if (ret >= 0) { if (!filter_probe_trace_event(&tev, filter)) @@ -2286,6 +2428,9 @@ int show_perf_probe_events(struct strfilter *filter) setup_pager(); + if (probe_conf.cache) + return probe_cache__show_all_caches(filter); + ret = init_probe_symbol_maps(false); if (ret < 0) return ret; @@ -2394,17 +2539,24 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev, char buf[64]; int ret; - if (pev->event) + /* If probe_event or trace_event already have the name, reuse it */ + if (pev->event && !pev->sdt) event = pev->event; - else + else if (tev->event) + event = tev->event; + else { + /* Or generate new one from probe point */ if (pev->point.function && (strncmp(pev->point.function, "0x", 2) != 0) && !strisglob(pev->point.function)) event = pev->point.function; else event = tev->point.realname; - if (pev->group) + } + if (pev->group && !pev->sdt) group = pev->group; + else if (tev->group) + group = tev->group; else group = PERFPROBE_GROUP; @@ -2426,40 +2578,60 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev, return 0; } -static int __add_probe_trace_events(struct perf_probe_event *pev, - struct probe_trace_event *tevs, - int ntevs, bool allow_suffix) +static int __open_probe_file_and_namelist(bool uprobe, + struct strlist **namelist) { - int i, fd, ret; - struct probe_trace_event *tev = NULL; - struct strlist *namelist; + int fd; - fd = probe_file__open(PF_FL_RW | (pev->uprobes ? PF_FL_UPROBE : 0)); + fd = probe_file__open(PF_FL_RW | (uprobe ? PF_FL_UPROBE : 0)); if (fd < 0) return fd; /* Get current event names */ - namelist = probe_file__get_namelist(fd); - if (!namelist) { + *namelist = probe_file__get_namelist(fd); + if (!(*namelist)) { pr_debug("Failed to get current event list.\n"); - ret = -ENOMEM; - goto close_out; + close(fd); + return -ENOMEM; } + return fd; +} + +static int __add_probe_trace_events(struct perf_probe_event *pev, + struct probe_trace_event *tevs, + int ntevs, bool allow_suffix) +{ + int i, fd[2] = {-1, -1}, up, ret; + struct probe_trace_event *tev = NULL; + struct probe_cache *cache = NULL; + struct strlist *namelist[2] = {NULL, NULL}; + + up = pev->uprobes ? 1 : 0; + fd[up] = __open_probe_file_and_namelist(up, &namelist[up]); + if (fd[up] < 0) + return fd[up]; ret = 0; for (i = 0; i < ntevs; i++) { tev = &tevs[i]; + up = tev->uprobes ? 1 : 0; + if (fd[up] == -1) { /* Open the kprobe/uprobe_events */ + fd[up] = __open_probe_file_and_namelist(up, + &namelist[up]); + if (fd[up] < 0) + goto close_out; + } /* Skip if the symbol is out of .text or blacklisted */ - if (!tev->point.symbol) + if (!tev->point.symbol && !pev->uprobes) continue; /* Set new name for tev (and update namelist) */ - ret = probe_trace_event__set_name(tev, pev, namelist, + ret = probe_trace_event__set_name(tev, pev, namelist[up], allow_suffix); if (ret < 0) break; - ret = probe_file__add_event(fd, tev); + ret = probe_file__add_event(fd[up], tev); if (ret < 0) break; @@ -2473,10 +2645,21 @@ static int __add_probe_trace_events(struct perf_probe_event *pev, } if (ret == -EINVAL && pev->uprobes) warn_uprobe_event_compat(tev); + if (ret == 0 && probe_conf.cache) { + cache = probe_cache__new(pev->target); + if (!cache || + probe_cache__add_entry(cache, pev, tevs, ntevs) < 0 || + probe_cache__commit(cache) < 0) + pr_warning("Failed to add event to probe cache\n"); + probe_cache__delete(cache); + } - strlist__delete(namelist); close_out: - close(fd); + for (up = 0; up < 2; up++) { + strlist__delete(namelist[up]); + if (fd[up] >= 0) + close(fd[up]); + } return ret; } @@ -2501,9 +2684,6 @@ static int find_probe_functions(struct map *map, char *name, return found; } -#define strdup_or_goto(str, label) \ - ({ char *__p = strdup(str); if (!__p) goto label; __p; }) - void __weak arch__fix_tev_from_maps(struct perf_probe_event *pev __maybe_unused, struct probe_trace_event *tev __maybe_unused, struct map *map __maybe_unused, @@ -2758,12 +2938,205 @@ errout: bool __weak arch__prefers_symtab(void) { return false; } +/* Concatinate two arrays */ +static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b) +{ + void *ret; + + ret = malloc(sz_a + sz_b); + if (ret) { + memcpy(ret, a, sz_a); + memcpy(ret + sz_a, b, sz_b); + } + return ret; +} + +static int +concat_probe_trace_events(struct probe_trace_event **tevs, int *ntevs, + struct probe_trace_event **tevs2, int ntevs2) +{ + struct probe_trace_event *new_tevs; + int ret = 0; + + if (ntevs == 0) { + *tevs = *tevs2; + *ntevs = ntevs2; + *tevs2 = NULL; + return 0; + } + + if (*ntevs + ntevs2 > probe_conf.max_probes) + ret = -E2BIG; + else { + /* Concatinate the array of probe_trace_event */ + new_tevs = memcat(*tevs, (*ntevs) * sizeof(**tevs), + *tevs2, ntevs2 * sizeof(**tevs2)); + if (!new_tevs) + ret = -ENOMEM; + else { + free(*tevs); + *tevs = new_tevs; + *ntevs += ntevs2; + } + } + if (ret < 0) + clear_probe_trace_events(*tevs2, ntevs2); + zfree(tevs2); + + return ret; +} + +/* + * Try to find probe_trace_event from given probe caches. Return the number + * of cached events found, if an error occurs return the error. + */ +static int find_cached_events(struct perf_probe_event *pev, + struct probe_trace_event **tevs, + const char *target) +{ + struct probe_cache *cache; + struct probe_cache_entry *entry; + struct probe_trace_event *tmp_tevs = NULL; + int ntevs = 0; + int ret = 0; + + cache = probe_cache__new(target); + /* Return 0 ("not found") if the target has no probe cache. */ + if (!cache) + return 0; + + for_each_probe_cache_entry(entry, cache) { + /* Skip the cache entry which has no name */ + if (!entry->pev.event || !entry->pev.group) + continue; + if ((!pev->group || strglobmatch(entry->pev.group, pev->group)) && + strglobmatch(entry->pev.event, pev->event)) { + ret = probe_cache_entry__get_event(entry, &tmp_tevs); + if (ret > 0) + ret = concat_probe_trace_events(tevs, &ntevs, + &tmp_tevs, ret); + if (ret < 0) + break; + } + } + probe_cache__delete(cache); + if (ret < 0) { + clear_probe_trace_events(*tevs, ntevs); + zfree(tevs); + } else { + ret = ntevs; + if (ntevs > 0 && target && target[0] == '/') + pev->uprobes = true; + } + + return ret; +} + +/* Try to find probe_trace_event from all probe caches */ +static int find_cached_events_all(struct perf_probe_event *pev, + struct probe_trace_event **tevs) +{ + struct probe_trace_event *tmp_tevs = NULL; + struct strlist *bidlist; + struct str_node *nd; + char *pathname; + int ntevs = 0; + int ret; + + /* Get the buildid list of all valid caches */ + bidlist = build_id_cache__list_all(true); + if (!bidlist) { + ret = -errno; + pr_debug("Failed to get buildids: %d\n", ret); + return ret; + } + + ret = 0; + strlist__for_each_entry(nd, bidlist) { + pathname = build_id_cache__origname(nd->s); + ret = find_cached_events(pev, &tmp_tevs, pathname); + /* In the case of cnt == 0, we just skip it */ + if (ret > 0) + ret = concat_probe_trace_events(tevs, &ntevs, + &tmp_tevs, ret); + free(pathname); + if (ret < 0) + break; + } + strlist__delete(bidlist); + + if (ret < 0) { + clear_probe_trace_events(*tevs, ntevs); + zfree(tevs); + } else + ret = ntevs; + + return ret; +} + +static int find_probe_trace_events_from_cache(struct perf_probe_event *pev, + struct probe_trace_event **tevs) +{ + struct probe_cache *cache; + struct probe_cache_entry *entry; + struct probe_trace_event *tev; + struct str_node *node; + int ret, i; + + if (pev->sdt) { + /* For SDT/cached events, we use special search functions */ + if (!pev->target) + return find_cached_events_all(pev, tevs); + else + return find_cached_events(pev, tevs, pev->target); + } + cache = probe_cache__new(pev->target); + if (!cache) + return 0; + + entry = probe_cache__find(cache, pev); + if (!entry) { + /* SDT must be in the cache */ + ret = pev->sdt ? -ENOENT : 0; + goto out; + } + + ret = strlist__nr_entries(entry->tevlist); + if (ret > probe_conf.max_probes) { + pr_debug("Too many entries matched in the cache of %s\n", + pev->target ? : "kernel"); + ret = -E2BIG; + goto out; + } + + *tevs = zalloc(ret * sizeof(*tev)); + if (!*tevs) { + ret = -ENOMEM; + goto out; + } + + i = 0; + strlist__for_each_entry(node, entry->tevlist) { + tev = &(*tevs)[i++]; + ret = parse_probe_trace_command(node->s, tev); + if (ret < 0) + goto out; + /* Set the uprobes attribute as same as original */ + tev->uprobes = pev->uprobes; + } + ret = i; + +out: + probe_cache__delete(cache); + return ret; +} + static int convert_to_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event **tevs) { int ret; - if (!pev->group) { + if (!pev->group && !pev->sdt) { /* Set group name if not given */ if (!pev->uprobes) { pev->group = strdup(PERFPROBE_GROUP); @@ -2780,6 +3153,11 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev, if (ret > 0) return ret; + /* At first, we need to lookup cache entry */ + ret = find_probe_trace_events_from_cache(pev, tevs); + if (ret > 0 || pev->sdt) /* SDT can be found only in the cache */ + return ret == 0 ? -ENOENT : ret; /* Found in probe cache */ + if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) { ret = find_probe_trace_events_from_map(pev, tevs); if (ret > 0) @@ -2934,8 +3312,16 @@ int show_available_funcs(const char *target, struct strfilter *_filter, /* Load symbols with given filter */ available_func_filter = _filter; - if (map__load(map, filter_available_functions)) { - pr_err("Failed to load symbols in %s\n", (target) ? : "kernel"); + ret = map__load(map, filter_available_functions); + if (ret) { + if (ret == -2) { + char *str = strfilter__string(_filter); + pr_err("Failed to find symbols matched to \"%s\"\n", + str); + free(str); + } else + pr_err("Failed to load symbols in %s\n", + (target) ? : "kernel"); goto end; } if (!dso__sorted_by_name(map->dso, map->type)) diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 5a27eb4fad05..e18ea9fe6385 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -12,6 +12,7 @@ struct probe_conf { bool show_location_range; bool force_add; bool no_inlines; + bool cache; int max_probes; }; extern struct probe_conf probe_conf; @@ -84,6 +85,7 @@ struct perf_probe_event { char *group; /* Group name */ struct perf_probe_point point; /* Probe point */ int nargs; /* Number of arguments */ + bool sdt; /* SDT/cached event flag */ bool uprobes; /* Uprobe event flag */ char *target; /* Target binary */ struct perf_probe_arg *args; /* Arguments */ @@ -121,6 +123,10 @@ int parse_probe_trace_command(const char *cmd, struct probe_trace_event *tev); char *synthesize_perf_probe_command(struct perf_probe_event *pev); char *synthesize_probe_trace_command(struct probe_trace_event *tev); char *synthesize_perf_probe_arg(struct perf_probe_arg *pa); +char *synthesize_perf_probe_point(struct perf_probe_point *pp); + +int perf_probe_event__copy(struct perf_probe_event *dst, + struct perf_probe_event *src); /* Check the perf_probe_event needs debuginfo */ bool perf_probe_event_need_dwarf(struct perf_probe_event *pev); diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 3fe6214970e6..9aed9c332da6 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -14,6 +14,7 @@ * GNU General Public License for more details. * */ +#include <sys/uio.h> #include "util.h" #include "event.h" #include "strlist.h" @@ -49,7 +50,7 @@ static void print_open_warning(int err, bool uprobe) else pr_warning("Failed to open %cprobe_events: %s\n", uprobe ? 'u' : 'k', - strerror_r(-err, sbuf, sizeof(sbuf))); + str_error_r(-err, sbuf, sizeof(sbuf))); } static void print_both_open_warning(int kerr, int uerr) @@ -63,9 +64,9 @@ static void print_both_open_warning(int kerr, int uerr) else { char sbuf[STRERR_BUFSIZE]; pr_warning("Failed to open kprobe events: %s.\n", - strerror_r(-kerr, sbuf, sizeof(sbuf))); + str_error_r(-kerr, sbuf, sizeof(sbuf))); pr_warning("Failed to open uprobe events: %s.\n", - strerror_r(-uerr, sbuf, sizeof(sbuf))); + str_error_r(-uerr, sbuf, sizeof(sbuf))); } } @@ -177,7 +178,7 @@ static struct strlist *__probe_file__get_namelist(int fd, bool include_group) if (!rawlist) return NULL; sl = strlist__new(NULL, NULL); - strlist__for_each(ent, rawlist) { + strlist__for_each_entry(ent, rawlist) { ret = parse_probe_trace_command(ent->s, &tev); if (ret < 0) break; @@ -223,7 +224,7 @@ int probe_file__add_event(int fd, struct probe_trace_event *tev) if (write(fd, buf, strlen(buf)) < (int)strlen(buf)) { ret = -errno; pr_warning("Failed to write event: %s\n", - strerror_r(errno, sbuf, sizeof(sbuf))); + str_error_r(errno, sbuf, sizeof(sbuf))); } } free(buf); @@ -261,7 +262,7 @@ static int __del_trace_probe_event(int fd, struct str_node *ent) return 0; error: pr_warning("Failed to delete event: %s\n", - strerror_r(-ret, buf, sizeof(buf))); + str_error_r(-ret, buf, sizeof(buf))); return ret; } @@ -280,7 +281,7 @@ int probe_file__get_events(int fd, struct strfilter *filter, if (!namelist) return -ENOENT; - strlist__for_each(ent, namelist) { + strlist__for_each_entry(ent, namelist) { p = strchr(ent->s, ':'); if ((p && strfilter__compare(filter, p + 1)) || strfilter__compare(filter, ent->s)) { @@ -298,7 +299,7 @@ int probe_file__del_strlist(int fd, struct strlist *namelist) int ret = 0; struct str_node *ent; - strlist__for_each(ent, namelist) { + strlist__for_each_entry(ent, namelist) { ret = __del_trace_probe_event(fd, ent); if (ret < 0) break; @@ -324,3 +325,533 @@ int probe_file__del_events(int fd, struct strfilter *filter) return ret; } + +/* Caller must ensure to remove this entry from list */ +static void probe_cache_entry__delete(struct probe_cache_entry *entry) +{ + if (entry) { + BUG_ON(!list_empty(&entry->node)); + + strlist__delete(entry->tevlist); + clear_perf_probe_event(&entry->pev); + zfree(&entry->spev); + free(entry); + } +} + +static struct probe_cache_entry * +probe_cache_entry__new(struct perf_probe_event *pev) +{ + struct probe_cache_entry *entry = zalloc(sizeof(*entry)); + + if (entry) { + INIT_LIST_HEAD(&entry->node); + entry->tevlist = strlist__new(NULL, NULL); + if (!entry->tevlist) + zfree(&entry); + else if (pev) { + entry->spev = synthesize_perf_probe_command(pev); + if (!entry->spev || + perf_probe_event__copy(&entry->pev, pev) < 0) { + probe_cache_entry__delete(entry); + return NULL; + } + } + } + + return entry; +} + +int probe_cache_entry__get_event(struct probe_cache_entry *entry, + struct probe_trace_event **tevs) +{ + struct probe_trace_event *tev; + struct str_node *node; + int ret, i; + + ret = strlist__nr_entries(entry->tevlist); + if (ret > probe_conf.max_probes) + return -E2BIG; + + *tevs = zalloc(ret * sizeof(*tev)); + if (!