diff options
Diffstat (limited to 'tools/perf')
59 files changed, 599 insertions, 260 deletions
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index f5b81d439387..1ef45d803024 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -48,8 +48,6 @@ libbpf/ libperf/ libsubcmd/ libsymbol/ -libtraceevent/ -libtraceevent_plugins/ fixdep Documentation/doc.dep python_ext_build/ diff --git a/tools/perf/Documentation/intel-hybrid.txt b/tools/perf/Documentation/intel-hybrid.txt index e7a776ad25d7..0379903673a4 100644 --- a/tools/perf/Documentation/intel-hybrid.txt +++ b/tools/perf/Documentation/intel-hybrid.txt @@ -8,15 +8,15 @@ Part of events are available on core cpu, part of events are available on atom cpu and even part of events are available on both. Kernel exports two new cpu pmus via sysfs: -/sys/devices/cpu_core -/sys/devices/cpu_atom +/sys/bus/event_source/devices/cpu_core +/sys/bus/event_source/devices/cpu_atom The 'cpus' files are created under the directories. For example, -cat /sys/devices/cpu_core/cpus +cat /sys/bus/event_source/devices/cpu_core/cpus 0-15 -cat /sys/devices/cpu_atom/cpus +cat /sys/bus/event_source/devices/cpu_atom/cpus 16-23 It indicates cpu0-cpu15 are core cpus and cpu16-cpu23 are atom cpus. @@ -60,8 +60,8 @@ can't carry pmu information. So now this type is extended to be PMU aware type. The PMU type ID is stored at attr.config[63:32]. PMU type ID is retrieved from sysfs. -/sys/devices/cpu_atom/type -/sys/devices/cpu_core/type +/sys/bus/event_source/devices/cpu_atom/type +/sys/bus/event_source/devices/cpu_core/type The new attr.config layout for PERF_TYPE_HARDWARE: diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index dea005410ec0..ee5d333e2ca9 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -188,7 +188,7 @@ in the CPU vendor specific documentation. The available PMUs and their raw parameters can be listed with - ls /sys/devices/*/format + ls /sys/bus/event_source/devices/*/format For example the raw event "LSD.UOPS" core pmu event above could be specified as diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index dc42de1785ce..908165fcec7d 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,5 +1,6 @@ arch/arm64/tools/gen-sysreg.awk arch/arm64/tools/sysreg +arch/*/include/uapi/asm/bpf_perf_event.h tools/perf tools/arch tools/scripts diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 2ce71d2e5fae..a2034fa18325 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -513,13 +513,14 @@ ifeq ($(feature-setns), 1) $(call detected,CONFIG_SETNS) endif +ifeq ($(feature-reallocarray), 0) + CFLAGS += -DCOMPAT_NEED_REALLOCARRAY +endif + ifdef CORESIGHT $(call feature_check,libopencsd) ifeq ($(feature-libopencsd), 1) CFLAGS += -DHAVE_CSTRACE_SUPPORT $(LIBOPENCSD_CFLAGS) - ifeq ($(feature-reallocarray), 0) - CFLAGS += -DCOMPAT_NEED_REALLOCARRAY - endif LDFLAGS += $(LIBOPENCSD_LDFLAGS) EXTLIBS += $(OPENCSDLIBS) $(call detected,CONFIG_LIBOPENCSD) @@ -568,6 +569,8 @@ ifndef NO_LIBELF ifeq ($(feature-libdebuginfod), 1) CFLAGS += -DHAVE_DEBUGINFOD_SUPPORT EXTLIBS += -ldebuginfod + else + $(warning No elfutils/debuginfod.h found, no debuginfo server support, please install libdebuginfod-dev/elfutils-debuginfod-client-devel or equivalent) endif endif @@ -1135,9 +1138,6 @@ ifndef NO_AUXTRACE ifndef NO_AUXTRACE $(call detected,CONFIG_AUXTRACE) CFLAGS += -DHAVE_AUXTRACE_SUPPORT - ifeq ($(feature-reallocarray), 0) - CFLAGS += -DCOMPAT_NEED_REALLOCARRAY - endif endif endif diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 9dd2e8d3f3c9..b61c355fbdee 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -164,7 +164,7 @@ ifneq ($(OUTPUT),) VPATH += $(OUTPUT) export VPATH # create symlink to the original source -SOURCE := $(shell ln -sf $(srctree)/tools/perf $(OUTPUT)/source) +SOURCE := $(shell ln -sfn $(srctree)/tools/perf $(OUTPUT)/source) endif ifeq ($(V),1) @@ -1143,7 +1143,8 @@ install-tests: all install-gtk $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_probe'; \ $(INSTALL) tests/shell/base_probe/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_probe'; \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \ - $(INSTALL) tests/shell/base_probe/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \ + $(INSTALL) tests/shell/base_report/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \ + $(INSTALL) tests/shell/base_report/*.txt '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/coresight' ; \ $(INSTALL) tests/shell/coresight/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/coresight' $(Q)$(MAKE) -C tests/shell/coresight install-tests diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c index df7b5dfcc26a..7ea882ef293a 100644 --- a/tools/perf/arch/x86/util/iostat.c +++ b/tools/perf/arch/x86/util/iostat.c @@ -32,7 +32,7 @@ #define MAX_PATH 1024 #endif -#define UNCORE_IIO_PMU_PATH "devices/uncore_iio_%d" +#define UNCORE_IIO_PMU_PATH "bus/event_source/devices/uncore_iio_%d" #define SYSFS_UNCORE_PMU_PATH "%s/"UNCORE_IIO_PMU_PATH #define PLATFORM_MAPPING_PATH UNCORE_IIO_PMU_PATH"/die%d" diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index ef5c4257844d..20fe4f72b4af 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -420,7 +420,12 @@ static int cmpworker(const void *p1, const void *p2) struct worker *w1 = (struct worker *) p1; struct worker *w2 = (struct worker *) p2; - return w1->tid > w2->tid; + + if (w1->tid > w2->tid) + return 1; + if (w1->tid < w2->tid) + return -1; + return 0; } int bench_epoll_wait(int argc, const char **argv) diff --git a/tools/perf/bench/syscall.c b/tools/perf/bench/syscall.c index ea4dfc07cbd6..e7dc216f717f 100644 --- a/tools/perf/bench/syscall.c +++ b/tools/perf/bench/syscall.c @@ -22,8 +22,7 @@ #define __NR_fork -1 #endif -#define LOOPS_DEFAULT 10000000 -static int loops = LOOPS_DEFAULT; +static int loops; static const struct option options[] = { OPT_INTEGER('l', "loop", &loops, "Specify number of loops"), @@ -80,6 +79,18 @@ static int bench_syscall_common(int argc, const char **argv, int syscall) const char *name = NULL; int i; + switch (syscall) { + case __NR_fork: + case __NR_execve: + /* Limit default loop to 10000 times to save time */ + loops = 10000; + break; + default: + loops = 10000000; + break; + } + + /* Options -l and --loops override default above */ argc = parse_options(argc, argv, options, bench_syscall_usage, 0); gettimeofday(&start, NULL); @@ -94,16 +105,9 @@ static int bench_syscall_common(int argc, const char **argv, int syscall) break; case __NR_fork: test_fork(); - /* Only loop 10000 times to save time */ - if (i == 10000) - loops = 10000; break; case __NR_execve: test_execve(); - /* Only loop 10000 times to save time */ - if (i == 10000) - loops = 10000; - break; default: break; } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index d6989195a061..11e49cafa3af 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -2367,10 +2367,10 @@ int cmd_inject(int argc, const char **argv) }; int ret; const char *known_build_ids = NULL; - bool build_ids; - bool build_id_all; - bool mmap2_build_ids; - bool mmap2_build_id_all; + bool build_ids = false; + bool build_id_all = false; + bool mmap2_build_ids = false; + bool mmap2_build_id_all = false; struct option options[] = { OPT_BOOLEAN('b', "build-ids", &build_ids, diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 062e2b56a2ab..33a456980664 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1591,8 +1591,8 @@ static const struct { { LCB_F_PERCPU | LCB_F_WRITE, "pcpu-sem:W", "percpu-rwsem" }, { LCB_F_MUTEX, "mutex", "mutex" }, { LCB_F_MUTEX | LCB_F_SPIN, "mutex", "mutex" }, - /* alias for get_type_flag() */ - { LCB_F_MUTEX | LCB_F_SPIN, "mutex-spin", "mutex" }, + /* alias for optimistic spinning only */ + { LCB_F_MUTEX | LCB_F_SPIN, "mutex:spin", "mutex-spin" }, }; static const char *get_type_str(unsigned int flags) @@ -1617,19 +1617,6 @@ static const char *get_type_name(unsigned int flags) return "unknown"; } -static unsigned int get_type_flag(const char *str) -{ - for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { - if (!strcmp(lock_type_table[i].name, str)) - return lock_type_table[i].flags; - } - for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { - if (!strcmp(lock_type_table[i].str, str)) - return lock_type_table[i].flags; - } - return UINT_MAX; -} - static void lock_filter_finish(void) { zfree(&filters.types); @@ -2350,29 +2337,58 @@ static int parse_lock_type(const struct option *opt __maybe_unused, const char * int unset __maybe_unused) { char *s, *tmp, *tok; - int ret = 0; s = strdup(str); if (s == NULL) return -1; for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { - unsigned int flags = get_type_flag(tok); + bool found = false; - if (flags == -1U) { - pr_err("Unknown lock flags: %s\n", tok); - ret = -1; - break; + /* `tok` is `str` in `lock_type_table` if it contains ':'. */ + if (strchr(tok, ':')) { + for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { + if (!strcmp(lock_type_table[i].str, tok) && + add_lock_type(lock_type_table[i].flags)) { + found = true; + break; + } + } + + if (!found) { + pr_err("Unknown lock flags name: %s\n", tok); + free(s); + return -1; + } + + continue; } - if (!add_lock_type(flags)) { - ret = -1; - break; + /* + * Otherwise `tok` is `name` in `lock_type_table`. + * Single lock name could contain multiple flags. + */ + for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { + if (!strcmp(lock_type_table[i].name, tok)) { + if (add_lock_type(lock_type_table[i].flags)) { + found = true; + } else { + free(s); + return -1; + } + } } + + if (!found) { + pr_err("Unknown lock name: %s\n", tok); + free(s); + return -1; + } + } free(s); - return ret; + return 0; } static bool add_lock_addr(unsigned long addr) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index adbaf80b398c..ab9035573a15 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -3471,7 +3471,7 @@ static struct option __record_options[] = { "sample selected machine registers on interrupt," " use '-I?' to list register names", parse_intr_regs), OPT_CALLBACK_OPTARG(0, "user-regs", &record.opts.sample_user_regs, NULL, "any register", - "sample selected machine registers on interrupt," + "sample selected machine registers in user space," " use '--user-regs=?' to list register names", parse_user_regs), OPT_BOOLEAN(0, "running-time", &record.opts.running_time, "Record running/enabled time of read (:S) events"), diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 5dc17ffee27a..8700c3968066 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1418,7 +1418,7 @@ int cmd_report(int argc, const char **argv) OPT_STRING(0, "addr2line", &addr2line_path, "path", "addr2line binary to use for line numbers"), OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, - "Disable symbol demangling"), + "Symbol demangling. Enabled by default, use --no-demangle to disable."), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"), @@ -1551,12 +1551,12 @@ int cmd_report(int argc, const char **argv) input_name = "perf.data"; } +repeat: data.path = input_name; data.force = symbol_conf.force; symbol_conf.skip_empty = report.skip_empty; -repeat: perf_tool__init(&report.tool, ordered_events); report.tool.sample = process_sample_event; report.tool.mmap = perf_event__process_mmap; diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 5981cc51abc8..64bf3ac237f2 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -999,7 +999,7 @@ thread_atoms_search(struct rb_root_cached *root, struct thread *thread, else if (cmp < 0) node = node->rb_right; else { - BUG_ON(thread != atoms->thread); + BUG_ON(!RC_CHK_EQUAL(thread, atoms->thread)); return atoms; } } @@ -1116,6 +1116,21 @@ add_sched_in_event(struct work_atoms *atoms, u64 timestamp) atoms->nb_atoms++; } +static void free_work_atoms(struct work_atoms *atoms) +{ + struct work_atom *atom, *tmp; + + if (atoms == NULL) + return; + + list_for_each_entry_safe(atom, tmp, &atoms->work_list, list) { + list_del(&atom->list); + free(atom); + } + thread__zput(atoms->thread); + free(atoms); +} + static int latency_switch_event(struct perf_sched *sched, struct evsel *evsel, struct perf_sample *sample, @@ -1639,6 +1654,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, const char *color = PERF_COLOR_NORMAL; char stimestamp[32]; const char *str; + int ret = -1; BUG_ON(this_cpu.cpu >= MAX_CPUS || this_cpu.cpu < 0); @@ -1669,17 +1685,20 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel, sched_in = map__findnew_thread(sched, machine, -1, next_pid); sched_out = map__findnew_thread(sched, machine, -1, prev_pid); if (sched_in == NULL || sched_out == NULL) - return -1; + goto out; tr = thread__get_runtime(sched_in); - if (tr == NULL) { - thread__put(sched_in); - return -1; - } + if (tr == NULL) + goto out; + + thread__put(sched->curr_thread[this_cpu.cpu]); + thread__put(sched->curr_out_thread[this_cpu.cpu]); sched->curr_thread[this_cpu.cpu] = thread__get(sched_in); sched->curr_out_thread[this_cpu.cpu] = thread__get(sched_out); + ret = 0; + str = thread__comm_str(sched_in); new_shortname = 0; if (!tr->shortname[0]) { @@ -1774,12 +1793,10 @@ sched_out: color_fprintf(stdout, color, "\n"); out: - if (sched->map.task_name) - thread__put(sched_out); - + thread__put(sched_out); thread__put(sched_in); - return 0; + return ret; } static int process_sched_switch_event(const struct perf_tool *tool, @@ -2023,6 +2040,16 @@ static u64 evsel__get_time(struct evsel *evsel, u32 cpu) return r->last_time[cpu]; } +static void timehist__evsel_priv_destructor(void *priv) +{ + struct evsel_runtime *r = priv; + + if (r) { + free(r->last_time); + free(r); + } +} + static int comm_width = 30; static char *timehist_get_commstr(struct thread *thread) @@ -3276,6 +3303,8 @@ static int perf_sched__timehist(struct perf_sched *sched) setup_pager(); + evsel__set_priv_destructor(timehist__evsel_priv_destructor); + /* prefer sched_waking if it is captured */ if (evlist__find_tracepoint_by_name(session->evlist, "sched:sched_waking")) handlers[1].handler = timehist_sched_wakeup_ignore; @@ -3376,13 +3405,13 @@ static void __merge_work_atoms(struct rb_root_cached *root, struct work_atoms *d this->total_runtime += data->total_runtime; this->nb_atoms += data->nb_atoms; this->total_lat += data->total_lat; - list_splice(&data->work_list, &this->work_list); + list_splice_init(&data->work_list, &this->work_list); if (this->max_lat < data->max_lat) { this->max_lat = data->max_lat; this->max_lat_start = data->max_lat_start; this->max_lat_end = data->max_lat_end; } - zfree(&data); + free_work_atoms(data); return; } } @@ -3461,7 +3490,6 @@ static int perf_sched__lat(struct perf_sched *sched) work_list = rb_entry(next, struct work_atoms, node); output_lat_thread(sched, work_list); next = rb_next(next); - thread__zput(work_list->thread); } printf(" -----------------------------------------------------------------------------------------------------------------\n"); @@ -3475,6 +3503,13 @@ static int perf_sched__lat(struct perf_sched *sched) rc = 0; + while ((next = rb_first_cached(&sched->sorted_atom_root))) { + struct work_atoms *data; + + data = rb_entry(next, struct work_atoms, node); + rb_erase_cached(next, &sched->sorted_atom_root); + free_work_atoms(data); + } out_free_cpus_switch_event: free_cpus_switch_event(sched); return rc; @@ -3546,10 +3581,10 @@ static int perf_sched__map(struct perf_sched *sched) sched->curr_out_thread = calloc(MAX_CPUS, sizeof(*(sched->curr_out_thread))); if (!sched->curr_out_thread) - return rc; + goto out_free_curr_thread; if (setup_cpus_switch_event(sched)) - goto out_free_curr_thread; + goto out_free_curr_out_thread; if (setup_map_cpus(sched)) goto out_free_cpus_switch_event; @@ -3580,7 +3615,14 @@ out_put_map_cpus: out_free_cpus_switch_event: free_cpus_switch_event(sched); +out_free_curr_out_thread: + for (int i = 0; i < MAX_CPUS; i++) + thread__put(sched->curr_out_thread[i]); + zfree(&sched->curr_out_thread); + out_free_curr_thread: + for (int i = 0; i < MAX_CPUS; i++) + thread__put(sched->curr_thread[i]); zfree(&sched->curr_thread); return rc; } @@ -3887,13 +3929,15 @@ int cmd_sched(int argc, const char **argv) if (!argc) usage_with_options(sched_usage, sched_options); + thread__set_priv_destructor(free); + /* * Aliased to 'perf script' for now: */ if (!strcmp(argv[0], "script")) { - return cmd_script(argc, argv); + ret = cmd_script(argc, argv); } else if (strlen(argv[0]) > 2 && strstarts("record", argv[0])) { - return __cmd_record(argc, argv); + ret = __cmd_record(argc, argv); } else if (strlen(argv[0]) > 2 && strstarts("latency", argv[0])) { sched.tp_handler = &lat_ops; if (argc > 1) { @@ -3902,7 +3946,7 @@ int cmd_sched(int argc, const char **argv) usage_with_options(latency_usage, latency_options); } setup_sorting(&sched, latency_options, latency_usage); - return perf_sched__lat(&sched); + ret = perf_sched__lat(&sched); } else if (!strcmp(argv[0], "map")) { if (argc) { argc = parse_options(argc, argv, map_options, map_usage, 0); @@ -3913,13 +3957,14 @@ int cmd_sched(int argc, const char **argv) sched.map.task_names = strlist__new(sched.map.task_name, NULL); if (sched.map.task_names == NULL) { fprintf(stderr, "Failed to parse task names\n"); - return -1; + ret = -1; + goto out; } } } sched.tp_handler = &map_ops; setup_sorting(&sched, latency_options, latency_usage); - return perf_sched__map(&sched); + ret = perf_sched__map(&sched); } else if (strlen(argv[0]) > 2 && strstarts("replay", argv[0])) { sched.tp_handler = &replay_ops; if (argc) { @@ -3927,7 +3972,7 @@ int cmd_sched(int argc, const char **argv) if (argc) usage_with_options(replay_usage, replay_options); } - return perf_sched__replay(&sched); + ret = perf_sched__replay(&sched); } else if (!strcmp(argv[0], "timehist")) { if (argc) { argc = parse_options(argc, argv, timehist_options, @@ -3943,19 +3988,19 @@ int cmd_sched(int argc, const char **argv) parse_options_usage(NULL, timehist_options, "w", true); if (sched.show_next) parse_options_usage(NULL, timehist_options, "n", true); - return -EINVAL; + ret = -EINVAL; + goto out; } ret = symbol__validate_sym_arguments(); - if (ret) - return ret; - - return perf_sched__timehist(&sched); + if (!ret) + ret = perf_sched__timehist(&sched); } else { usage_with_options(sched_usage, sched_options); } +out: /* free usage string allocated by parse_options_subcommand */ free((void *)sched_usage[0]); - return 0; + return ret; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 4933efdfee76..628c61397d2d 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -96,7 +96,7 @@ #include <internal/threadmap.h> #define DEFAULT_SEPARATOR " " -#define FREEZE_ON_SMI_PATH "devices/cpu/freeze_on_smi" +#define FREEZE_ON_SMI_PATH "bus/event_source/devices/cpu/freeze_on_smi" static void print_counters(struct timespec *ts, int argc, const char **argv); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 724a79386321..ca3e8eca6610 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -809,7 +809,7 @@ static void perf_event__process_sample(const struct perf_tool *tool, * invalid --vmlinux ;-) */ if (!machine->kptr_restrict_warned && !top->vmlinux_warned && - __map__is_kernel(al.map) && map__has_symbols(al.map)) { + __map__is_kernel(al.map) && !map__has_symbols(al.map)) { if (symbol_conf.vmlinux_name) { char serr[256]; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index ffa129527309..f77e4f4b6f03 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1327,7 +1327,7 @@ static const struct syscall_fmt syscall_fmts[] = { .arg = { [0] = { .scnprintf = SCA_FDAT, /* olddirfd */ }, [2] = { .scnprintf = SCA_FDAT, /* newdirfd */ }, [4] = { .scnprintf = SCA_RENAMEAT2_FLAGS, /* flags */ }, }, }, - { .name = "rseq", .errpid = true, + { .name = "rseq", .arg = { [0] = { .from_user = true /* rseq */, }, }, }, { .name = "rt_sigaction", .arg = { [0] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, }, @@ -1351,7 +1351,7 @@ static const struct syscall_fmt syscall_fmts[] = { { .name = "sendto", .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, [4] = SCA_SOCKADDR_FROM_USER(addr), }, }, - { .name = "set_robust_list", .errpid = true, + { .name = "set_robust_list", .arg = { [0] = { .from_user = true /* head */, }, }, }, { .name = "set_tid_address", .errpid = true, }, { .name = "setitimer", @@ -2122,8 +2122,12 @@ static int trace__read_syscall_info(struct trace *trace, int id) return PTR_ERR(sc->tp_format); } + /* + * The tracepoint format contains __syscall_nr field, so it's one more + * than the actual number of syscall arguments. + */ if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? - RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields)) + RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields - 1)) return -ENOMEM; sc->args = sc->tp_format->format.fields; @@ -2869,8 +2873,8 @@ errno_print: { else if (sc->fmt->errpid) { struct thread *child = machine__find_thread(trace->host, ret, ret); + fprintf(trace->output, "%ld", ret); if (child != NULL) { - fprintf(trace->output, "%ld", ret); if (thread__comm_set(child)) fprintf(trace->output, " (%s)", thread__comm_str(child)); thread__put(child); @@ -3982,10 +3986,13 @@ static int trace__set_filter_loop_pids(struct trace *trace) if (!strcmp(thread__comm_str(parent), "sshd") || strstarts(thread__comm_str(parent), "gnome-terminal")) { pids[nr++] = thread__tid(parent); + thread__put(parent); break; } + thread__put(thread); thread = parent; } + thread__put(thread); err = evlist__append_tp_filter_pids(trace->evlist, nr, pids); if (!err && trace->filter_pids.map) diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json index c5d1d22bd034..5228f94a793f 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json @@ -229,19 +229,19 @@ }, { "MetricName": "slots_lost_misspeculation_fraction", - "MetricExpr": "(OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots)", + "MetricExpr": "100 * (OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots)", "BriefDescription": "Fraction of slots lost due to misspeculation", "DefaultMetricgroupName": "TopdownL1", "MetricGroup": "Default;TopdownL1", - "ScaleUnit": "100percent of slots" + "ScaleUnit": "1percent of slots" }, { "MetricName": "retired_fraction", - "MetricExpr": "OP_RETIRED / (CPU_CYCLES * #slots)", + "MetricExpr": "100 * OP_RETIRED / (CPU_CYCLES * #slots)", "BriefDescription": "Fraction of slots retiring, useful work", "DefaultMetricgroupName": "TopdownL1", "MetricGroup": "Default;TopdownL1", - "ScaleUnit": "100percent of slots" + "ScaleUnit": "1percent of slots" }, { "MetricName": "backend_core", @@ -266,7 +266,7 @@ }, { "MetricName": "frontend_bandwidth", - "MetricExpr": "frontend_bound - frontend_latency", + "MetricExpr": "frontend_bound - 100 * frontend_latency", "BriefDescription": "Fraction of slots the CPU did not dispatch at full bandwidth - able to dispatch partial slots only (1, 2, or 3 uops)", "MetricGroup": "TopdownL2", "ScaleUnit": "1percent of slots" diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 121cf61ba1b3..e0b2e7268ef6 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -680,7 +680,10 @@ class CallGraphModelBase(TreeModel): s = value.replace("%", "\\%") s = s.replace("_", "\\_") # Translate * and ? into SQL LIKE pattern characters % and _ - trans = string.maketrans("*?", "%_") + if sys.version_info[0] == 3: + trans = str.maketrans("*?", "%_") + else: + trans = string.maketrans("*?", "%_") match = " LIKE '" + str(s).translate(trans) + "'" else: match = " GLOB '" + str(value) + "'" diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c index 4cb7d486b5c1..047433c977bc 100644 --- a/tools/perf/tests/bp_account.c +++ b/tools/perf/tests/bp_account.c @@ -104,6 +104,7 @@ static int bp_accounting(int wp_cnt, int share) fd_wp = wp_event((void *)&the_var, &attr_new); TEST_ASSERT_VAL("failed to create max wp\n", fd_wp != -1); pr_debug("wp max created\n"); + close(fd_wp); } for (i = 0; i < wp_cnt; i++) diff --git a/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S b/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S index 75cf084a927d..577760046772 100644 --- a/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S +++ b/tools/perf/tests/shell/coresight/asm_pure_loop/asm_pure_loop.S @@ -26,3 +26,5 @@ skip: mov x0, #0 mov x8, #93 // __NR_exit syscall svc #0 + +.section .note.GNU-stack, "", @progbits diff --git a/tools/perf/tests/shell/record_bpf_filter.sh b/tools/perf/tests/shell/record_bpf_filter.sh index 1b58ccc1fd88..4d6c3c1b7fb9 100755 --- a/tools/perf/tests/shell/record_bpf_filter.sh +++ b/tools/perf/tests/shell/record_bpf_filter.sh @@ -89,7 +89,7 @@ test_bpf_filter_fail() { test_bpf_filter_group() { echo "Group bpf-filter test" - if ! perf record -e task-clock --filter 'period > 1000 || ip > 0' \ + if ! perf record -e task-clock --filter 'period > 1000, ip > 0' \ -o /dev/null true 2>/dev/null then echo "Group bpf-filter test [Failed should succeed]" @@ -97,7 +97,7 @@ test_bpf_filter_group() { return fi - if ! perf record -e task-clock --filter 'cpu > 0 || ip > 0' \ + if ! perf record -e task-clock --filter 'period > 1000 , cpu > 0 || ip > 0' \ -o /dev/null true 2>&1 | grep -q PERF_SAMPLE_CPU then echo "Group bpf-filter test [Failed forbidden CPU]" diff --git a/tools/perf/tests/shell/trace_btf_enum.sh b/tools/perf/tests/shell/trace_btf_enum.sh index 5a3b8a5a9b5c..8d1e6bbeac90 100755 --- a/tools/perf/tests/shell/trace_btf_enum.sh +++ b/tools/perf/tests/shell/trace_btf_enum.sh @@ -26,8 +26,12 @@ check_vmlinux() { trace_landlock() { echo "Tracing syscall ${syscall}" - # test flight just to see if landlock_add_rule and libbpf are available - $TESTPROG + # test flight just to see if landlock_add_rule is available + if ! perf trace $TESTPROG 2>&1 | grep -q landlock + then + echo "No landlock system call found, skipping to non-syscall tracing." + return + fi if perf trace -e $syscall $TESTPROG 2>&1 | \ grep -q -E ".*landlock_add_rule\(ruleset_fd: 11, rule_type: (LANDLOCK_RULE_PATH_BENEATH|LANDLOCK_RULE_NET_PORT), rule_attr: 0x[a-f0-9]+, flags: 45\) = -1.*" diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 5cab17a1942e..ee43d8fa2ed6 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -258,7 +258,7 @@ static int compar(const void *a, const void *b) const struct event_node *nodeb = b; s64 cmp = nodea->event_time - nodeb->event_time; - return cmp; + return cmp < 0 ? -1 : (cmp > 0 ? 1 : 0); } static int process_events(struct evlist *evlist, diff --git a/tools/perf/tests/tests-scripts.c b/tools/perf/tests/tests-scripts.c index ed114b044293..b6986d50dde6 100644 --- a/tools/perf/tests/tests-scripts.c +++ b/tools/perf/tests/tests-scripts.c @@ -255,6 +255,7 @@ static void append_scripts_in_dir(int dir_fd, continue; /* Skip scripts that have a separate driver. */ fd = openat(dir_fd, ent->d_name, O_PATH); append_scripts_in_dir(fd, result, result_sz); + close(fd); } for (i = 0; i < n_dirs; i++) /* Clean up */ zfree(&entlist[i]); diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 49ba82bf3391..3283b6313bab 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -3267,10 +3267,10 @@ do_hotkey: // key came straight from options ui__popup_menu() /* * No need to set actions->dso here since * it's just to remove the current filter. - * Ditto for thread below. */ do_zoom_dso(browser, actions); } else if (top == &browser->hists->thread_filter) { + actions->thread = thread; do_zoom_thread(browser, actions); } else if (top == &browser->hists->socket_filter) { do_zoom_socket(browser, actions); diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 138ffc71b32d..2c06f2a85400 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -37,6 +37,8 @@ #include "../../arch/arm64/include/asm/cputype.h" #define MAX_TIMESTAMP (~0ULL) +#define is_ldst_op(op) (!!((op) & ARM_SPE_OP_LDST)) + struct arm_spe { struct auxtrace auxtrace; struct auxtrace_queues queues; @@ -520,6 +522,10 @@ static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 m union perf_mem_data_src data_src = { .mem_op = PERF_MEM_OP_NA }; bool is_neoverse = is_midr_in_range_list(midr, neoverse_spe); + /* Only synthesize data source for LDST operations */ + if (!is_ldst_op(record->op)) + return 0; + if (record->op & ARM_SPE_OP_LD) data_src.mem_op = PERF_MEM_OP_LOAD; else if (record->op & ARM_SPE_OP_ST) @@ -619,7 +625,7 @@ static int arm_spe_sample(struct arm_spe_queue *speq) * When data_src is zero it means the record is not a memory operation, * skip to synthesize memory sample for this case. */ - if (spe->sample_memory && data_src) { + if (spe->sample_memory && is_ldst_op(record->op)) { err = arm_spe__synth_mem_sample(speq, spe->memory_id, data_src); if (err) return err; diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 13608237c50e..c81444059ad0 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -289,7 +289,10 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, } info_node->info_linear = info_linear; - perf_env__insert_bpf_prog_info(env, info_node); + if (!perf_env__insert_bpf_prog_info(env, info_node)) { + free(info_linear); + free(info_node); + } info_linear = NULL; /* @@ -480,7 +483,10 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id) info_node = malloc(sizeof(struct bpf_prog_info_node)); if (info_node) { info_node->info_linear = info_linear; - perf_env__insert_bpf_prog_info(env, info_node); + if (!perf_env__insert_bpf_prog_info(env, info_node)) { + free(info_linear); + free(info_node); + } } else free(info_linear); diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l index f313404f95a9..6aa65ade3385 100644 --- a/tools/perf/util/bpf-filter.l +++ b/tools/perf/util/bpf-filter.l @@ -76,7 +76,7 @@ static int path_or_error(void) num_dec [0-9]+ num_hex 0[Xx][0-9a-fA-F]+ space [ \t]+ -path [^ \t\n]+ +path [^ \t\n,]+ ident [_a-zA-Z][_a-zA-Z0-9]+ %% diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index 4a62ed593e84..e4352881e3fa 100644 --- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -431,9 +431,9 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid) static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) { bool augmented, do_output = false; - int zero = 0, size, aug_size, index, - value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value); + int zero = 0, index, value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value); u64 output = 0; /* has to be u64, otherwise it won't pass the verifier */ + s64 aug_size, size; unsigned int nr, *beauty_map; struct