*tevs) + return -ENOMEM; + + i = 0; + strlist__for_each_entry(node, entry->tevlist) { + tev = &(*tevs)[i++]; + ret = parse_probe_trace_command(node->s, tev); + if (ret < 0) + break; + } + return i; +} + +/* For the kernel probe caches, pass target = NULL or DSO__NAME_KALLSYMS */ +static int probe_cache__open(struct probe_cache *pcache, const char *target) +{ + char cpath[PATH_MAX]; + char sbuildid[SBUILD_ID_SIZE]; + char *dir_name = NULL; + bool is_kallsyms = false; + int ret, fd; + + if (target && build_id_cache__cached(target)) { + /* This is a cached buildid */ + strncpy(sbuildid, target, SBUILD_ID_SIZE); + dir_name = build_id_cache__linkname(sbuildid, NULL, 0); + goto found; + } + + if (!target || !strcmp(target, DSO__NAME_KALLSYMS)) { + target = DSO__NAME_KALLSYMS; + is_kallsyms = true; + ret = sysfs__sprintf_build_id("/", sbuildid); + } else + ret = filename__sprintf_build_id(target, sbuildid); + + if (ret < 0) { + pr_debug("Failed to get build-id from %s.\n", target); + return ret; + } + + /* If we have no buildid cache, make it */ + if (!build_id_cache__cached(sbuildid)) { + ret = build_id_cache__add_s(sbuildid, target, + is_kallsyms, NULL); + if (ret < 0) { + pr_debug("Failed to add build-id cache: %s\n", target); + return ret; + } + } + + dir_name = build_id_cache__cachedir(sbuildid, target, is_kallsyms, + false); +found: + if (!dir_name) { + pr_debug("Failed to get cache from %s\n", target); + return -ENOMEM; + } + + snprintf(cpath, PATH_MAX, "%s/probes", dir_name); + fd = open(cpath, O_CREAT | O_RDWR, 0644); + if (fd < 0) + pr_debug("Failed to open cache(%d): %s\n", fd, cpath); + free(dir_name); + pcache->fd = fd; + + return fd; +} + +static int probe_cache__load(struct probe_cache *pcache) +{ + struct probe_cache_entry *entry = NULL; + char buf[MAX_CMDLEN], *p; + int ret = 0; + FILE *fp; + + fp = fdopen(dup(pcache->fd), "r"); + if (!fp) + return -EINVAL; + + while (!feof(fp)) { + if (!fgets(buf, MAX_CMDLEN, fp)) + break; + p = strchr(buf, '\n'); + if (p) + *p = '\0'; + /* #perf_probe_event or %sdt_event */ + if (buf[0] == '#' || buf[0] == '%') { + entry = probe_cache_entry__new(NULL); + if (!entry) { + ret = -ENOMEM; + goto out; + } + if (buf[0] == '%') + entry->sdt = true; + entry->spev = strdup(buf + 1); + if (entry->spev) + ret = parse_perf_probe_command(buf + 1, + &entry->pev); + else + ret = -ENOMEM; + if (ret < 0) { + probe_cache_entry__delete(entry); + goto out; + } + list_add_tail(&entry->node, &pcache->entries); + } else { /* trace_probe_event */ + if (!entry) { + ret = -EINVAL; + goto out; + } + strlist__add(entry->tevlist, buf); + } + } +out: + fclose(fp); + return ret; +} + +static struct probe_cache *probe_cache__alloc(void) +{ + struct probe_cache *pcache = zalloc(sizeof(*pcache)); + + if (pcache) { + INIT_LIST_HEAD(&pcache->entries); + pcache->fd = -EINVAL; + } + return pcache; +} + +void probe_cache__purge(struct probe_cache *pcache) +{ + struct probe_cache_entry *entry, *n; + + list_for_each_entry_safe(entry, n, &pcache->entries, node) { + list_del_init(&entry->node); + probe_cache_entry__delete(entry); + } +} + +void probe_cache__delete(struct probe_cache *pcache) +{ + if (!pcache) + return; + + probe_cache__purge(pcache); + if (pcache->fd > 0) + close(pcache->fd); + free(pcache); +} + +struct probe_cache *probe_cache__new(const char *target) +{ + struct probe_cache *pcache = probe_cache__alloc(); + int ret; + + if (!pcache) + return NULL; + + ret = probe_cache__open(pcache, target); + if (ret < 0) { + pr_debug("Cache open error: %d\n", ret); + goto out_err; + } + + ret = probe_cache__load(pcache); + if (ret < 0) { + pr_debug("Cache read error: %d\n", ret); + goto out_err; + } + + return pcache; + +out_err: + probe_cache__delete(pcache); + return NULL; +} + +static bool streql(const char *a, const char *b) +{ + if (a == b) + return true; + + if (!a || !b) + return false; + + return !strcmp(a, b); +} + +struct probe_cache_entry * +probe_cache__find(struct probe_cache *pcache, struct perf_probe_event *pev) +{ + struct probe_cache_entry *entry = NULL; + char *cmd = synthesize_perf_probe_command(pev); + + if (!cmd) + return NULL; + + for_each_probe_cache_entry(entry, pcache) { + if (pev->sdt) { + if (entry->pev.event && + streql(entry->pev.event, pev->event) && + (!pev->group || + streql(entry->pev.group, pev->group))) + goto found; + + continue; + } + /* Hit if same event name or same command-string */ + if ((pev->event && + (streql(entry->pev.group, pev->group) && + streql(entry->pev.event, pev->event))) || + (!strcmp(entry->spev, cmd))) + goto found; + } + entry = NULL; + +found: + free(cmd); + return entry; +} + +struct probe_cache_entry * +probe_cache__find_by_name(struct probe_cache *pcache, + const char *group, const char *event) +{ + struct probe_cache_entry *entry = NULL; + + for_each_probe_cache_entry(entry, pcache) { + /* Hit if same event name or same command-string */ + if (streql(entry->pev.group, group) && + streql(entry->pev.event, event)) + goto found; + } + entry = NULL; + +found: + return entry; +} + +int probe_cache__add_entry(struct probe_cache *pcache, + struct perf_probe_event *pev, + struct probe_trace_event *tevs, int ntevs) +{ + struct probe_cache_entry *entry = NULL; + char *command; + int i, ret = 0; + + if (!pcache || !pev || !tevs || ntevs <= 0) { + ret = -EINVAL; + goto out_err; + } + + /* Remove old cache entry */ + entry = probe_cache__find(pcache, pev); + if (entry) { + list_del_init(&entry->node); + probe_cache_entry__delete(entry); + } + + ret = -ENOMEM; + entry = probe_cache_entry__new(pev); + if (!entry) + goto out_err; + + for (i = 0; i < ntevs; i++) { + if (!tevs[i].point.symbol) + continue; + + command = synthesize_probe_trace_command(&tevs[i]); + if (!command) + goto out_err; + strlist__add(entry->tevlist, command); + free(command); + } + list_add_tail(&entry->node, &pcache->entries); + pr_debug("Added probe cache: %d\n", ntevs); + return 0; + +out_err: + pr_debug("Failed to add probe caches\n"); + probe_cache_entry__delete(entry); + return ret; +} + +#ifdef HAVE_GELF_GETNOTE_SUPPORT +static unsigned long long sdt_note__get_addr(struct sdt_note *note) +{ + return note->bit32 ? (unsigned long long)note->addr.a32[0] + : (unsigned long long)note->addr.a64[0]; +} + +int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname) +{ + struct probe_cache_entry *entry = NULL; + struct list_head sdtlist; + struct sdt_note *note; + char *buf; + char sdtgrp[64]; + int ret; + + INIT_LIST_HEAD(&sdtlist); + ret = get_sdt_note_list(&sdtlist, pathname); + if (ret < 0) { + pr_debug("Failed to get sdt note: %d\n", ret); + return ret; + } + list_for_each_entry(note, &sdtlist, note_list) { + ret = snprintf(sdtgrp, 64, "sdt_%s", note->provider); + if (ret < 0) + break; + /* Try to find same-name entry */ + entry = probe_cache__find_by_name(pcache, sdtgrp, note->name); + if (!entry) { + entry = probe_cache_entry__new(NULL); + if (!entry) { + ret = -ENOMEM; + break; + } + entry->sdt = true; + ret = asprintf(&entry->spev, "%s:%s=%s", sdtgrp, + note->name, note->name); + if (ret < 0) + break; + entry->pev.event = strdup(note->name); + entry->pev.group = strdup(sdtgrp); + list_add_tail(&entry->node, &pcache->entries); + } + ret = asprintf(&buf, "p:%s/%s %s:0x%llx", + sdtgrp, note->name, pathname, + sdt_note__get_addr(note)); + if (ret < 0) + break; + strlist__add(entry->tevlist, buf); + free(buf); + entry = NULL; + } + if (entry) { + list_del_init(&entry->node); + probe_cache_entry__delete(entry); + } + cleanup_sdt_note_list(&sdtlist); + return ret; +} +#endif + +static int probe_cache_entry__write(struct probe_cache_entry *entry, int fd) +{ + struct str_node *snode; + struct stat st; + struct iovec iov[3]; + const char *prefix = entry->sdt ? "%" : "#"; + int ret; + /* Save stat for rollback */ + ret = fstat(fd, &st); + if (ret < 0) + return ret; + + pr_debug("Writing cache: %s%s\n", prefix, entry->spev); + iov[0].iov_base = (void *)prefix; iov[0].iov_len = 1; + iov[1].iov_base = entry->spev; iov[1].iov_len = strlen(entry->spev); + iov[2].iov_base = (void *)"\n"; iov[2].iov_len = 1; + ret = writev(fd, iov, 3); + if (ret < (int)iov[1].iov_len + 2) + goto rollback; + + strlist__for_each_entry(snode, entry->tevlist) { + iov[0].iov_base = (void *)snode->s; + iov[0].iov_len = strlen(snode->s); + iov[1].iov_base = (void *)"\n"; iov[1].iov_len = 1; + ret = writev(fd, iov, 2); + if (ret < (int)iov[0].iov_len + 1) + goto rollback; + } + return 0; + +rollback: + /* Rollback to avoid cache file corruption */ + if (ret > 0) + ret = -1; + if (ftruncate(fd, st.st_size) < 0) + ret = -2; + + return ret; +} + +int probe_cache__commit(struct probe_cache *pcache) +{ + struct probe_cache_entry *entry; + int ret = 0; + + /* TBD: if we do not update existing entries, skip it */ + ret = lseek(pcache->fd, 0, SEEK_SET); + if (ret < 0) + goto out; + + ret = ftruncate(pcache->fd, 0); + if (ret < 0) + goto out; + + for_each_probe_cache_entry(entry, pcache) { + ret = probe_cache_entry__write(entry, pcache->fd); + pr_debug("Cache committed: %d\n", ret); + if (ret < 0) + break; + } +out: + return ret; +} + +static bool probe_cache_entry__compare(struct probe_cache_entry *entry, + struct strfilter *filter) +{ + char buf[128], *ptr = entry->spev; + + if (entry->pev.event) { + snprintf(buf, 128, "%s:%s", entry->pev.group, entry->pev.event); + ptr = buf; + } + return strfilter__compare(filter, ptr); +} + +int probe_cache__filter_purge(struct probe_cache *pcache, + struct strfilter *filter) +{ + struct probe_cache_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &pcache->entries, node) { + if (probe_cache_entry__compare(entry, filter)) { + pr_info("Removed cached event: %s\n", entry->spev); + list_del_init(&entry->node); + probe_cache_entry__delete(entry); + } + } + return 0; +} + +static int probe_cache__show_entries(struct probe_cache *pcache, + struct strfilter *filter) +{ + struct probe_cache_entry *entry; + + for_each_probe_cache_entry(entry, pcache) { + if (probe_cache_entry__compare(entry, filter)) + printf("%s\n", entry->spev); + } + return 0; +} + +/* Show all cached probes */ +int probe_cache__show_all_caches(struct strfilter *filter) +{ + struct probe_cache *pcache; + struct strlist *bidlist; + struct str_node *nd; + char *buf = strfilter__string(filter); + + pr_debug("list cache with filter: %s\n", buf); + free(buf); + + bidlist = build_id_cache__list_all(true); + if (!bidlist) { + pr_debug("Failed to get buildids: %d\n", errno); + return -EINVAL; + } + strlist__for_each_entry(nd, bidlist) { + pcache = probe_cache__new(nd->s); + if (!pcache) + continue; + if (!list_empty(&pcache->entries)) { + buf = build_id_cache__origname(nd->s); + printf("%s (%s):\n", buf, nd->s); + free(buf); + probe_cache__show_entries(pcache, filter); + } + probe_cache__delete(pcache); + } + strlist__delete(bidlist); + + return 0; +} diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index 18ac9cf51c34..9577b5c0b487 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -5,9 +5,27 @@ #include "strfilter.h" #include "probe-event.h" +/* Cache of probe definitions */ +struct probe_cache_entry { + struct list_head node; + bool sdt; + struct perf_probe_event pev; + char *spev; + struct strlist *tevlist; +}; + +struct probe_cache { + int fd; + struct list_head entries; +}; + #define PF_FL_UPROBE 1 #define PF_FL_RW 2 +#define for_each_probe_cache_entry(entry, pcache) \ + list_for_each_entry(entry, &pcache->entries, node) +/* probe-file.c depends on libelf */ +#ifdef HAVE_LIBELF_SUPPORT int probe_file__open(int flag); int probe_file__open_both(int *kfd, int *ufd, int flag); struct strlist *probe_file__get_namelist(int fd); @@ -18,5 +36,29 @@ int probe_file__get_events(int fd, struct strfilter *filter, struct strlist *plist); int probe_file__del_strlist(int fd, struct strlist *namelist); +int probe_cache_entry__get_event(struct probe_cache_entry *entry, + struct probe_trace_event **tevs); +struct probe_cache *probe_cache__new(const char *target); +int probe_cache__add_entry(struct probe_cache *pcache, + struct perf_probe_event *pev, + struct probe_trace_event *tevs, int ntevs); +int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname); +int probe_cache__commit(struct probe_cache *pcache); +void probe_cache__purge(struct probe_cache *pcache); +void probe_cache__delete(struct probe_cache *pcache); +int probe_cache__filter_purge(struct probe_cache *pcache, + struct strfilter *filter); +struct probe_cache_entry *probe_cache__find(struct probe_cache *pcache, + struct perf_probe_event *pev); +struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache, + const char *group, const char *event); +int probe_cache__show_all_caches(struct strfilter *filter); +#else /* ! HAVE_LIBELF_SUPPORT */ +static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused) +{ + return NULL; +} +#define probe_cache__delete(pcache) do {} while (0) +#endif #endif diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 1259839dbf6d..f2d9ff064e2d 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -381,7 +381,7 @@ formatted: if (ret >= 16) ret = -E2BIG; pr_warning("Failed to convert variable type: %s\n", - strerror_r(-ret, sbuf, sizeof(sbuf))); + str_error_r(-ret, sbuf, sizeof(sbuf))); return ret; } tvar->type = strdup(buf); @@ -809,7 +809,7 @@ static int find_lazy_match_lines(struct intlist *list, fp = fopen(fname, "r"); if (!fp) { pr_warning("Failed to open %s: %s\n", fname, - strerror_r(errno, sbuf, sizeof(sbuf))); + str_error_r(errno, sbuf, sizeof(sbuf))); return -errno; } diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 36c6862119e3..5065ec98049c 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -13,6 +13,8 @@ util/cpumap.c ../lib/bitmap.c ../lib/find_bit.c ../lib/hweight.c +../lib/str_error_r.c +../lib/vsprintf.c util/thread_map.c util/util.c util/xyarray.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 98f127abfa42..a5fbc012e3df 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -2,6 +2,7 @@ #include <structmember.h> #include <inttypes.h> #include <poll.h> +#include <linux/err.h> #include "evlist.h" #include "evsel.h" #include "event.h" @@ -47,6 +48,7 @@ PyMODINIT_FUNC initperf(void); struct pyrf_event { PyObject_HEAD + struct perf_evsel *evsel; struct perf_sample sample; union perf_event event; }; @@ -288,6 +290,85 @@ static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent) return ret; } +static bool is_tracepoint(struct pyrf_event *pevent) +{ + return pevent->evsel->attr.type == PERF_TYPE_TRACEPOINT; +} + +static PyObject* +tracepoint_field(struct pyrf_event *pe, struct format_field *field) +{ + struct pevent *pevent = field->event->pevent; + void *data = pe->sample.raw_data; + PyObject *ret = NULL; + unsigned long long val; + unsigned int offset, len; + + if (field->flags & FIELD_IS_ARRAY) { + offset = field->offset; + len = field->size; + if (field->flags & FIELD_IS_DYNAMIC) { + val = pevent_read_number(pevent, data + offset, len); + offset = val; + len = offset >> 16; + offset &= 0xffff; + } + if (field->flags & FIELD_IS_STRING && + is_printable_array(data + offset, len)) { + ret = PyString_FromString((char *)data + offset); + } else { + ret = PyByteArray_FromStringAndSize((const char *) data + offset, len); + field->flags &= ~FIELD_IS_STRING; + } + } else { + val = pevent_read_number(pevent, data + field->offset, + field->size); + if (field->flags & FIELD_IS_POINTER) + ret = PyLong_FromUnsignedLong((unsigned long) val); + else if (field->flags & FIELD_IS_SIGNED) + ret = PyLong_FromLong((long) val); + else + ret = PyLong_FromUnsignedLong((unsigned long) val); + } + + return ret; +} + +static PyObject* +get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name) +{ + const char *str = PyString_AsString(PyObject_Str(attr_name)); + struct perf_evsel *evsel = pevent->evsel; + struct format_field *field; + + if (!evsel->tp_format) { + struct event_format *tp_format; + + tp_format = trace_event__tp_format_id(evsel->attr.config); + if (!tp_format) + return NULL; + + evsel->tp_format = tp_format; + } + + field = pevent_find_any_field(evsel->tp_format, str); + if (!field) + return NULL; + + return tracepoint_field(pevent, field); +} + +static PyObject* +pyrf_sample_event__getattro(struct pyrf_event *pevent, PyObject *attr_name) +{ + PyObject *obj = NULL; + + if (is_tracepoint(pevent)) + obj = get_tracepoint_field(pevent, attr_name); + + return obj ?: PyObject_GenericGetAttr((PyObject *) pevent, attr_name); +} + static PyTypeObject pyrf_sample_event__type = { PyVarObject_HEAD_INIT(NULL, 0) .tp_name = "perf.sample_event", @@ -296,6 +377,7 @@ static PyTypeObject pyrf_sample_event__type = { .tp_doc = pyrf_sample_event__doc, .tp_members = pyrf_sample_event__members, .tp_repr = (reprfunc)pyrf_sample_event__repr, + .tp_getattro = (getattrofunc) pyrf_sample_event__getattro, }; static char pyrf_context_switch_event__doc[] = PyDoc_STR("perf context_switch event object."); @@ -653,6 +735,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel, attr.precise_ip = precise_ip; attr.mmap_data = mmap_data; attr.sample_id_all = sample_id_all; + attr.size = sizeof(attr); perf_evsel__init(&pevsel->evsel, &attr, idx); return 0; @@ -863,13 +946,22 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, if (event != NULL) { PyObject *pyevent = pyrf_event__new(event); struct pyrf_event *pevent = (struct pyrf_event *)pyevent; - - perf_evlist__mmap_consume(evlist, cpu); + struct perf_evsel *evsel; if (pyevent == NULL) return PyErr_NoMemory(); - err = perf_evlist__parse_sample(evlist, event, &pevent->sample); + evsel = perf_evlist__event2evsel(evlist, event); + if (!evsel) + return Py_None; + + pevent->evsel = evsel; + + err = perf_evsel__parse_sample(evsel, event, &pevent->sample); + + /* Consume the even only after we parsed it out. */ + perf_evlist__mmap_consume(evlist, cpu); + if (err) return PyErr_Format(PyExc_OSError, "perf: can't parse sample, err=%d", err); @@ -957,7 +1049,7 @@ static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i) if (i >= pevlist->evlist.nr_entries) return NULL; - evlist__for_each(&pevlist->evlist, pos) { + evlist__for_each_entry(&pevlist->evlist, pos) { if (i-- == 0) break; } @@ -1073,7 +1165,32 @@ static struct { { .name = NULL, }, }; +static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel, + PyObject *args, PyObject *kwargs) +{ + struct event_format *tp_format; + static char *kwlist[] = { "sys", "name", NULL }; + char *sys = NULL; + char *name = NULL; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ss", kwlist, + &sys, &name)) + return NULL; + + tp_format = trace_event__tp_format(sys, name); + if (IS_ERR(tp_format)) + return PyInt_FromLong(-1); + + return PyInt_FromLong(tp_format->id); +} + static PyMethodDef perf__methods[] = { + { + .ml_name = "tracepoint", + .ml_meth = (PyCFunction) pyrf__tracepoint, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("Get tracepoint config.") + }, { .ml_name = NULL, } }; @@ -1100,6 +1217,33 @@ PyMODINIT_FUNC initperf(void) Py_INCREF(&pyrf_evsel__type); PyModule_AddObject(module, "evsel", (PyObject*)&pyrf_evsel__type); + Py_INCREF(&pyrf_mmap_event__type); + PyModule_AddObject(module, "mmap_event", (PyObject *)&pyrf_mmap_event__type); + + Py_INCREF(&pyrf_lost_event__type); + PyModule_AddObject(module, "lost_event", (PyObject *)&pyrf_lost_event__type); + + Py_INCREF(&pyrf_comm_event__type); + PyModule_AddObject(module, "comm_event", (PyObject *)&pyrf_comm_event__type); + + Py_INCREF(&pyrf_task_event__type); + PyModule_AddObject(module, "task_event", (PyObject *)&pyrf_task_event__type); + + Py_INCREF(&pyrf_throttle_event__type); + PyModule_AddObject(module, "throttle_event", (PyObject *)&pyrf_throttle_event__type); + + Py_INCREF(&pyrf_task_event__type); + PyModule_AddObject(module, "task_event", (PyObject *)&pyrf_task_event__type); + + Py_INCREF(&pyrf_read_event__type); + PyModule_AddObject(module, "read_event", (PyObject *)&pyrf_read_event__type); + + Py_INCREF(&pyrf_sample_event__type); + PyModule_AddObject(module, "sample_event", (PyObject *)&pyrf_sample_event__type); + + Py_INCREF(&pyrf_context_switch_event__type); + PyModule_AddObject(module, "switch_event", (PyObject *)&pyrf_context_switch_event__type); + Py_INCREF(&pyrf_thread_map__type); PyModule_AddObject(module, "thread_map", (PyObject*)&pyrf_thread_map__type); diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c index c6d4ee2de752..639d1da2f978 100644 --- a/tools/perf/util/quote.c +++ b/tools/perf/util/quote.c @@ -1,5 +1,7 @@ -#include "cache.h" +#include <stdlib.h> +#include "strbuf.h" #include "quote.h" +#include "util.h" /* Help to copy the thing properly quoted for the shell safety. * any single quote is replaced with '\'', any exclamation point diff --git a/tools/perf/util/quote.h b/tools/perf/util/quote.h index e1ec19146fb0..055ca45bed99 100644 --- a/tools/perf/util/quote.h +++ b/tools/perf/util/quote.h @@ -2,7 +2,6 @@ #define __PERF_QUOTE_H #include <stddef.h> -#include <stdio.h> /* Help to copy the thing properly quoted for the shell safety. * any single quote is replaced with '\'', any exclamation point @@ -24,6 +23,8 @@ * sq_quote() in a real application. */ +struct strbuf; + int sq_quote_argv(struct strbuf *, const char **argv, size_t maxlen); #endif /* __PERF_QUOTE_H */ diff --git a/tools/perf/util/rb_resort.h b/tools/perf/util/rb_resort.h index abc76e3d3098..808cc45611fe 100644 --- a/tools/perf/util/rb_resort.h +++ b/tools/perf/util/rb_resort.h @@ -35,7 +35,7 @@ DEFINE_RB_RESORT_RB(threads, strcmp(a->thread->shortname, struct rb_node *nd; - resort_rb__for_each(nd, threads) { + resort_rb__for_each_entry(nd, threads) { struct thread *t = threads_entry; printf("%s: %d\n", t->shortname, t->tid); } @@ -123,7 +123,7 @@ static void __name##_sorted__init_entry(struct rb_node *nd, \ struct __name##_sorted_entry *__name##_entry; \ struct __name##_sorted *__name = __name##_sorted__new -#define resort_rb__for_each(__nd, __name) \ +#define resort_rb__for_each_entry(__nd, __name) \ for (__nd = rb_first(&__name->entries); \ __name##_entry = rb_entry(__nd, struct __name##_sorted_entry, \ rb_node), __nd; \ diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 481792c7484b..98bf584853ea 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -148,7 +148,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, use_comm_exec = perf_can_comm_exec(); - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { perf_evsel__config(evsel, opts, callchain); if (evsel->tracking && use_comm_exec) evsel->attr.comm_exec = 1; @@ -161,18 +161,18 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, * match the id. */ use_sample_identifier = perf_can_sample_identifier(); - evlist__for_each(evlist, evsel) + evlist__for_each_entry(evlist, evsel) perf_evsel__set_sample_id(evsel, use_sample_identifier); } else if (evlist->nr_entries > 1) { struct perf_evsel *first = perf_evlist__first(evlist); - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel->attr.sample_type == first->attr.sample_type) continue; use_sample_identifier = perf_can_sample_identifier(); break; } - evlist__for_each(evlist, evsel) + evlist__for_each_entry(evlist, evsel) perf_evsel__set_sample_id(evsel, use_sample_identifier); } diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index ff134700bf30..e0203b979474 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -273,7 +273,7 @@ static PyObject *get_field_numeric_entry(struct event_format *event, struct format_field *field, void *data) { bool is_array = field->flags & FIELD_IS_ARRAY; - PyObject *obj, *list = NULL; + PyObject *obj = NULL, *list = NULL; unsigned long long val; unsigned int item_size, n_items, i; @@ -386,13 +386,12 @@ exit: return pylist; } - static void python_process_tracepoint(struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al) { struct event_format *event = evsel->tp_format; - PyObject *handler, *context, *t, *obj, *callchain; + PyObject *handler, *context, *t, *obj = NULL, *callchain; PyObject *dict = NULL; static char handler_name[256]; struct format_field *field; @@ -457,14 +456,26 @@ static void python_process_tracepoint(struct perf_sample *sample, pydict_set_item_string_decref(dict, "common_callchain", callchain); } for (field = event->format.fields; field; field = field->next) { - if (field->flags & FIELD_IS_STRING) { - int offset; + unsigned int offset, len; + unsigned long long val; + + if (field->flags & FIELD_IS_ARRAY) { + offset = field->offset; + len = field->size; if (field->flags & FIELD_IS_DYNAMIC) { - offset = *(int *)(data + field->offset); + val = pevent_read_number(scripting_context->pevent, + data + offset, len); + offset = val; + len = offset >> 16; offset &= 0xffff; - } else - offset = field->offset; - obj = PyString_FromString((char *)data + offset); + } + if (field->flags & FIELD_IS_STRING && + is_printable_array(data + offset, len)) { + obj = PyString_FromString((char *) data + offset); + } else { + obj = PyByteArray_FromStringAndSize((const char *) data + offset, len); + field->flags &= ~FIELD_IS_STRING; + } } else { /* FIELD_IS_NUMERIC */ obj = get_field_numeric_entry(event, field, data); } diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 5214974e841a..5d61242a6e64 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -83,7 +83,7 @@ static bool perf_session__has_comm_exec(struct perf_session *session) { struct perf_evsel *evsel; - evlist__for_each(session->evlist, evsel) { + evlist__for_each_entry(session->evlist, evsel) { if (evsel->attr.comm_exec) return true; } @@ -178,6 +178,8 @@ static void perf_session__delete_threads(struct perf_session *session) void perf_session__delete(struct perf_session *session) { + if (session == NULL) + return; auxtrace__free(session); auxtrace_index__free(&session->auxtrace_index); perf_session__destroy_kernel_maps(session); @@ -593,6 +595,7 @@ do { \ if (bswap_safe(f, 0)) \ attr->f = bswap_##sz(attr->f); \ } while(0) +#define bswap_field_16(f) bswap_field(f, 16) #define bswap_field_32(f) bswap_field(f, 32) #define bswap_field_64(f) bswap_field(f, 64) @@ -608,6 +611,7 @@ do { \ bswap_field_64(sample_regs_user); bswap_field_32(sample_stack_user); bswap_field_32(aux_watermark); + bswap_field_16(sample_max_stack); /* * After read_format are bitfields. Check read_format because @@ -1495,10 +1499,27 @@ int perf_session__register_idle_thread(struct perf_session *session) return err; } +static void +perf_session__warn_order(const struct perf_session *session) +{ + const struct ordered_events *oe = &session->ordered_events; + struct perf_evsel *evsel; + bool should_warn = true; + + evlist__for_each_entry(session->evlist, evsel) { + if (evsel->attr.write_backward) + should_warn = false; + } + + if (!should_warn) + return; + if (oe->nr_unordered_events != 0) + ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events); +} + static void perf_session__warn_about_errors(const struct perf_session *session) { 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) { @@ -1555,8 +1576,7 @@ static void perf_session__warn_about_errors(const struct perf_session *session) stats->nr_unprocessable_samples); } - if (oe->nr_unordered_events != 0) - ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events); + perf_session__warn_order(session); events_stats__auxtrace_error_warn(stats); @@ -1868,7 +1888,7 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg) { struct perf_evsel *evsel; - evlist__for_each(session->evlist, evsel) { + evlist__for_each_entry(session->evlist, evsel) { if (evsel->attr.type == PERF_TYPE_TRACEPOINT) return true; } @@ -1950,7 +1970,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, { struct perf_evsel *pos; - evlist__for_each(session->evlist, pos) { + evlist__for_each_entry(session->evlist, pos) { if (pos->attr.type == type) return pos; } @@ -2105,7 +2125,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, max_nr = (UINT16_MAX - sizeof(struct id_index_event)) / sizeof(struct id_index_entry); - evlist__for_each(evlist, evsel) + evlist__for_each_entry(evlist, evsel) nr += evsel->ids; n = nr > max_nr ? max_nr : nr; @@ -2118,7 +2138,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, ev->id_index.header.size = sz; ev->id_index.nr = n; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { u32 j; for (j = 0; j < evsel->ids; j++) { diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index c4e9bd70723c..947d21f38398 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -79,8 +79,8 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf, { const char *comm = thread__comm_str(he->thread); - width = max(7U, width) - 6; - return repsep_snprintf(bf, size, "%5d:%-*.*s", he->thread->tid, + width = max(7U, width) - 8; + return repsep_snprintf(bf, size, "%7d:%-*.