beauty_payload_enter *payload; void *arg, *payload_offset; @@ -484,14 +484,11 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) } else if (size > 0 && size <= value_size) { /* struct */ if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, size, arg)) augmented = true; - } else if (size < 0 && size >= -6) { /* buffer */ + } else if ((int)size < 0 && size >= -6) { /* buffer */ index = -(size + 1); barrier_var(index); // Prevent clang (noticed with v18) from removing the &= 7 trick. index &= 7; // Satisfy the bounds checking with the verifier in some kernels. - aug_size = args->args[index]; - - if (aug_size > TRACE_AUG_MAX_BUF) - aug_size = TRACE_AUG_MAX_BUF; + aug_size = args->args[index] > TRACE_AUG_MAX_BUF ? TRACE_AUG_MAX_BUF : args->args[index]; if (aug_size > 0) { if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, aug_size, arg)) diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index e763e8d99a43..ee00313d5d7e 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -864,7 +864,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine, char *allocated_name = NULL; int ret = 0; - if (!dso__has_build_id(dso)) + if (!dso__has_build_id(dso) || !dso__hit(dso)) return 0; if (dso__is_kcore(dso)) { diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 49b79cf0c5cc..8aa456d7c2cd 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -5,6 +5,8 @@ #include <internal/rc_check.h> #include <linux/refcount.h> #include <linux/zalloc.h> +#include <tools/libc_compat.h> // reallocarray + #include "rwsem.h" DECLARE_RC_STRUCT(comm_str) { diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index d633d15329fa..e56330c85fe7 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -46,8 +46,8 @@ int debug_type_profile; FILE *debug_file(void) { if (!_debug_file) { - pr_warning_once("debug_file not set"); debug_set_file(stderr); + pr_warning_once("debug_file not set"); } return _debug_file; } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index bb8e8f444054..c0472a41147c 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -808,7 +808,9 @@ static inline bool dso__is_kcore(const struct dso *dso) static inline bool dso__is_kallsyms(const struct dso *dso) { - return RC_CHK_ACCESS(dso)->kernel && RC_CHK_ACCESS(dso)->long_name[0] != '/'; + enum dso_binary_type bt = dso__binary_type(dso); + + return bt == DSO_BINARY_TYPE__KALLSYMS || bt == DSO_BINARY_TYPE__GUEST_KALLSYMS; } bool dso__is_object_file(const struct dso *dso); diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 1edbccfc3281..d981b6f4bc5e 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -22,15 +22,19 @@ struct perf_env perf_env; #include "bpf-utils.h" #include <bpf/libbpf.h> -void perf_env__insert_bpf_prog_info(struct perf_env *env, +bool perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node) { + bool ret; + down_write(&env->bpf_progs.lock); - __perf_env__insert_bpf_prog_info(env, info_node); + ret = __perf_env__insert_bpf_prog_info(env, info_node); up_write(&env->bpf_progs.lock); + + return ret; } -void __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node) +bool __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node) { __u32 prog_id = info_node->info_linear->info.id; struct bpf_prog_info_node *node; @@ -48,13 +52,14 @@ void __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info p = &(*p)->rb_right; } else { pr_debug("duplicated bpf prog info %u\n", prog_id); - return; + return false; } } rb_link_node(&info_node->rb_node, parent, p); rb_insert_color(&info_node->rb_node, &env->bpf_progs.infos); env->bpf_progs.infos_cnt++; + return true; } struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 51b36c36019b..38de0af2a680 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -176,9 +176,9 @@ const char *perf_env__raw_arch(struct perf_env *env); int perf_env__nr_cpus_avail(struct perf_env *env); void perf_env__init(struct perf_env *env); -void __perf_env__insert_bpf_prog_info(struct perf_env *env, +bool __perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node); -void perf_env__insert_bpf_prog_info(struct perf_env *env, +bool perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node); struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, __u32 prog_id); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index a9df84692d4a..dac87dccaaaa 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1434,19 +1434,18 @@ static int evlist__create_syswide_maps(struct evlist *evlist) */ cpus = perf_cpu_map__new_online_cpus(); if (!cpus) - goto out; + return -ENOMEM; threads = perf_thread_map__new_dummy(); - if (!threads) - goto out_put; + if (!threads) { + perf_cpu_map__put(cpus); + return -ENOMEM; + } perf_evlist__set_maps(&evlist->core, cpus, threads); - perf_thread_map__put(threads); -out_put: perf_cpu_map__put(cpus); -out: - return -ENOMEM; + return 0; } int evlist__open(struct evlist *evlist) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index dbf9c8cee3c5..6d7249cc1a99 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1477,6 +1477,15 @@ static void evsel__free_config_terms(struct evsel *evsel) free_config_terms(&evsel->config_terms); } +static void (*evsel__priv_destructor)(void *priv); + +void evsel__set_priv_destructor(void (*destructor)(void *priv)) +{ + assert(evsel__priv_destructor == NULL); + + evsel__priv_destructor = destructor; +} + void evsel__exit(struct evsel *evsel) { assert(list_empty(&evsel->core.node)); @@ -1502,6 +1511,8 @@ void evsel__exit(struct evsel *evsel) hashmap__free(evsel->per_pkg_mask); evsel->per_pkg_mask = NULL; zfree(&evsel->metric_events); + if (evsel__priv_destructor) + evsel__priv_destructor(evsel->priv); perf_evsel__object.fini(evsel); if (evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME || evsel__tool_event(evsel) == PERF_TOOL_USER_TIME) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 15e745a9a798..26574a33a725 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -282,6 +282,8 @@ void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx); void evsel__exit(struct evsel *evsel); void evsel__delete(struct evsel *evsel); +void evsel__set_priv_destructor(void (*destructor)(void *priv)); + struct callchain_param; void evsel__config(struct evsel *evsel, struct record_opts *opts, diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index b2536a59c44e..90c6ce2212e4 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -288,7 +288,7 @@ struct expr_parse_ctx *expr__ctx_new(void) { struct expr_parse_ctx *ctx; - ctx = malloc(sizeof(struct expr_parse_ctx)); + ctx = calloc(1, sizeof(struct expr_parse_ctx)); if (!ctx) return NULL; @@ -297,9 +297,6 @@ struct expr_parse_ctx *expr__ctx_new(void) free(ctx); return NULL; } - ctx->sctx.user_requested_cpu_list = NULL; - ctx->sctx.runtime = 0; - ctx->sctx.system_wide = false; return ctx; } diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index a6386d12afd7..7b99f58f7bf2 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -3188,7 +3188,10 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) /* after reading from file, translate offset to address */ bpil_offs_to_addr(info_linear); info_node->info_linear = info_linear; - __perf_env__insert_bpf_prog_info(env, info_node); + if (!__perf_env__insert_bpf_prog_info(env, info_node)) { + free(info_linear); + free(info_node); + } } up_write(&env->bpf_progs.lock); @@ -3235,7 +3238,8 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) if (__do_read(ff, node->data, data_size)) goto out; - __perf_env__insert_btf(env, node); + if (!__perf_env__insert_btf(env, node)) + free(node); node = NULL; } diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index fd2597613f3d..61f10578e121 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -127,6 +127,7 @@ struct intel_pt { bool single_pebs; bool sample_pebs; + int pebs_data_src_fmt; struct evsel *pebs_evsel; u64 evt_sample_type; @@ -175,6 +176,7 @@ enum switch_state { struct intel_pt_pebs_event { struct evsel *evsel; u64 id; + int data_src_fmt; }; struct intel_pt_queue { @@ -2232,7 +2234,146 @@ static void intel_pt_add_lbrs(struct branch_stack *br_stack, } } -static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel, u64 id) +#define P(a, b) PERF_MEM_S(a, b) +#define OP_LH (P(OP, LOAD) | P(LVL, HIT)) +#define LEVEL(x) P(LVLNUM, x) +#define REM P(REMOTE, REMOTE) +#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) + +#define PERF_PEBS_DATA_SOURCE_GRT_MAX 0x10 +#define PERF_PEBS_DATA_SOURCE_GRT_MASK (PERF_PEBS_DATA_SOURCE_GRT_MAX - 1) + +/* Based on kernel __intel_pmu_pebs_data_source_grt() and pebs_data_source */ +static const u64 pebs_data_source_grt[PERF_PEBS_DATA_SOURCE_GRT_MAX] = { + P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA), /* L3 miss|SNP N/A */ + OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* L1 hit|SNP None */ + OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* LFB/MAB hit|SNP None */ + OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* L2 hit|SNP None */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* L3 hit|SNP None */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT), /* L3 hit|SNP Hit */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* L3 hit|SNP HitM */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* L3 hit|SNP HitM */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD), /* L3 hit|SNP Fwd */ + OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* Remote L3 hit|SNP HitM */ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, HIT), /* RAM hit|SNP Hit */ + OP_LH | P(LVL, REM_RAM1) | REM | LEVEL(L3) | P(SNOOP, HIT), /* Remote L3 hit|SNP Hit */ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | SNOOP_NONE_MISS, /* RAM hit|SNP None or Miss */ + OP_LH | P(LVL, REM_RAM1) | LEVEL(RAM) | REM | SNOOP_NONE_MISS, /* Remote RAM hit|SNP None or Miss */ + OP_LH | P(LVL, IO) | LEVEL(NA) | P(SNOOP, NONE), /* I/O hit|SNP None */ + OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE), /* Uncached hit|SNP None */ +}; + +/* Based on kernel __intel_pmu_pebs_data_source_cmt() and pebs_data_source */ +static const u64 pebs_data_source_cmt[PERF_PEBS_DATA_SOURCE_GRT_MAX] = { + P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA), /* L3 miss|SNP N/A */ + OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* L1 hit|SNP None */ + OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* LFB/MAB hit|SNP None */ + OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* L2 hit|SNP None */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* L3 hit|SNP None */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, MISS), /* L3 hit|SNP Hit */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT), /* L3 hit|SNP HitM */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD), /* L3 hit|SNP HitM */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* L3 hit|SNP Fwd */ + OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* Remote L3 hit|SNP HitM */ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, NONE), /* RAM hit|SNP Hit */ + OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE), /* Remote L3 hit|SNP Hit */ + OP_LH | LEVEL(RAM) | REM | P(SNOOPX, FWD), /* RAM hit|SNP None or Miss */ + OP_LH | LEVEL(RAM) | REM | P(SNOOP, HITM), /* Remote RAM hit|SNP None or Miss */ + OP_LH | P(LVL, IO) | LEVEL(NA) | P(SNOOP, NONE), /* I/O hit|SNP None */ + OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE), /* Uncached hit|SNP None */ +}; + +/* Based on kernel pebs_set_tlb_lock() */ +static inline void pebs_set_tlb_lock(u64 *val, bool tlb, bool lock) +{ + /* + * TLB access + * 0 = did not miss 2nd level TLB + * 1 = missed 2nd level TLB + */ + if (tlb) + *val |= P(TLB, MISS) | P(TLB, L2); + else + *val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2); + + /* locked prefix */ + if (lock) + *val |= P(LOCK, LOCKED); +} + +/* Based on kernel __grt_latency_data() */ +static u64 intel_pt_grt_latency_data(u8 dse, bool tlb, bool lock, bool blk, + const u64 *pebs_data_source) +{ + u64 val; + + dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK; + val = pebs_data_source[dse]; + + pebs_set_tlb_lock(&val, tlb, lock); + + if (blk) + val |= P(BLK, DATA); + else + val |= P(BLK, NA); + + return