*s", he->thread->tid, width, width, comm ?: ""); } @@ -95,7 +95,7 @@ static int hist_entry__thread_filter(struct hist_entry *he, int type, const void } struct sort_entry sort_thread = { - .se_header = " Pid:Command", + .se_header = " Pid:Command", .se_cmp = sort__thread_cmp, .se_snprintf = hist_entry__thread_snprintf, .se_filter = hist_entry__thread_filter, @@ -1218,7 +1218,7 @@ struct sort_entry sort_mem_daddr_dso = { .se_header = "Data Object", .se_cmp = sort__dso_daddr_cmp, .se_snprintf = hist_entry__dso_daddr_snprintf, - .se_width_idx = HISTC_MEM_DADDR_SYMBOL, + .se_width_idx = HISTC_MEM_DADDR_DSO, }; struct sort_entry sort_mem_locked = { @@ -1488,7 +1488,7 @@ void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists) } static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, - struct perf_evsel *evsel) + struct hists *hists) { struct hpp_sort_entry *hse; size_t len = fmt->user_len; @@ -1496,14 +1496,14 @@ static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, hse = container_of(fmt, struct hpp_sort_entry, hpp); if (!len) - len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx); + len = hists__col_len(hists, hse->se->se_width_idx); return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name); } static int __sort__hpp_width(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp __maybe_unused, - struct perf_evsel *evsel) + struct hists *hists) { struct hpp_sort_entry *hse; size_t len = fmt->user_len; @@ -1511,7 +1511,7 @@ static int __sort__hpp_width(struct perf_hpp_fmt *fmt, hse = container_of(fmt, struct hpp_sort_entry, hpp); if (!len) - len = hists__col_len(evsel__hists(evsel), hse->se->se_width_idx); + len = hists__col_len(hists, hse->se->se_width_idx); return len; } @@ -1793,7 +1793,7 @@ static void update_dynamic_len(struct hpp_dynamic_entry *hde, } static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, - struct perf_evsel *evsel __maybe_unused) + struct hists *hists __maybe_unused) { struct hpp_dynamic_entry *hde; size_t len = fmt->user_len; @@ -1808,7 +1808,7 @@ static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, static int __sort__hde_width(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp __maybe_unused, - struct perf_evsel *evsel __maybe_unused) + struct hists *hists __maybe_unused) { struct hpp_dynamic_entry *hde; size_t len = fmt->user_len; @@ -2069,7 +2069,7 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam } full_name = !!strchr(event_name, ':'); - evlist__for_each(evlist, pos) { + evlist__for_each_entry(evlist, pos) { /* case 2 */ if (full_name && !strcmp(pos->name, event_name)) return pos; @@ -2125,7 +2125,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace, int ret; struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel->attr.type != PERF_TYPE_TRACEPOINT) continue; @@ -2143,7 +2143,7 @@ static int add_all_matching_fields(struct perf_evlist *evlist, struct perf_evsel *evsel; struct format_field *field; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel->attr.type != PERF_TYPE_TRACEPOINT) continue; @@ -2381,6 +2381,9 @@ static int sort_dimension__add(struct perf_hpp_list *list, const char *tok, if (sort__mode != SORT_MODE__MEMORY) return -EINVAL; + if (sd->entry == &sort_mem_dcacheline && cacheline_size == 0) + return -EINVAL; + if (sd->entry == &sort_mem_daddr_sym) list->sym = 1; @@ -2424,7 +2427,10 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str, if (*tok) { ret = sort_dimension__add(list, tok, evlist, level); if (ret == -EINVAL) { - error("Invalid --sort key: `%s'", tok); + if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok))) + error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system"); + else + error("Invalid --sort key: `%s'", tok); break; } else if (ret == -ESRCH) { error("Unknown --sort key: `%s'", tok); @@ -2456,7 +2462,7 @@ static const char *get_default_sort_order(struct perf_evlist *evlist) if (evlist == NULL) goto out_no_evlist; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { use_trace = false; break; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index ebb59cacd092..7ca37ea17395 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -67,6 +67,11 @@ struct hist_entry_diff { }; }; +struct hist_entry_ops { + void *(*new)(size_t size); + void (*free)(void *ptr); +}; + /** * struct hist_entry - histogram entry * @@ -125,6 +130,7 @@ struct hist_entry { void *trace_output; struct perf_hpp_list *hpp_list; struct hist_entry *parent_he; + struct hist_entry_ops *ops; union { /* this is for hierarchical entry structure */ struct { diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index aa9efe08762b..8a2bbd2a4d82 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -36,6 +36,11 @@ static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS]; +static struct stats runtime_topdown_total_slots[NUM_CTX][MAX_NR_CPUS]; +static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS]; +static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS]; +static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS]; +static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS]; static bool have_frontend_stalled; struct stats walltime_nsecs_stats; @@ -82,6 +87,11 @@ void perf_stat__reset_shadow_stats(void) sizeof(runtime_transaction_stats)); memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats)); memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats)); + memset(runtime_topdown_total_slots, 0, sizeof(runtime_topdown_total_slots)); + memset(runtime_topdown_slots_retired, 0, sizeof(runtime_topdown_slots_retired)); + memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued)); + memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles)); + memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles)); } /* @@ -105,6 +115,16 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, update_stats(&runtime_transaction_stats[ctx][cpu], count[0]); else if (perf_stat_evsel__is(counter, ELISION_START)) update_stats(&runtime_elision_stats[ctx][cpu], count[0]); + else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS)) + update_stats(&runtime_topdown_total_slots[ctx][cpu], count[0]); + else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED)) + update_stats(&runtime_topdown_slots_issued[ctx][cpu], count[0]); + else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED)) + update_stats(&runtime_topdown_slots_retired[ctx][cpu], count[0]); + else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES)) + update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu],count[0]); + else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES)) + update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]); else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) @@ -302,6 +322,107 @@ static void print_ll_cache_misses(int cpu, out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio); } +/* + * High level "TopDown" CPU core pipe line bottleneck break down. + * + * Basic concept following + * Yasin, A Top Down Method for Performance analysis and Counter architecture + * ISPASS14 + * + * The CPU pipeline is divided into 4 areas that can be bottlenecks: + * + * Frontend -> Backend -> Retiring + * BadSpeculation in addition means out of order execution that is thrown away + * (for example branch mispredictions) + * Frontend is instruction decoding. + * Backend is execution, like computation and accessing data in memory + * Retiring is good execution that is not directly bottlenecked + * + * The formulas are computed in slots. + * A slot is an entry in the pipeline each for the pipeline width + * (for example a 4-wide pipeline has 4 slots for each cycle) + * + * Formulas: + * BadSpeculation = ((SlotsIssued - SlotsRetired) + RecoveryBubbles) / + * TotalSlots + * Retiring = SlotsRetired / TotalSlots + * FrontendBound = FetchBubbles / TotalSlots + * BackendBound = 1.0 - BadSpeculation - Retiring - FrontendBound + * + * The kernel provides the mapping to the low level CPU events and any scaling + * needed for the CPU pipeline width, for example: + * + * TotalSlots = Cycles * 4 + * + * The scaling factor is communicated in the sysfs unit. + * + * In some cases the CPU may not be able to measure all the formulas due to + * missing events. In this case multiple formulas are combined, as possible. + * + * Full TopDown supports more levels to sub-divide each area: for example + * BackendBound into computing bound and memory bound. For now we only + * support Level 1 TopDown. + */ + +static double sanitize_val(double x) +{ + if (x < 0 && x >= -0.02) + return 0.0; + return x; +} + +static double td_total_slots(int ctx, int cpu) +{ + return avg_stats(&runtime_topdown_total_slots[ctx][cpu]); +} + +static double td_bad_spec(int ctx, int cpu) +{ + double bad_spec = 0; + double total_slots; + double total; + + total = avg_stats(&runtime_topdown_slots_issued[ctx][cpu]) - + avg_stats(&runtime_topdown_slots_retired[ctx][cpu]) + + avg_stats(&runtime_topdown_recovery_bubbles[ctx][cpu]); + total_slots = td_total_slots(ctx, cpu); + if (total_slots) + bad_spec = total / total_slots; + return sanitize_val(bad_spec); +} + +static double td_retiring(int ctx, int cpu) +{ + double retiring = 0; + double total_slots = td_total_slots(ctx, cpu); + double ret_slots = avg_stats(&runtime_topdown_slots_retired[ctx][cpu]); + + if (total_slots) + retiring = ret_slots / total_slots; + return retiring; +} + +static double td_fe_bound(int ctx, int cpu) +{ + double fe_bound = 0; + double total_slots = td_total_slots(ctx, cpu); + double fetch_bub = avg_stats(&runtime_topdown_fetch_bubbles[ctx][cpu]); + + if (total_slots) + fe_bound = fetch_bub / total_slots; + return fe_bound; +} + +static double td_be_bound(int ctx, int cpu) +{ + double sum = (td_fe_bound(ctx, cpu) + + td_bad_spec(ctx, cpu) + + td_retiring(ctx, cpu)); + if (sum == 0) + return 0; + return sanitize_val(1.0 - sum); +} + void perf_stat__print_shadow_stats(struct perf_evsel *evsel, double avg, int cpu, struct perf_stat_output_ctx *out) @@ -309,6 +430,7 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, void *ctxp = out->ctx; print_metric_t print_metric = out->print_metric; double total, ratio = 0.0, total2; + const char *color = NULL; int ctx = evsel_context(evsel); if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { @@ -452,6 +574,46 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, avg / ratio); else print_metric(ctxp, NULL, NULL, "CPUs utilized", 0); + } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) { + double fe_bound = td_fe_bound(ctx, cpu); + + if (fe_bound > 0.2) + color = PERF_COLOR_RED; + print_metric(ctxp, color, "%8.1f%%", "frontend bound", + fe_bound * 100.); + } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) { + double retiring = td_retiring(ctx, cpu); + + if (retiring > 0.7) + color = PERF_COLOR_GREEN; + print_metric(ctxp, color, "%8.1f%%", "retiring", + retiring * 100.); + } else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) { + double bad_spec = td_bad_spec(ctx, cpu); + + if (bad_spec > 0.1) + color = PERF_COLOR_RED; + print_metric(ctxp, color, "%8.1f%%", "bad speculation", + bad_spec * 100.); + } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) { + double be_bound = td_be_bound(ctx, cpu); + const char *name = "backend bound"; + static int have_recovery_bubbles = -1; + + /* In case the CPU does not support topdown-recovery-bubbles */ + if (have_recovery_bubbles < 0) + have_recovery_bubbles = pmu_have_event("cpu", + "topdown-recovery-bubbles"); + if (!have_recovery_bubbles) + name = "backend bound/bad spec"; + + if (be_bound > 0.2) + color = PERF_COLOR_RED; + if (td_total_slots(ctx, cpu) > 0) + print_metric(ctxp, color, "%8.1f%%", name, + be_bound * 100.); + else + print_metric(ctxp, NULL, NULL, name, 0); } else if (runtime_nsecs_stats[cpu].n != 0) { char unit = 'M'; char unit_buf[10]; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index ffa1d0653861..39345c2ddfc2 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -79,6 +79,11 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { ID(TRANSACTION_START, cpu/tx-start/), ID(ELISION_START, cpu/el-start/), ID(CYCLES_IN_TX_CP, cpu/cycles-ct/), + ID(TOPDOWN_TOTAL_SLOTS, topdown-total-slots), + ID(TOPDOWN_SLOTS_ISSUED, topdown-slots-issued), + ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired), + ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles), + ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles), }; #undef ID @@ -157,7 +162,7 @@ int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw) { struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { if (perf_evsel__alloc_stats(evsel, alloc_raw)) goto out_free; } @@ -173,7 +178,7 @@ void perf_evlist__free_stats(struct perf_evlist *evlist) { struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { perf_evsel__free_stat_priv(evsel); perf_evsel__free_counts(evsel); perf_evsel__free_prev_raw_counts(evsel); @@ -184,7 +189,7 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist) { struct perf_evsel *evsel; - evlist__for_each(evlist, evsel) { + evlist__for_each_entry(evlist, evsel) { perf_evsel__reset_stat_priv(evsel); perf_evsel__reset_counts(evsel); } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 0150e786ccc7..c29bb94c48a4 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -17,6 +17,11 @@ enum perf_stat_evsel_id { PERF_STAT_EVSEL_ID__TRANSACTION_START, PERF_STAT_EVSEL_ID__ELISION_START, PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP, + PERF_STAT_EVSEL_ID__TOPDOWN_TOTAL_SLOTS, + PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_ISSUED, + PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED, + PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES, + PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES, PERF_STAT_EVSEL_ID__MAX, }; diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c index f95f682aa2b2..817593908d47 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -1,5 +1,5 @@ #include "debug.h" -#include "cache.h" +#include "util.h" #include <linux/kernel.h> int prefixcmp(const char *str, const char *prefix) diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h index 54b409297d4a..b268a6648a5d 100644 --- a/tools/perf/util/strbuf.h +++ b/tools/perf/util/strbuf.h @@ -40,6 +40,9 @@ #include <assert.h> #include <stdarg.h> +#include <stddef.h> +#include <string.h> +#include <sys/types.h> extern char strbuf_slopbuf[]; struct strbuf { diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h index ca990029e243..19207e50fce5 100644 --- a/tools/perf/util/strlist.h +++ b/tools/perf/util/strlist.h @@ -73,7 +73,7 @@ static inline struct str_node *strlist__next(struct str_node *sn) * @pos: the &struct str_node to use as a loop cursor. * @slist: the &struct strlist for loop. */ -#define strlist__for_each(pos, slist) \ +#define strlist__for_each_entry(pos, slist) \ for (pos = strlist__first(slist); pos; pos = strlist__next(pos)) /** @@ -83,7 +83,7 @@ static inline struct str_node *strlist__next(struct str_node *sn) * @n: another &struct str_node to use as temporary storage. * @slist: the &struct strlist for loop. */ -#define strlist__for_each_safe(pos, n, slist) \ +#define strlist__for_each_entry_safe(pos, n, slist) \ for (pos = strlist__first(slist), n = strlist__next(pos); pos;\ pos = n, n = strlist__next(n)) #endif /* __PERF_STRLIST_H */ diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 87a297dd8901..a34321e9b44d 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -7,6 +7,7 @@ #include "symbol.h" #include "demangle-java.h" +#include "demangle-rust.h" #include "machine.h" #include "vdso.h" #include <symbol/kallsyms.h> @@ -16,6 +17,7 @@ #define EM_AARCH64 183 /* ARM 64 bit */ #endif +typedef Elf64_Nhdr GElf_Nhdr; #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT extern char *cplus_demangle(const char *, int); @@ -54,6 +56,14 @@ static int elf_getphdrnum(Elf *elf, size_t *dst) } #endif +#ifndef HAVE_ELF_GETSHDRSTRNDX_SUPPORT +static int elf_getshdrstrndx(Elf *elf __maybe_unused, size_t *dst __maybe_unused) +{ + pr_err("%s: update your libelf to > 0.140, this one lacks elf_getshdrstrndx().\n", __func__); + return -1; +} +#endif + #ifndef NT_GNU_BUILD_ID #define NT_GNU_BUILD_ID 3 #endif @@ -1072,6 +1082,13 @@ new_symbol: demangled = bfd_demangle(NULL, elf_name, demangle_flags); if (demangled == NULL) demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET); + else if (rust_is_mangled(demangled)) + /* + * Input to Rust demangling is the BFD-demangled + * name which it Rust-demangles in place. + */ + rust_demangle_sym(demangled); + if (demangled != NULL) elf_name = demangled; } @@ -1781,6 +1798,260 @@ void kcore_extract__delete(struct kcore_extract *kce) unlink(kce->extract_filename); } +#ifdef HAVE_GELF_GETNOTE_SUPPORT +/** + * populate_sdt_note : Parse raw data and identify SDT note + * @elf: elf of the opened file + * @data: raw data of a section with description offset applied + * @len: note description size + * @type: type of the note + * @sdt_notes: List to add the SDT note + * + * Responsible for parsing the @data in section .note.stapsdt in @elf and + * if its an SDT note, it appends to @sdt_notes list. + */ +static int populate_sdt_note(Elf **elf, const char *data, size_t len, + struct list_head *sdt_notes) +{ + const char *provider, *name; + struct sdt_note *tmp = NULL; + GElf_Ehdr ehdr; + GElf_Addr base_off = 0; + GElf_Shdr shdr; + int ret = -EINVAL; + + union { + Elf64_Addr a64[NR_ADDR]; + Elf32_Addr a32[NR_ADDR]; + } buf; + + Elf_Data dst = { + .d_buf = &buf, .d_type = ELF_T_ADDR, .d_version = EV_CURRENT, + .d_size = gelf_fsize((*elf), ELF_T_ADDR, NR_ADDR, EV_CURRENT), + .d_off = 0, .d_align = 0 + }; + Elf_Data src = { + .d_buf = (void *) data, .d_type = ELF_T_ADDR, + .d_version = EV_CURRENT, .d_size = dst.d_size, .d_off = 0, + .d_align = 0 + }; + + tmp = (struct sdt_note *)calloc(1, sizeof(struct sdt_note)); + if (!tmp) { + ret = -ENOMEM; + goto out_err; + } + + INIT_LIST_HEAD(&tmp->note_list); + + if (len < dst.d_size + 3) + goto out_free_note; + + /* Translation from file representation to memory representation */ + if (gelf_xlatetom(*elf, &dst, &src, + elf_getident(*elf, NULL)[EI_DATA]) == NULL) { + pr_err("gelf_xlatetom : %s\n", elf_errmsg(-1)); + goto out_free_note; + } + + /* Populate the fields of sdt_note */ + provider = data + dst.d_size; + + name = (const char *)memchr(provider, '\0', data + len - provider); + if (name++ == NULL) + goto out_free_note; + + tmp->provider = strdup(provider); + if (!tmp->provider) { + ret = -ENOMEM; + goto out_free_note; + } + tmp->name = strdup(name); + if (!tmp->name) { + ret = -ENOMEM; + goto out_free_prov; + } + + if (gelf_getclass(*elf) == ELFCLASS32) { + memcpy(&tmp->addr, &buf, 3 * sizeof(Elf32_Addr)); + tmp->bit32 = true; + } else { + memcpy(&tmp->addr, &buf, 3 * sizeof(Elf64_Addr)); + tmp->bit32 = false; + } + + if (!gelf_getehdr(*elf, &ehdr)) { + pr_debug("%s : cannot get elf header.\n", __func__); + ret = -EBADF; + goto out_free_name; + } + + /* Adjust the prelink effect : + * Find out the .stapsdt.base section. + * This scn will help us to handle prelinking (if present). + * Compare the retrieved file offset of the base section with the + * base address in the description of the SDT note. If its different, + * then accordingly, adjust the note location. + */ + if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_BASE_SCN, NULL)) { + base_off = shdr.sh_offset; + if (base_off) { + if (tmp->bit32) + tmp->addr.a32[0] = tmp->addr.a32[0] + base_off - + tmp->addr.a32[1]; + else + tmp->addr.a64[0] = tmp->addr.a64[0] + base_off - + tmp->addr.a64[1]; + } + } + + list_add_tail(&tmp->note_list, sdt_notes); + return 0; + +out_free_name: + free(tmp->name); +out_free_prov: + free(tmp->provider); +out_free_note: + free(tmp); +out_err: + return ret; +} + +/** + * construct_sdt_notes_list : constructs a list of SDT notes + * @elf : elf to look into + * @sdt_notes : empty list_head + * + * Scans the sections in 'elf' for the section + * .note.stapsdt. It, then calls populate_sdt_note to find + * out the SDT events and populates the 'sdt_notes'. + */ +static int construct_sdt_notes_list(Elf *elf, struct list_head *sdt_notes) +{ + GElf_Ehdr ehdr; + Elf_Scn *scn = NULL; + Elf_Data *data; + GElf_Shdr shdr; + size_t shstrndx, next; + GElf_Nhdr nhdr; + size_t name_off, desc_off, offset; + int ret = 0; + + if (gelf_getehdr(elf, &ehdr) == NULL) { + ret = -EBADF; + goto out_ret; + } + if (elf_getshdrstrndx(elf, &shstrndx) != 0) { + ret = -EBADF; + goto out_ret; + } + + /* Look for the required section */ + scn = elf_section_by_name(elf, &ehdr, &shdr, SDT_NOTE_SCN, NULL); + if (!scn) { + ret = -ENOENT; + goto out_ret; + } + + if ((shdr.sh_type != SHT_NOTE) || (shdr.sh_flags & SHF_ALLOC)) { + ret = -ENOENT; + goto out_ret; + } + + data = elf_getdata(scn, NULL); + + /* Get the SDT notes */ + for (offset = 0; (next = gelf_getnote(data, offset, &nhdr, &name_off, + &desc_off)) > 0; offset = next) { + if (nhdr.n_namesz == sizeof(SDT_NOTE_NAME) && + !memcmp(data->d_buf + name_off, SDT_NOTE_NAME, + sizeof(SDT_NOTE_NAME))) { + /* Check the type of the note */ + if (nhdr.n_type != SDT_NOTE_TYPE) + goto out_ret; + + ret = populate_sdt_note(&elf, ((data->d_buf) + desc_off), + nhdr.n_descsz, sdt_notes); + if (ret < 0) + goto out_ret; + } + } + if (list_empty(sdt_notes)) + ret = -ENOENT; + +out_ret: + return ret; +} + +/** + * get_sdt_note_list : Wrapper to construct a list of sdt notes + * @head : empty list_head + * @target : file to find SDT notes from + * + * This opens the file, initializes + * the ELF and then calls construct_sdt_notes_list. + */ +int get_sdt_note_list(struct list_head *head, const char *target) +{ + Elf *elf; + int fd, ret; + + fd = open(target, O_RDONLY); + if (fd < 0) + return -EBADF; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (!elf) { + ret = -EBADF; + goto out_close; + } + ret = construct_sdt_notes_list(elf, head); + elf_end(elf); +out_close: + close(fd); + return ret; +} + +/** + * cleanup_sdt_note_list : free the sdt notes' list + * @sdt_notes: sdt notes' list + * + * Free up the SDT notes in @sdt_notes. + * Returns the number of SDT notes free'd. + */ +int cleanup_sdt_note_list(struct list_head *sdt_notes) +{ + struct sdt_note *tmp, *pos; + int nr_free = 0; + + list_for_each_entry_safe(pos, tmp, sdt_notes, note_list) { + list_del(&pos->note_list); + free(pos->name); + free(pos->provider); + free(pos); + nr_free++; + } + return nr_free; +} + +/** + * sdt_notes__get_count: Counts the number of sdt events + * @start: list_head to sdt_notes list + * + * Returns the number of SDT notes in a list + */ +int sdt_notes__get_count(struct list_head *start) +{ + struct sdt_note *sdt_ptr; + int count = 0; + + list_for_each_entry(sdt_ptr, start, note_list) + count++; + return count; +} +#endif + void symbol__elf_init(void) { elf_version(EV_CURRENT); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 20f9cb32b703..37e8d20ae03e 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1430,7 +1430,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) * Read the build id if possible. This is required for * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work */ - if (is_regular_file(name) && + if (is_regular_file(dso->long_name) && filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) dso__set_build_id(dso, build_id); @@ -1626,7 +1626,7 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz) if (!dirs) return -1; - strlist__for_each(nd, dirs) { + strlist__for_each_entry(nd, dirs) { scnprintf(kallsyms_filename, sizeof(kallsyms_filename), "%s/%s/kallsyms", dir, nd->s); if (!validate_kcore_addresses(kallsyms_filename, map)) { @@ -1641,6 +1641,20 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz) return ret; } +/* + * Use open(O_RDONLY) to check readability directly instead of access(R_OK) + * since access(R_OK) only checks with real UID/GID but open() use effective + * UID/GID and actual capabilities (e.g. /proc/kcore requires CAP_SYS_RAWIO). + */ +static bool filename__readable(const char *file) +{ + int fd = open(file, O_RDONLY); + if (fd < 0) + return false; + close(fd); + return true; +} + static char *dso__find_kallsyms(struct dso *dso, struct map *map) { u8 host_build_id[BUILD_ID_SIZE]; @@ -1660,58 +1674,43 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map) sizeof(host_build_id)) == 0) is_host = dso__build_id_equal(dso, host_build_id); - build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); - - scnprintf(path, sizeof(path), "%s/%s/%s", buildid_dir, - DSO__NAME_KCORE, sbuild_id); - - /* Use /proc/kallsyms if possible */ + /* Try a fast path for /proc/kallsyms if possible */ if (is_host) { - DIR *d; - int fd; - - /* If no cached kcore go with /proc/kallsyms */ - d = opendir(path); - if (!d) - goto proc_kallsyms; - closedir(d); - /* - * Do not check the build-id cache, until we know we cannot use - * /proc/kcore. + * Do not check the build-id cache, unless we know we cannot use + * /proc/kcore or module maps don't match to /proc/kallsyms. + * To check readability of /proc/kcore, do not use access(R_OK) + * since /proc/kcore requires CAP_SYS_RAWIO to read and access + * can't check it. */ - fd = open("/proc/kcore", O_RDONLY); - if (fd != -1) { - close(fd); - /* If module maps match go with /proc/kallsyms */ - if (!validate_kcore_addresses("/proc/kallsyms", map)) - goto proc_kallsyms; - } - - /* Find kallsyms in build-id cache with kcore */ - if (!find_matching_kcore(map, path, sizeof(path))) - return strdup(path); - - goto proc_kallsyms; + if (filename__readable("/proc/kcore") && + !validate_kcore_addresses("/proc/kallsyms", map)) + goto proc_kallsyms; } + build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id); + /* Find kallsyms in build-id cache with kcore */ + scnprintf(path, sizeof(path), "%s/%s/%s", + buildid_dir, DSO__NAME_KCORE, sbuild_id); + if (!find_matching_kcore(map, path, sizeof(path))) return strdup(path); - scnprintf(path, sizeof(path), "%s/%s/%s", - buildid_dir, DSO__NAME_KALLSYMS, sbuild_id); + /* Use current /proc/kallsyms if possible */ + if (is_host) { +proc_kallsyms: + return strdup("/proc/kallsyms"); + } - if (access(path, F_OK)) { + /* Finally, find a cache of kallsyms */ + if (!build_id_cache__kallsyms_path(sbuild_id, path, sizeof(path))) { pr_err("No kallsyms or vmlinux with build-id %s was found\n", sbuild_id); return NULL; } return strdup(path); - -proc_kallsyms: - return strdup("/proc/kallsyms"); } static int dso__load_kernel_sym(struct dso *dso, struct map *map, @@ -1933,17 +1932,17 @@ int setup_intlist(struct intlist **list, const char *list_str, static bool symbol__read_kptr_restrict(void) { bool value = false; + FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r"); - if (geteuid() != 0) { - FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r"); - if (fp != NULL) { - char line[8]; + if (fp != NULL) { + char line[8]; - if (fgets(line, sizeof(line), fp) != NULL) - value = atoi(line) != 0; + if (fgets(line, sizeof(line), fp) != NULL) + value = (geteuid() != 0) ? + (atoi(line) != 0) : + (atoi(line) == 2); - fclose(fp); - } + fclose(fp); } return value; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index b10d558a8803..699f7cbcfe72 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -342,4 +342,26 @@ void arch__sym_update(struct symbol *s, GElf_Sym *sym); int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb); +/* structure containing an SDT note's info */ +struct sdt_note { + char *name; /* name of the note*/ + char *provider; /* provider name */ + bool bit32; /* whether the location is 32 bits? */ + union { /* location, base and semaphore addrs */ + Elf64_Addr a64[3]; + Elf32_Addr a32[3]; + } addr; + struct list_head note_list; /* SDT notes' list */ +}; + +int get_sdt_note_list(struct list_head *head, const char *target); +int cleanup_sdt_note_list(struct list_head *sdt_notes); +int sdt_notes__get_count(struct list_head *start); + +#define SDT_BASE_SCN ".stapsdt.base" +#define SDT_NOTE_SCN ".note.stapsdt" +#define SDT_NOTE_TYPE 3 +#define SDT_NOTE_NAME "stapsdt" +#define NR_ADDR 3 + #endif /* __PERF_SYMBOL */ diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c index a53603b27e52..8cdcf4641c51 100644 --- a/tools/perf/util/target.c +++ b/tools/perf/util/target.c @@ -7,6 +7,7 @@ */ #include "target.h" +#include "util.h" #include "debug.h" #include <pwd.h> @@ -121,7 +122,7 @@ int target__strerror(struct target *target, int errnum, BUG_ON(buflen == 0); if (errnum >= 0) { - const char *err = strerror_r(errnum, buf, buflen); + const char *err = str_error_r(errnum, buf, buflen); if (err != buf) scnprintf(buf, buflen, "%s", err); diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c index 825086aa9a08..d3301529f6a7 100644 --- a/tools/perf/util/thread-stack.c +++ b/tools/perf/util/thread-stack.c @@ -616,3 +616,10 @@ int thread_stack__process(struct thread *thread, struct comm *comm, return err; } + +size_t thread_stack__depth(struct thread *thread) +{ + if (!thread->ts) + return 0; + return thread->ts->cnt; +} diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h index ad44c7944b8e..b7e41c4ebfdd 100644 --- a/tools/perf/util/thread-stack.h +++ b/tools/perf/util/thread-stack.h @@ -87,6 +87,7 @@ void thread_stack__sample(struct thread *thread, struct ip_callchain *chain, size_t sz, u64 ip); int thread_stack__flush(struct thread *thread); void thread_stack__free(struct thread *thread); +size_t thread_stack__depth(struct thread *thread); struct call_return_processor * call_return_processor__new(int (*process)(struct call_return *cr, void *data), diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 45fcb715a36b..8b10a55410a2 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -43,9 +43,6 @@ struct thread *thread__new(pid_t pid, pid_t tid) thread->cpu = -1; INIT_LIST_HEAD(&thread->comm_list); - if (unwind__prepare_access(thread) < 0) - goto err_thread; - comm_str = malloc(32); if (!comm_str) goto err_thread; @@ -201,10 +198,51 @@ size_t thread__fprintf(struct thread *thread, FILE *fp) map_groups__fprintf(thread->mg, fp); } -void thread__insert_map(struct thread *thread, struct map *map) +int thread__insert_map(struct thread *thread, struct map *map) { + int ret; + + ret = unwind__prepare_access(thread, map, NULL); + if (ret) + return ret; + map_groups__fixup_overlappings(thread->mg, map, stderr); map_groups__insert(thread->mg, map); + + return 0; +} + +static int __thread__prepare_access(struct thread *thread) +{ + bool initialized = false; + int i, err = 0; + + for (i = 0; i < MAP__NR_TYPES; ++i) { + struct maps *maps = &thread->mg->maps[i]; + struct map *map; + + pthread_rwlock_rdlock(&maps->lock); + + for (map = maps__first(maps); map; map = map__next(map)) { + err = unwind__prepare_access(thread, map, &initialized); + if (err || initialized) + break; + } + + pthread_rwlock_unlock(&maps->lock); + } + + return err; +} + +static int thread__prepare_access(struct thread *thread) +{ + int err = 0; + + if (symbol_conf.use_callchain) + err = __thread__prepare_access(thread); + + return err; } static int thread__clone_map_groups(struct thread *thread, @@ -214,7 +252,7 @@ static int thread__clone_map_groups(struct thread *thread, /* This is new thread, we share map groups for process. */ if (thread->pid_ == parent->pid_) - return 0; + return thread__prepare_access(thread); if (thread->mg == parent->mg) { pr_debug("broken map groups on thread %d/%d parent %d/%d\n", @@ -224,7 +262,7 @@ static int thread__clone_map_groups(struct thread *thread, /* But this one is new process, copy maps. */ for (i = 0; i < MAP__NR_TYPES; ++i) - if (map_groups__clone(thread->mg, parent->mg, i) < 0) + if (map_groups__clone(thread, parent->mg, i) < 0) return -ENOMEM; return 0; @@ -265,3 +303,14 @@ void thread__find_cpumode_addr_location(struct thread *thread, break; } } + +struct thread *thread__main_thread(struct machine *machine, struct thread *thread) +{ + if (thread->pid_ == thread->tid) + return thread__get(thread); + + if (thread->pid_ == -1) + return NULL; + + return machine__find_thread(machine, thread->pid_, thread->pid_); +} diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 45fba13c800b..99263cb6e6b6 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -9,11 +9,9 @@ #include "symbol.h" #include <strlist.h> #include <intlist.h> -#ifdef HAVE_LIBUNWIND_SUPPORT -#include <libunwind.h> -#endif struct thread_stack; +struct unwind_libunwind_ops; struct thread { union { @@ -36,7 +34,8 @@ struct thread { void *priv; struct thread_stack *ts; #ifdef HAVE_LIBUNWIND_SUPPORT - unw_addr_space_t addr_space; + void *addr_space; + struct unwind_libunwind_ops *unwind_libunwind_ops; #endif }; @@ -77,10 +76,12 @@ int thread__comm_len(struct thread *thread); struct comm *thread__comm(const struct thread *thread); struct comm *thread__exec_comm(const struct thread *thread); const char *thread__comm_str(const struct thread *thread); -void thread__insert_map(struct thread *thread, struct map *map); +int thread__insert_map(struct thread *thread, struct map *map); int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp); size_t thread__fprintf(struct thread *thread, FILE *fp); +struct thread *thread__main_thread(struct machine *machine, struct thread *thread); + void thread__find_addr_map(struct thread *thread, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al); diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 5654fe15e036..40585f5b7027 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -202,7 +202,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str) if (!slist) return NULL; - strlist__for_each(pos, slist) { + strlist__for_each_entry(pos, slist) { pid = strtol(pos->s, &end_ptr, 10); if (pid == INT_MIN || pid == INT_MAX || @@ -278,7 +278,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str) if (!slist) return NULL; - strlist__for_each(pos, slist) { + strlist__for_each_entry(pos, slist) { tid = strtol(pos->s, &end_ptr, 10); if (tid == INT_MIN || tid == INT_MAX || diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c index 8ae051e0ec79..c330780674fc 100644 --- a/tools/perf/util/trace-event.c +++ b/tools/perf/util/trace-event.c @@ -105,3 +105,11 @@ trace_event__tp_format(const char *sys, const char *name) return tp_format(sys, name); } + +struct event_format *trace_event__tp_format_id(int id) +{ + if (!tevent_initialized && trace_event__init2()) + return ERR_PTR(-ENOMEM); + + return pevent_find_event(tevent.pevent, id); +} diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index bce5b1dac268..b0af9c81bb0d 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -23,6 +23,8 @@ int trace_event__register_resolver(struct machine *machine, struct event_format* trace_event__tp_format(const char *sys, const char *name); +struct event_format *trace_event__tp_format_id(int id); + int bigendian(void); void event_format__fprintf(struct event_format *event, diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c new file mode 100644 index 000000000000..97c0f8fc5561 --- /dev/null +++ b/tools/perf/util/unwind-libunwind-local.c @@ -0,0 +1,699 @@ +/* + * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps. + * + * Lots of this code have been borrowed or heavily inspired from parts of + * the libunwind 0.99 code which are (amongst other contributors I may have + * forgotten): + * + * Copyright (C) 2002-2007 Hewlett-Packard Co + * Contributed by David Mosberger-Tang <davidm@hpl.hp.com> + * + * And the bugs have been added by: + * + * Copyright (C) 2010, Frederic Weisbecker <fweisbec@gmail.com> + * Copyright (C) 2012, Jiri Olsa <jolsa@redhat.com> + * + */ + +#include <elf.h> +#include <gelf.h> +#include <fcntl.h> +#include <string.h> +#include <unistd.h> +#include <sys/mman.h> +#include <linux/list.h> +#ifndef REMOTE_UNWIND_LIBUNWIND +#include <libunwind.h> +#include <libunwind-ptrace.h> +#endif +#include "callchain.h" +#include "thread.h" +#include "session.h" +#include "perf_regs.h" +#include "unwind.h" +#include "symbol.h" +#include "util.h" +#include "debug.h" +#include "asm/bug.h" + +extern int +UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, + unw_word_t ip, + unw_dyn_info_t *di, + unw_proc_info_t *pi, + int need_unwind_info, void *arg); + +#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) + +extern int +UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug, + unw_word_t ip, + unw_word_t segbase, + const char *obj_name, unw_word_t start, + unw_word_t end); + +#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame) + +#define DW_EH_PE_FORMAT_MASK 0x0f /* format of the encoded value */ +#define DW_EH_PE_APPL_MASK 0x70 /* how the value is to be applied */ + +/* Pointer-encoding formats: */ +#define DW_EH_PE_omit 0xff +#define DW_EH_PE_ptr 0x00 /* pointer-sized unsigned value */ +#define DW_EH_PE_udata4 0x03 /* unsigned 32-bit value */ +#define DW_EH_PE_udata8 0x04 /* unsigned 64-bit value */ +#define DW_EH_PE_sdata4 0x0b /* signed 32-bit value */ +#define DW_EH_PE_sdata8 0x0c /* signed 64-bit value */ + +/* Pointer-encoding application: */ +#define DW_EH_PE_absptr 0x00 /* absolute value */ +#define DW_EH_PE_pcrel 0x10 /* rel. to addr. of encoded value */ + +/* + * The following are not documented by LSB v1.3, yet they are used by + * GCC, presumably they aren't documented by LSB since they aren't + * used on Linux: + */ +#define DW_EH_PE_funcrel 0x40 /* start-of-procedure-relative */ +#define DW_EH_PE_aligned 0x50 /* aligned pointer */ + +/* Flags intentionaly not handled, since they're not needed: + * #define DW_EH_PE_indirect 0x80 + * #define DW_EH_PE_uleb128 0x01 + * #define DW_EH_PE_udata2 0x02 + * #define DW_EH_PE_sleb128 0x09 + * #define DW_EH_PE_sdata2 0x0a + * #define DW_EH_PE_textrel 0x20 + * #define DW_EH_PE_datarel 0x30 + */ + +struct unwind_info { + struct perf_sample *sample; + struct machine *machine; + struct thread *thread; +}; + +#define dw_read(ptr, type, end) ({ \ + type *__p = (type *) ptr; \ + type __v; \ + if ((__p + 1) > (type *) end) \ + return -EINVAL; \ + __v = *__p++; \ + ptr = (typeof(ptr)) __p; \ + __v; \ + }) + +static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val, + u8 encoding) +{ + u8 *cur = *p; + *val = 0; + + switch (encoding) { + case DW_EH_PE_omit: + *val = 0; + goto out; + case DW_EH_PE_ptr: + *val = dw_read(cur, unsigned long, end); + goto out; + default: + break; + } + + switch (encoding & DW_EH_PE_APPL_MASK) { + case DW_EH_PE_absptr: + break; + case DW_EH_PE_pcrel: + *val = (unsigned long) cur; + break; + default: + return -EINVAL; + } + + if ((encoding & 0x07) == 0x00) + encoding |= DW_EH_PE_udata4; + + switch (encoding & DW_EH_PE_FORMAT_MASK) { + case DW_EH_PE_sdata4: + *val += dw_read(cur, s32, end); + break; + case DW_EH_PE_udata4: + *val += dw_read(cur, u32, end); + break; + case DW_EH_PE_sdata8: + *val += dw_read(cur, s64, end); + break; + case DW_EH_PE_udata8: + *val += dw_read(cur, u64, end); + break; + default: + return -EINVAL; + } + + out: + *p = cur; + return 0; +} + +#define dw_read_encoded_value(ptr, end, enc) ({ \ + u64 __v; \ + if (__dw_read_encoded_value(&ptr, end, &__v, enc)) { \ + return -EINVAL; \ + } \ + __v; \ + }) + +static u64 elf_section_offset(int fd, const char *name) +{ + Elf *elf; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + u64 offset = 0; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + return 0; + + do { + if (gelf_getehdr(elf, &ehdr) == NULL) + break; + + if (!elf_section_by_name(elf, &ehdr, &shdr, name, NULL)) + break; + + offset = shdr.sh_offset; + } while (0); + + elf_end(elf); + return offset; +} + +#ifndef NO_LIBUNWIND_DEBUG_FRAME +static int elf_is_exec(int fd, const char *name) +{ + Elf *elf; + GElf_Ehdr ehdr; + int retval = 0; + + elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); + if (elf == NULL) + return 0; + if (gelf_getehdr(elf, &ehdr) == NULL) + goto out; + + retval = (ehdr.e_type == ET_EXEC); + +out: + elf_end(elf); + pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval); + return retval; +} +#endif + +struct table_entry { + u32 start_ip_offset; + u32 fde_offset; +}; + +struct eh_frame_hdr { + unsigned char version; + unsigned char eh_frame_ptr_enc; + unsigned char fde_count_enc; + unsigned char table_enc; + + /* + * The rest of the header is variable-length and consists of the + * following members: + * + * encoded_t eh_frame_ptr; + * encoded_t fde_count; + */ + + /* A single encoded pointer should not be more than 8 bytes. */ + u64 enc[2]; + + /* + * struct { + * encoded_t start_ip; + * encoded_t fde_addr; + * } binary_search_table[fde_count]; + */ + char data[0]; +} __packed; + +static int unwind_spec_ehframe(struct dso *dso, struct machine *machine, + u64 offset, u64 *table_data, u64 *segbase, + u64 *fde_count) +{ + struct eh_frame_hdr hdr; + u8 *enc = (u8 *) &hdr.enc; + u8 *end = (u8 *) &hdr.data; + ssize_t r; + + r = dso__data_read_offset(dso, machine, offset, + (u8 *) &hdr, sizeof(hdr)); + if (r != sizeof(hdr)) + return -EINVAL; + + /* We dont need eh_frame_ptr, just skip it. */ + dw_read_encoded_value(enc, end, hdr.eh_frame_ptr_enc); + + *fde_count = dw_read_encoded_value(enc, end, hdr.fde_count_enc); + *segbase = offset; + *table_data = (enc - (u8 *) &hdr) + offset; + return 0; +} + +static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, + u64 *table_data, u64 *segbase, + u64 *fde_count) +{ + int ret = -EINVAL, fd; + u64 offset = dso->data.eh_frame_hdr_offset; + + if (offset == 0) { + fd = dso__data_get_fd(dso, machine); + if (fd < 0) + return -EINVAL; + + /* Check the .eh_frame section for unwinding info */ + offset = elf_section_offset(fd, ".eh_frame_hdr"); + dso->data.eh_frame_hdr_offset = offset; + dso__data_put_fd(dso); + } + + if (offset) + ret = unwind_spec_ehframe(dso, machine, offset, + table_data, segbase, + fde_count); + + return ret; +} + +#ifndef NO_LIBUNWIND_DEBUG_FRAME +static int read_unwind_spec_debug_frame(struct dso *dso, + struct machine *machine, u64 *offset) +{ + int fd; + u64 ofs = dso->data.debug_frame_offset; + + if (ofs == 0) { + fd = dso__data_get_fd(dso, machine); + if (fd < 0) + return -EINVAL; + + /* Check the .debug_frame section for unwinding info */ + ofs = elf_section_offset(fd, ".debug_frame"); + dso->data.debug_frame_offset = ofs; + dso__data_put_fd(dso); + } + + *offset = ofs; + if (*offset) + return 0; + + return -EINVAL; +} +#endif + +static struct map *find_map(unw_word_t ip, struct unwind_info *ui) +{ + struct addr_location al; + + thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, + MAP__FUNCTION, ip, &al); + if (!al.map) { + /* + * We've seen cases (softice) where DWARF unwinder went + * through non executable mmaps, which we need to lookup + * in MAP__VARIABLE tree. + */ + thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, + MAP__VARIABLE, ip, &al); + } + return al.map; +} + +static int +find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, + int need_unwind_info, void *arg) +{ + struct unwind_info *ui = arg; + struct map *map; + unw_dyn_info_t di; + u64 table_data, segbase, fde_count; + int ret = -EINVAL; + + map = find_map(ip, ui); + if (!map || !map->dso) + return -EINVAL; + + pr_debug("unwind: find_proc_info dso %s\n", map->dso->name); + + /* Check the .eh_frame section for unwinding info */ + if (!read_unwind_spec_eh_frame(map->dso, ui->machine, + &table_data, &segbase, &fde_count)) { + memset(&di, 0, sizeof(di)); + di.format = UNW_INFO_FORMAT_REMOTE_TABLE; + di.start_ip = map->start; + di.end_ip = map->end; + di.u.rti.segbase = map->start + segbase; + di.u.rti.table_data = map->start + table_data; + di.u.rti.table_len = fde_count * sizeof(struct table_entry) + / sizeof(unw_word_t); + ret = dwarf_search_unwind_table(as, ip, &di, pi, + need_unwind_info, arg); + } + +#ifndef NO_LIBUNWIND_DEBUG_FRAME + /* Check the .debug_frame section for unwinding info */ + if (ret < 0 && + !read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) { + int fd = dso__data_get_fd(map->dso, ui->machine); + int is_exec = elf_is_exec(fd, map->dso->name); + unw_word_t base = is_exec ? 0 : map->start; + const char *symfile; + + if (fd >= 0) + dso__data_put_fd(map->dso); + + symfile = map->dso->symsrc_filename ?: map->dso->name; + + memset(&di, 0, sizeof(di)); + if (dwarf_find_debug_frame(0, &di, ip, base, symfile, + map->start, map->end)) + return dwarf_search_unwind_table(as, ip, &di, pi, + need_unwind_info, arg); + } +#endif + + return ret; +} + +static int access_fpreg(unw_addr_space_t __maybe_unused as, + unw_regnum_t __maybe_unused num, + unw_fpreg_t __maybe_unused *val, + int __maybe_unused __write, + void __maybe_unused *arg) +{ + pr_err("unwind: access_fpreg unsupported\n"); + return -UNW_EINVAL; +} + +static int get_dyn_info_list_addr(unw_addr_space_t __maybe_unused as, + unw_word_t __maybe_unused *dil_addr, + void __maybe_unused *arg) +{ + return -UNW_ENOINFO; +} + +static int resume(unw_addr_space_t __maybe_unused as, + unw_cursor_t __maybe_unused *cu, + void __maybe_unused *arg) +{ + pr_err("unwind: resume unsupported\n"); + return -UNW_EINVAL; +} + +static int +get_proc_name(unw_addr_space_t __maybe_unused as, + unw_word_t __maybe_unused addr, + char __maybe_unused *bufp, size_t __maybe_unused buf_len, + unw_word_t __maybe_unused *offp, void __maybe_unused *arg) +{ + pr_err("unwind: get_proc_name unsupported\n"); + return -UNW_EINVAL; +} + +static int access_dso_mem(struct unwind_info *ui, unw_word_t addr, + unw_word_t *data) +{ + struct map *map; + ssize_t size; + + map = find_map(addr, ui); + if (!map) { + pr_debug("unwind: no map for %lx\n", (unsigned long)addr); + return -1; + } + + if (!map->dso) + return -1; + + size = dso__data_read_addr(map->dso, map, ui->machine, + addr, (u8 *) data, sizeof(*data)); + + return !(size == sizeof(*data)); +} + +static int access_mem(unw_addr_space_t __maybe_unused as, + unw_word_t addr, unw_word_t *valp, + int __write, void *arg) +{ + struct unwind_info *ui = arg; + struct stack_dump *stack = &ui->sample->user_stack; + u64 start, end; + int offset; + int ret; + + /* Don't support write, probably not needed. */ + if (__write || !stack || !ui->sample->user_regs.regs) { + *valp = 0; + return 0; + } + + ret = perf_reg_value(&start, &ui->sample->user_regs, + LIBUNWIND__ARCH_REG_SP); + if (ret) + return ret; + + end = start + stack->size; + + /* Check overflow. */ + if (addr + sizeof(unw_word_t) < addr) + return -EINVAL; + + if (addr < start || addr + sizeof(unw_word_t) >= end) { + ret = access_dso_mem(ui, addr, valp); + if (ret) { + pr_debug("unwind: access_mem %p not inside range" + " 0x%" PRIx64 "-0x%" PRIx64 "\n", + (void *) (uintptr_t) addr, start, end); + *valp = 0; + return ret; + } + return 0; + } + + offset = addr - start; + *valp = *(unw_word_t *)&stack->data[offset]; + pr_debug("unwind: access_mem addr %p val %lx, offset %d\n", + (void *) (uintptr_t) addr, (unsigned long)*valp, offset); + return 0; +} + +static int access_reg(unw_addr_space_t __maybe_unused as, + unw_regnum_t regnum, unw_word_t *valp, + int __write, void *arg) +{ + struct unwind_info *ui = arg; + int id, ret; + u64 val; + + /* Don't support write, I suspect we don't need it. */ + if (__write) { + pr_err("unwind: access_reg w %d\n", regnum); + return 0; + } + + if (!ui->sample->user_regs.regs) { + *valp = 0; + return 0; + } + + id = LIBUNWIND__ARCH_REG_ID(regnum); + if (id < 0) + return -EINVAL; + + ret = perf_reg_value(&val, &ui->sample->user_regs, id); + if (ret) { + pr_err("unwind: can't read reg %d\n", regnum); + return ret; + } + + *valp = (unw_word_t) val; + pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp); + return 0; +} + +static void put_unwind_info(unw_addr_space_t __maybe_unused as, + unw_proc_info_t *pi __maybe_unused, + void *arg __maybe_unused) +{ + pr_debug("unwind: put_unwind_info called\n"); +} + +static int entry(u64 ip, struct thread *thread, + unwind_entry_cb_t cb, void *arg) +{ + struct unwind_entry e; + struct addr_location al; + + thread__find_addr_location(thread, PERF_RECORD_MISC_USER, + MAP__FUNCTION, ip, &al); + + e.ip = ip; + e.map = al.map; + e.sym = al.sym; + + pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", + al.sym ? al.sym->name : "''", + ip, + al.map ? al.map->map_ip(al.map, ip) : (u64) 0); + + return cb(&e, arg); +} + +static void display_error(int err) +{ + switch (err) { + case UNW_EINVAL: + pr_err("unwind: Only supports local.\n"); + break; + case UNW_EUNSPEC: + pr_err("unwind: Unspecified error.\n"); + break; + case UNW_EBADREG: + pr_err("unwind: Register unavailable.\n"); + break; + default: + break; + } +} + +static unw_accessors_t accessors = { + .find_proc_info = find_proc_info, + .put_unwind_info = put_unwind_info, + .get_dyn_info_list_addr = get_dyn_info_list_addr, + .access_mem = access_mem, + .access_reg = access_reg, + .access_fpreg = access_fpreg, + .resume = resume, + .get_proc_name = get_proc_name, +}; + +static int _unwind__prepare_access(struct thread *thread) +{ + if (callchain_param.record_mode != CALLCHAIN_DWARF) + return 0; + + thread->addr_space = unw_create_addr_space(&accessors, 0); + if (!thread->addr_space) { + pr_err("unwind: Can't create unwind address space.\n"); + return -ENOMEM; + } + + unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL); + return 0; +} + +static void _unwind__flush_access(struct thread *thread) +{ + if (callchain_param.record_mode != CALLCHAIN_DWARF) + return; + + unw_flush_cache(thread->addr_space, 0, 0); +} + +static void _unwind__finish_access(struct thread *thread) +{ + if (callchain_param.record_mode != CALLCHAIN_DWARF) + return; + + unw_destroy_addr_space(thread->addr_space); +} + +static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, + void *arg, int max_stack) +{ + u64 val; + unw_word_t ips[max_stack]; + unw_addr_space_t addr_space; + unw_cursor_t c; + int ret, i = 0; + + ret = perf_reg_value(&val, &ui->sample->user_regs, + LIBUNWIND__ARCH_REG_IP); + if (ret) + return ret; + + ips[i++] = (unw_word_t) val; + + /* + * If we need more than one entry, do the DWARF + * unwind itself. + */ + if (max_stack - 1 > 0) { + WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL"); + addr_space = ui->thread->addr_space; + + if (addr_space == NULL) + return -1; + + ret = unw_init_remote(&c, addr_space, ui); + if (ret) + display_error(ret); + + while (!ret && (unw_step(&c) > 0) && i < max_stack) { + unw_get_reg(&c, UNW_REG_IP, &ips[i]); + ++i; + } + + max_stack = i; + } + + /* + * Display what we got based on the order setup. + */ + for (i = 0; i < max_stack && !ret; i++) { + int j = i; + + if (callchain_param.order == ORDER_CALLER) + j = max_stack - i - 1; + ret = ips[j] ? entry(ips[j], ui->thread, cb, arg) : 0; + } + + return ret; +} + +static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg, + struct thread *thread, + struct perf_sample *data, int max_stack) +{ + struct unwind_info ui = { + .sample = data, + .thread = thread, + .machine = thread->mg->machine, + }; + + if (!data->user_regs.regs) + return -EINVAL; + + if (max_stack <= 0) + return -EINVAL; + + return get_entries(&ui, cb, arg, max_stack); +} + +static struct unwind_libunwind_ops +_unwind_libunwind_ops = { + .prepare_access = _unwind__prepare_access, + .flush_access = _unwind__flush_access, + .finish_access = _unwind__finish_access, + .get_entries = _unwind__get_entries, +}; + +#ifndef REMOTE_UNWIND_LIBUNWIND +struct unwind_libunwind_ops * +local_unwind_libunwind_ops = &_unwind_libunwind_ops; +#endif diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 63687d3a344e..6d542a4e0648 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -1,682 +1,83 @@ -/* - * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps. - * - * Lots of this code have been borrowed or heavily inspired from parts of - * the libunwind 0.99 code which are (amongst other contributors I may have - * forgotten): - * - * Copyright (C) 2002-2007 Hewlett-Packard Co - * Contributed by David Mosberger-Tang <davidm@hpl.hp.com> - * - * And the bugs have been added by: - * - * Copyright (C) 2010, Frederic Weisbecker <fweisbec@gmail.com> - * Copyright (C) 2012, Jiri Olsa <jolsa@redhat.com> - * - */ - -#include <elf.h> -#include <gelf.h> -#include <fcntl.h> -#include <string.h> -#include <unistd.h> -#include <sys/mman.h> -#include <linux/list.h> -#include <libunwind.h> -#include <libunwind-ptrace.h> -#include "callchain.h" +#include "unwind.h" #include "thread.h" #include "session.h" -#include "perf_regs.h" -#include "unwind.h" -#include "symbol.h" -#include "util.h" #include "debug.h" -#include "asm/bug.h" - -extern int -UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, - unw_word_t ip, - unw_dyn_info_t *di, - unw_proc_info_t *pi, - int need_unwind_info, void *arg); - -#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) - -extern int -UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug, - unw_word_t ip, - unw_word_t segbase, - const char *obj_name, unw_word_t start, - unw_word_t end); - -#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame) - -#define DW_EH_PE_FORMAT_MASK 0x0f /* format of the encoded value */ -#define DW_EH_PE_APPL_MASK 0x70 /* how the value is to be applied */ - -/* Pointer-encoding formats: */ -#define DW_EH_PE_omit 0xff -#define DW_EH_PE_ptr 0x00 /* pointer-sized unsigned value */ -#define DW_EH_PE_udata4 0x03 /* unsigned 32-bit value */ -#define DW_EH_PE_udata8 0x04 /* unsigned 64-bit value */ -#define DW_EH_PE_sdata4 0x0b /* signed 32-bit value */ -#define DW_EH_PE_sdata8 0x0c /* signed 64-bit value */ - -/* Pointer-encoding application: */ -#define DW_EH_PE_absptr 0x00 /* absolute value */ -#define DW_EH_PE_pcrel 0x10 /* rel. to addr. of encoded value */ - -/* - * The following are not documented by LSB v1.3, yet they are used by - * GCC, presumably they aren't documented by LSB since they aren't - * used on Linux: - */ -#define DW_EH_PE_funcrel 0x40 /* start-of-procedure-relative */ -#define DW_EH_PE_aligned 0x50 /* aligned pointer */ +#include "arch/common.h" -/* Flags intentionaly not handled, since they're not needed: - * #define DW_EH_PE_indirect 0x80 - * #define DW_EH_PE_uleb128 0x01 - * #define DW_EH_PE_udata2 0x02 - * #define DW_EH_PE_sleb128 0x09 - * #define DW_EH_PE_sdata2 0x0a - * #define DW_EH_PE_textrel 0x20 - * #define DW_EH_PE_datarel 0x30 - */ +struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops; +struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops; +struct unwind_libunwind_ops __weak *arm64_unwind_libunwind_ops; -struct unwind_info { - struct perf_sample *sample; - struct machine *machine; - struct thread *thread; -}; - -#define dw_read(ptr, type, end) ({ \ - type *__p = (type *) ptr; \ - type __v; \ - if ((__p + 1) > (type *) end) \ - return -EINVAL; \ - __v = *__p++; \ - ptr = (typeof(ptr)) __p; \ - __v; \ - }) - -static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val, - u8 encoding) +static void unwind__register_ops(struct thread *thread, + struct unwind_libunwind_ops *ops) { - u8 *cur = *p; - *val = 0; - - switch (encoding) { - case DW_EH_PE_omit: - *val = 0; - goto out; - case DW_EH_PE_ptr: - *val = dw_read(cur, unsigned long, end); - goto out; - default: - break; - } - - switch (encoding & DW_EH_PE_APPL_MASK) { - case DW_EH_PE_absptr: - break; - case DW_EH_PE_pcrel: - *val = (unsigned long) cur; - break; - default: - return -EINVAL; - } - - if ((encoding & 0x07) == 0x00) - encoding |= DW_EH_PE_udata4; - - switch (encoding & DW_EH_PE_FORMAT_MASK) { - case DW_EH_PE_sdata4: - *val += dw_read(cur, s32, end); - break; - case DW_EH_PE_udata4: - *val += dw_read(cur, u32, end); - break; - case DW_EH_PE_sdata8: - *val += dw_read(cur, s64, end); - break; - case DW_EH_PE_udata8: - *val += dw_read(cur, u64, end); - break; - default: - return -EINVAL; - } - - out: - *p = cur; - return 0; -} - -#define dw_read_encoded_value(ptr, end, enc) ({ \ - u64 __v; \ - if (__dw_read_encoded_value(&ptr, end, &__v, enc)) { \ - return -EINVAL; \ - } \ - __v; \ - }) - -static u64 elf_section_offset(int fd, const char *name) -{ - Elf *elf; - GElf_Ehdr ehdr; - GElf_Shdr shdr; - u64 offset = 0; - - elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); - if (elf == NULL) - return 0; - - do { - if (gelf_getehdr(elf, &ehdr) == NULL) - break; - - if (!elf_section_by_name(elf, &ehdr, &shdr, name, NULL)) - break; - - offset = shdr.sh_offset; - } while (0); - - elf_end(elf); - return offset; + thread->unwind_libunwind_ops = ops; } -#ifndef NO_LIBUNWIND_DEBUG_FRAME -static int elf_is_exec(int fd, const char *name) +int unwind__prepare_access(struct thread *thread, struct map *map, + bool *initialized) { - Elf *elf; - GElf_Ehdr ehdr; - int retval = 0; + const char *arch; + enum dso_type dso_type; + struct unwind_libunwind_ops *ops = local_unwind_libunwind_ops; + int err; - elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL); - if (elf == NULL) + if (thread->addr_space) { + pr_debug("unwind: thread map already set, dso=%s\n", + map->dso->name); + if (initialized) + *initialized = true; return 0; - if (gelf_getehdr(elf, &ehdr) == NULL) - goto out; - - retval = (ehdr.e_type == ET_EXEC); - -out: - elf_end(elf); - pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval); - return retval; -} -#endif - -struct table_entry { - u32 start_ip_offset; - u32 fde_offset; -}; - -struct eh_frame_hdr { - unsigned char version; - unsigned char eh_frame_ptr_enc; - unsigned char fde_count_enc; - unsigned char table_enc; - - /* - * The rest of the header is variable-length and consists of the - * following members: - * - * encoded_t eh_frame_ptr; - * encoded_t fde_count; - */ - - /* A single encoded pointer should not be more than 8 bytes. */ - u64 enc[2]; - - /* - * struct { - * encoded_t start_ip; - * encoded_t fde_addr; - * } binary_search_table[fde_count]; - */ - char data[0]; -} __packed; - -static int unwind_spec_ehframe(struct dso *dso, struct machine *machine, - u64 offset, u64 *table_data, u64 *segbase, - u64 *fde_count) -{ - struct eh_frame_hdr hdr; - u8 *enc = (u8 *) &hdr.enc; - u8 *end = (u8 *) &hdr.data; - ssize_t r; - - r = dso__data_read_offset(dso, machine, offset, - (u8 *) &hdr, sizeof(hdr)); - if (r != sizeof(hdr)) - return -EINVAL; - - /* We dont need eh_frame_ptr, just skip it. */ - dw_read_encoded_value(enc, end, hdr.eh_frame_ptr_enc); - - *fde_count = dw_read_encoded_value(enc, end, hdr.fde_count_enc); - *segbase = offset; - *table_data = (enc - (u8 *) &hdr) + offset; - return 0; -} - -static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, - u64 *table_data, u64 *segbase, - u64 *fde_count) -{ - int ret = -EINVAL, fd; - u64 offset = dso->data.eh_frame_hdr_offset; - - if (offset == 0) { - fd = dso__data_get_fd(dso, machine); - if (fd < 0) - return -EINVAL; - - /* Check the .eh_frame section for unwinding info */ - offset = elf_section_offset(fd, ".eh_frame_hdr"); - dso->data.eh_frame_hdr_offset = offset; - dso__data_put_fd(dso); } - if (offset) - ret = unwind_spec_ehframe(dso, machine, offset, - table_data, segbase, - fde_count); + /* env->arch is NULL for live-mode (i.e. perf top) */ + if (!thread->mg->machine->env || !thread->mg->machine->env->arch) + goto out_register; - return ret; -} - -#ifndef NO_LIBUNWIND_DEBUG_FRAME -static int read_unwind_spec_debug_frame(struct dso *dso, - struct machine *machine, u64 *offset) -{ - int fd; - u64 ofs = dso->data.debug_frame_offset; - - if (ofs == 0) { - fd = dso__data_get_fd(dso, machine); - if (fd < 0) - return -EINVAL; - - /* Check the .debug_frame section for unwinding info */ - ofs = elf_section_offset(fd, ".debug_frame"); - dso->data.debug_frame_offset = ofs; - dso__data_put_fd(dso); - } - - *offset = ofs; - if (*offset) + dso_type = dso__type(map->dso, thread->mg->machine); + if (dso_type == DSO__TYPE_UNKNOWN) return 0; - return -EINVAL; -} -#endif - -static struct map *find_map(unw_word_t ip, struct unwind_info *ui) -{ - struct addr_location al; - - thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__FUNCTION, ip, &al); - if (!al.map) { - /* - * We've seen cases (softice) where DWARF unwinder went - * through non executable mmaps, which we need to lookup - * in MAP__VARIABLE tree. - */ - thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__VARIABLE, ip, &al); - } - return al.map; -} - -static int -find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, - int need_unwind_info, void *arg) -{ - struct unwind_info *ui = arg; - struct map *map; - unw_dyn_info_t di; - u64 table_data, segbase, fde_count; - int ret = -EINVAL; - - map = find_map(ip, ui); - if (!map || !map->dso) - return -EINVAL; - - pr_debug("unwind: find_proc_info dso %s\n", map->dso->name); - - /* Check the .eh_frame section for unwinding info */ - if (!read_unwind_spec_eh_frame(map->dso, ui->machine, - &table_data, &segbase, &fde_count)) { - memset(&di, 0, sizeof(di)); - di.format = UNW_INFO_FORMAT_REMOTE_TABLE; - di.start_ip = map->start; - di.end_ip = map->end; - di.u.rti.segbase = map->start + segbase; - di.u.rti.table_data = map->start + table_data; - di.u.rti.table_len = fde_count * sizeof(struct table_entry) - / sizeof(unw_word_t); - ret = dwarf_search_unwind_table(as, ip, &di, pi, - need_unwind_info, arg); - } - -#ifndef NO_LIBUNWIND_DEBUG_FRAME - /* Check the .debug_frame section for unwinding info */ - if (ret < 0 && - !read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) { - int fd = dso__data_get_fd(map->dso, ui->machine); - int is_exec = elf_is_exec(fd, map->dso->name); - unw_word_t base = is_exec ? 0 : map->start; - const char *symfile; - - if (fd >= 0) - dso__data_put_fd(map->dso); - - symfile = map->dso->symsrc_filename ?: map->dso->name; - - memset(&di, 0, sizeof(di)); - if (dwarf_find_debug_frame(0, &di, ip, base, symfile, - map->start, map->end)) - return dwarf_search_unwind_table(as, ip, &di, pi, - need_unwind_info, arg); - } -#endif - - return ret; -} - -static int access_fpreg(unw_addr_space_t __maybe_unused as, - unw_regnum_t __maybe_unused num, - unw_fpreg_t __maybe_unused *val, - int __maybe_unused __write, - void __maybe_unused *arg) -{ - pr_err("unwind: access_fpreg unsupported\n"); - return -UNW_EINVAL; -} - -static int get_dyn_info_list_addr(unw_addr_space_t __maybe_unused as, - unw_word_t __maybe_unused *dil_addr, - void __maybe_unused *arg) -{ - return -UNW_ENOINFO; -} - -static int resume(unw_addr_space_t __maybe_unused as, - unw_cursor_t __maybe_unused *cu, - void __maybe_unused *arg) -{ - pr_err("unwind: resume unsupported\n"); - return -UNW_EINVAL; -} + arch = normalize_arch(thread->mg->machine->env->arch); -static int -get_proc_name(unw_addr_space_t __maybe_unused as, - unw_word_t __maybe_unused addr, - char __maybe_unused *bufp, size_t __maybe_unused buf_len, - unw_word_t __maybe_unused *offp, void __maybe_unused *arg) -{ - pr_err("unwind: get_proc_name unsupported\n"); - return -UNW_EINVAL; -} - -static int access_dso_mem(struct unwind_info *ui, unw_word_t addr, - unw_word_t *data) -{ - struct map *map; - ssize_t size; - - map = find_map(addr, ui); - if (!map) { - pr_debug("unwind: no map for %lx\n", (unsigned long)addr); - return -1; + if (!strcmp(arch, "x86")) { + if (dso_type != DSO__TYPE_64BIT) + ops = x86_32_unwind_libunwind_ops; + } else if (!strcmp(arch, "arm64") || !strcmp(arch, "arm")) { + if (dso_type == DSO__TYPE_64BIT) + ops = arm64_unwind_libunwind_ops; } - if (!map->dso) + if (!ops) { + pr_err("unwind: target platform=%s is not supported\n", arch); return -1; - - size = dso__data_read_addr(map->dso, map, ui->machine, - addr, (u8 *) data, sizeof(*data)); - - return !(size == sizeof(*data)); -} - -static int access_mem(unw_addr_space_t __maybe_unused as, - unw_word_t addr, unw_word_t *valp, - int __write, void *arg) -{ - struct unwind_info *ui = arg; - struct stack_dump *stack = &ui->sample->user_stack; - u64 start, end; - int offset; - int ret; - - /* Don't support write, probably not needed. */ - if (__write || !stack || !ui->sample->user_regs.regs) { - *valp = 0; - return 0; - } - - ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP); - if (ret) - return ret; - - end = start + stack->size; - - /* Check overflow. */ - if (addr + sizeof(unw_word_t) < addr) - return -EINVAL; - - if (addr < start || addr + sizeof(unw_word_t) >= end) { - ret = access_dso_mem(ui, addr, valp); - if (ret) { - pr_debug("unwind: access_mem %p not inside range" - " 0x%" PRIx64 "-0x%" PRIx64 "\n", - (void *) (uintptr_t) addr, start, end); - *valp = 0; - return ret; - } - return 0; - } - - offset = addr - start; - *valp = *(unw_word_t *)&stack->data[offset]; - pr_debug("unwind: access_mem addr %p val %lx, offset %d\n", - (void *) (uintptr_t) addr, (unsigned long)*valp, offset); - return 0; -} - -static int access_reg(unw_addr_space_t __maybe_unused as, - unw_regnum_t regnum, unw_word_t *valp, - int __write, void *arg) -{ - struct unwind_info *ui = arg; - int id, ret; - u64 val; - - /* Don't support write, I suspect we don't need it. */ - if (__write) { - pr_err("unwind: access_reg w %d\n", regnum); - return 0; - } - - if (!ui->sample->user_regs.regs) { - *valp = 0; - return 0; - } - - id = libunwind__arch_reg_id(regnum); - if (id < 0) - return -EINVAL; - - ret = perf_reg_value(&val, &ui->sample->user_regs, id); - if (ret) { - pr_err("unwind: can't read reg %d\n", regnum); - return ret; - } - - *valp = (unw_word_t) val; - pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp); - return 0; -} - -static void put_unwind_info(unw_addr_space_t __maybe_unused as, - unw_proc_info_t *pi __maybe_unused, - void *arg __maybe_unused) -{ - pr_debug("unwind: put_unwind_info called\n"); -} - -static int entry(u64 ip, struct thread *thread, - unwind_entry_cb_t cb, void *arg) -{ - struct unwind_entry e; - struct addr_location al; - - thread__find_addr_location(thread, PERF_RECORD_MISC_USER, - MAP__FUNCTION, ip, &al); - - e.ip = ip; - e.map = al.map; - e.sym = al.sym; - - pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", - al.sym ? al.sym->name : "''", - ip, - al.map ? al.map->map_ip(al.map, ip) : (u64) 0); - - return cb(&e, arg); -} - -static void display_error(int err) -{ - switch (err) { - case UNW_EINVAL: - pr_err("unwind: Only supports local.\n"); - break; - case UNW_EUNSPEC: - pr_err("unwind: Unspecified error.\n"); - break; - case UNW_EBADREG: - pr_err("unwind: Register unavailable.\n"); - break; - default: - break; - } -} - -static unw_accessors_t accessors = { - .find_proc_info = find_proc_info, - .put_unwind_info = put_unwind_info, - .get_dyn_info_list_addr = get_dyn_info_list_addr, - .access_mem = access_mem, - .access_reg = access_reg, - .access_fpreg = access_fpreg, - .resume = resume, - .get_proc_name = get_proc_name, -}; - -int unwind__prepare_access(struct thread *thread) -{ - if (callchain_param.record_mode != CALLCHAIN_DWARF) - return 0; - - thread->addr_space = unw_create_addr_space(&accessors, 0); - if (!thread->addr_space) { - pr_err("unwind: Can't create unwind address space.\n"); - return -ENOMEM; } +out_register: + unwind__register_ops(thread, ops); - unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL); - return 0; + err = thread->unwind_libunwind_ops->prepare_access(thread); + if (initialized) + *initialized = err ? false : true; + return err; } void unwind__flush_access(struct thread *thread) { - if (callchain_param.record_mode != CALLCHAIN_DWARF) - return; - - unw_flush_cache(thread->addr_space, 0, 0); + if (thread->unwind_libunwind_ops) + thread->unwind_libunwind_ops->flush_access(thread); } void unwind__finish_access(struct thread *thread) { - if (callchain_param.record_mode != CALLCHAIN_DWARF) - return; - - unw_destroy_addr_space(thread->addr_space); -} - -static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, - void *arg, int max_stack) -{ - u64 val; - unw_word_t ips[max_stack]; - unw_addr_space_t addr_space; - unw_cursor_t c; - int ret, i = 0; - - ret = perf_reg_value(&val, &ui->sample->user_regs, PERF_REG_IP); - if (ret) - return ret; - - ips[i++] = (unw_word_t) val; - - /* - * If we need more than one entry, do the DWARF - * unwind itself. - */ - if (max_stack - 1 > 0) { - WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL"); - addr_space = ui->thread->addr_space; - - if (addr_space == NULL) - return -1; - - ret = unw_init_remote(&c, addr_space, ui); - if (ret) - display_error(ret); - - while (!ret && (unw_step(&c) > 0) && i < max_stack) { - unw_get_reg(&c, UNW_REG_IP, &ips[i]); - ++i; - } - - max_stack = i; - } - - /* - * Display what we got based on the order setup. - */ - for (i = 0; i < max_stack && !ret; i++) { - int j = i; - - if (callchain_param.order == ORDER_CALLER) - j = max_stack - i - 1; - ret = ips[j] ? entry(ips[j], ui->thread, cb, arg) : 0; - } - - return ret; + if (thread->unwind_libunwind_ops) + thread->unwind_libunwind_ops->finish_access(thread); } int unwind__get_entries(unwind_entry_cb_t cb, void *arg, - struct thread *thread, - struct perf_sample *data, int max_stack) + struct thread *thread, + struct perf_sample *data, int max_stack) { - struct unwind_info ui = { - .sample = data, - .thread = thread, - .machine = thread->mg->machine, - }; - - if (!data->user_regs.regs) - return -EINVAL; - - if (max_stack <= 0) - return -EINVAL; - - return get_entries(&ui, cb, arg, max_stack); + if (thread->unwind_libunwind_ops) + return thread->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); + return 0; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index 12790cf94618..61fb1e90ff51 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -14,18 +14,42 @@ struct unwind_entry { typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg); +struct unwind_libunwind_ops { + int (*prepare_access)(struct thread *thread); + void (*flush_access)(struct thread *thread); + void (*finish_access)(struct thread *thread); + int (*get_entries)(unwind_entry_cb_t cb, void *arg, + struct thread *thread, + struct perf_sample *data, int max_stack); +}; + #ifdef HAVE_DWARF_UNWIND_SUPPORT int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, int max_stack); /* libunwind specific */ #ifdef HAVE_LIBUNWIND_SUPPORT -int libunwind__arch_reg_id(int regnum); -int unwind__prepare_access(struct thread *thread); +#ifndef LIBUNWIND__ARCH_REG_ID +#define LIBUNWIND__ARCH_REG_ID(regnum) libunwind__arch_reg_id(regnum) +#endif + +#ifndef LIBUNWIND__ARCH_REG_SP +#define LIBUNWIND__ARCH_REG_SP PERF_REG_SP +#endif + +#ifndef LIBUNWIND__ARCH_REG_IP +#define LIBUNWIND__ARCH_REG_IP PERF_REG_IP +#endif + +int LIBUNWIND__ARCH_REG_ID(int regnum); +int unwind__prepare_access(struct thread *thread, struct map *map, + bool *initialized); void unwind__flush_access(struct thread *thread); void unwind__finish_access(struct thread *thread); #else -static inline int unwind__prepare_access(struct thread *thread __maybe_unused) +static inline int unwind__prepare_access(struct thread *thread __maybe_unused, + struct map *map __maybe_unused, + bool *initialized __maybe_unused) { return 0; } @@ -44,7 +68,9 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, return 0; } -static inline int unwind__prepare_access(struct thread *thread __maybe_unused) +static inline int unwind__prepare_access(struct thread *thread __maybe_unused, + struct map *map __maybe_unused, + bool *initialized __maybe_unused) { return 0; } diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 23504ad5d6dd..cee559d8c9e8 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -19,12 +19,19 @@ #include "callchain.h" #include "strlist.h" -struct callchain_param callchain_param = { - .mode = CHAIN_GRAPH_ABS, - .min_percent = 0.5, - .order = ORDER_CALLEE, - .key = CCKEY_FUNCTION, - .value = CCVAL_PERCENT, +#define CALLCHAIN_PARAM_DEFAULT \ + .mode = CHAIN_GRAPH_ABS, \ + .min_percent = 0.5, \ + .order = ORDER_CALLEE, \ + .key = CCKEY_FUNCTION, \ + .value = CCVAL_PERCENT, \ + +struct callchain_param callchain_param = { + CALLCHAIN_PARAM_DEFAULT +}; + +struct callchain_param callchain_param_default = { + CALLCHAIN_PARAM_DEFAULT }; /* @@ -97,20 +104,17 @@ int rm_rf(char *path) scnprintf(namebuf, sizeof(namebuf), "%s/%s", path, d->d_name); - ret = stat(namebuf, &statbuf); + /* We have to check symbolic link itself */ + ret = lstat(namebuf, &statbuf); if (ret < 0) { pr_debug("stat failed: %s\n", namebuf); break; } - if (S_ISREG(statbuf.st_mode)) - ret = unlink(namebuf); - else if (S_ISDIR(statbuf.st_mode)) + if (S_ISDIR(statbuf.st_mode)) ret = rm_rf(namebuf); - else { - pr_debug("unknown file: %s\n", namebuf); - ret = -1; - } + else + ret = unlink(namebuf); } closedir(dir); @@ -742,3 +746,19 @@ void print_binary(unsigned char *data, size_t len, } printer(BINARY_PRINT_DATA_END, -1, extra); } + +int is_printable_array(char *p, unsigned int len) +{ + unsigned int i; + + if (!p || !len || p[len - 1] != 0) + return 0; + + len--; + + for (i = 0; i < len; i++) { + if (!isprint(p[i]) && !isspace(p[i])) + return 0; + } + return 1; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 1e8c3167b9fb..e5f55477491d 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -72,7 +72,6 @@ #include <sys/ioctl.h> #include <inttypes.h> #include <linux/kernel.h> -#include <linux/magic.h> #include <linux/types.h> #include <sys/ttydefaults.h> #include <api/fs/tracing_path.h> @@ -360,4 +359,10 @@ typedef void (*print_binary_t)(enum binary_printer_ops, void print_binary(unsigned char *data, size_t len, size_t bytes_per_line, print_binary_t printer, void *extra); + +#if !defined(__GLIBC__) && !defined(__ANDROID__) +extern int sched_getcpu(void); +#endif + +int is_printable_array(char *p, unsigned int len); #endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 44d440da15dc..7bdcad484225 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -134,8 +134,6 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s return dso; } -#if BITS_PER_LONG == 64 - static enum dso_type machine__thread_dso_type(struct machine *machine, struct thread *thread) { @@ -156,6 +154,8 @@ static enum dso_type machine__thread_dso_type(struct machine *machine, return dso_type; } +#if BITS_PER_LONG == 64 + static int vdso__do_copy_compat(FILE *f, int fd) { char buf[4096]; @@ -283,8 +283,38 @@ static int __machine__findnew_vdso_compat(struct machine *machine, #endif +static struct dso *machine__find_vdso(struct machine *machine, + struct thread *thread) +{ + struct dso *dso = NULL; + enum dso_type dso_type; + + dso_type = machine__thread_dso_type(machine, thread); + switch (dso_type) { + case DSO__TYPE_32BIT: + dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO32, true); + if (!dso) { + dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, + true); + if (dso && dso_type != dso__type(dso, machine)) + dso = NULL; + } + break; + case DSO__TYPE_X32BIT: + dso = __dsos__find(&machine->dsos, DSO__NAME_VDSOX32, true); + break; + case DSO__TYPE_64BIT: + case DSO__TYPE_UNKNOWN: + default: + dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true); + break; + } + + return dso; +} + struct dso *machine__findnew_vdso(struct machine *machine, - struct thread *thread __maybe_unused) + struct thread *thread) { struct vdso_info *vdso_info; struct dso *dso = NULL; @@ -297,6 +327,10 @@ struct dso *machine__findnew_vdso(struct machine *machine, if (!vdso_info) goto out_unlock; + dso = machine__find_vdso(machine, thread); + if (dso) + goto out_unlock; + #if BITS_PER_LONG == 64 if (__machine__findnew_vdso_compat(machine, thread, vdso_info, &dso)) goto out_unlock; |