val; +} + +/* Default value for data source */ +#define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ + PERF_MEM_S(LVL, NA) |\ + PERF_MEM_S(SNOOP, NA) |\ + PERF_MEM_S(LOCK, NA) |\ + PERF_MEM_S(TLB, NA) |\ + PERF_MEM_S(LVLNUM, NA)) + +enum DATA_SRC_FORMAT { + DATA_SRC_FORMAT_ERR = -1, + DATA_SRC_FORMAT_NA = 0, + DATA_SRC_FORMAT_GRT = 1, + DATA_SRC_FORMAT_CMT = 2, +}; + +/* Based on kernel grt_latency_data() and cmt_latency_data */ +static u64 intel_pt_get_data_src(u64 mem_aux_info, int data_src_fmt) +{ + switch (data_src_fmt) { + case DATA_SRC_FORMAT_GRT: { + union { + u64 val; + struct { + unsigned int dse:4; + unsigned int locked:1; + unsigned int stlb_miss:1; + unsigned int fwd_blk:1; + unsigned int reserved:25; + }; + } x = {.val = mem_aux_info}; + return intel_pt_grt_latency_data(x.dse, x.stlb_miss, x.locked, x.fwd_blk, + pebs_data_source_grt); + } + case DATA_SRC_FORMAT_CMT: { + union { + u64 val; + struct { + unsigned int dse:5; + unsigned int locked:1; + unsigned int stlb_miss:1; + unsigned int fwd_blk:1; + unsigned int reserved:24; + }; + } x = {.val = mem_aux_info}; + return intel_pt_grt_latency_data(x.dse, x.stlb_miss, x.locked, x.fwd_blk, + pebs_data_source_cmt); + } + default: + return PERF_MEM_NA; + } +} + +static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evsel *evsel, + u64 id, int data_src_fmt) { const struct intel_pt_blk_items *items = &ptq->state->items; struct perf_sample sample = { .ip = 0, }; @@ -2350,6 +2491,18 @@ static int intel_pt_do_synth_pebs_sample(struct intel_pt_queue *ptq, struct evse } } + if (sample_type & PERF_SAMPLE_DATA_SRC) { + if (items->has_mem_aux_info && data_src_fmt) { + if (data_src_fmt < 0) { + pr_err("Intel PT missing data_src info\n"); + return -1; + } + sample.data_src = intel_pt_get_data_src(items->mem_aux_info, data_src_fmt); + } else { + sample.data_src = PERF_MEM_NA; + } + } + if (sample_type & PERF_SAMPLE_TRANSACTION && items->has_tsx_aux_info) { u64 ax = items->has_rax ? items->rax : 0; /* Refer kernel's intel_hsw_transaction() */ @@ -2368,9 +2521,10 @@ static int intel_pt_synth_single_pebs_sample(struct intel_pt_queue *ptq) { struct intel_pt *pt = ptq->pt; struct evsel *evsel = pt->pebs_evsel; + int data_src_fmt = pt->pebs_data_src_fmt; u64 id = evsel->core.id[0]; - return intel_pt_do_synth_pebs_sample(ptq, evsel, id); + return intel_pt_do_synth_pebs_sample(ptq, evsel, id, data_src_fmt); } static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) @@ -2395,7 +2549,7 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq) hw_id); return intel_pt_synth_single_pebs_sample(ptq); } - err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id); + err = intel_pt_do_synth_pebs_sample(ptq, pe->evsel, pe->id, pe->data_src_fmt); if (err) return err; } @@ -3355,6 +3509,49 @@ static int intel_pt_process_itrace_start(struct intel_pt *pt, event->itrace_start.tid); } +/* + * Events with data_src are identified by L1_Hit_Indication + * refer https://github.com/intel/perfmon + */ +static int intel_pt_data_src_fmt(struct intel_pt *pt, struct evsel *evsel) +{ + struct perf_env *env = pt->machine->env; + int fmt = DATA_SRC_FORMAT_NA; + + if (!env->cpuid) + return DATA_SRC_FORMAT_ERR; + + /* + * PEBS-via-PT is only supported on E-core non-hybrid. Of those only + * Gracemont and Crestmont have data_src. Check for: + * Alderlake N (Gracemont) + * Sierra Forest (Crestmont) + * Grand Ridge (Crestmont) + */ + + if (!strncmp(env->cpuid, "GenuineIntel,6,190,", 19)) + fmt = DATA_SRC_FORMAT_GRT; + + if (!strncmp(env->cpuid, "GenuineIntel,6,175,", 19) || + !strncmp(env->cpuid, "GenuineIntel,6,182,", 19)) + fmt = DATA_SRC_FORMAT_CMT; + + if (fmt == DATA_SRC_FORMAT_NA) + return fmt; + + /* + * Only data_src events are: + * mem-loads event=0xd0,umask=0x5 + * mem-stores event=0xd0,umask=0x6 + */ + if (evsel->core.attr.type == PERF_TYPE_RAW && + ((evsel->core.attr.config & 0xffff) == 0x5d0 || + (evsel->core.attr.config & 0xffff) == 0x6d0)) + return fmt; + + return DATA_SRC_FORMAT_NA; +} + static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt, union perf_event *event, struct perf_sample *sample) @@ -3375,6 +3572,7 @@ static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt, ptq->pebs[hw_id].evsel = evsel; ptq->pebs[hw_id].id = sample->id; + ptq->pebs[hw_id].data_src_fmt = intel_pt_data_src_fmt(pt, evsel); return 0; } @@ -3924,6 +4122,7 @@ static void intel_pt_setup_pebs_events(struct intel_pt *pt) } pt->single_pebs = true; pt->sample_pebs = true; + pt->pebs_data_src_fmt = intel_pt_data_src_fmt(pt, evsel); pt->pebs_evsel = evsel; } } diff --git a/tools/perf/util/intel-tpebs.c b/tools/perf/util/intel-tpebs.c index 50a3c3e07160..2c421b475b3b 100644 --- a/tools/perf/util/intel-tpebs.c +++ b/tools/perf/util/intel-tpebs.c @@ -254,7 +254,7 @@ int tpebs_start(struct evlist *evsel_list) new = zalloc(sizeof(*new)); if (!new) { ret = -1; - zfree(name); + zfree(&name); goto err; } new->name = name; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 27d5345d2b30..20fd742984e3 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1003,7 +1003,7 @@ static int machine__get_running_kernel_start(struct machine *machine, err = kallsyms__get_symbol_start(filename, "_edata", &addr); if (err) - err = kallsyms__get_function_start(filename, "_etext", &addr); + err = kallsyms__get_symbol_start(filename, "_etext", &addr); if (!err) *end = addr; @@ -1974,7 +1974,7 @@ static void ip__resolve_ams(struct thread *thread, * Thus, we have to try consecutively until we find a match * or else, the symbol is unknown */ - thread__find_cpumode_addr_location(thread, ip, &al); + thread__find_cpumode_addr_location(thread, ip, /*symbols=*/true, &al); ams->addr = ip; ams->al_addr = al.addr; @@ -2076,7 +2076,7 @@ static int add_callchain_ip(struct thread *thread, al.sym = NULL; al.srcline = NULL; if (!cpumode) { - thread__find_cpumode_addr_location(thread, ip, &al); + thread__find_cpumode_addr_location(thread, ip, symbols, &al); } else { if (ip >= PERF_CONTEXT_MAX) { switch (ip) { @@ -2104,6 +2104,8 @@ static int add_callchain_ip(struct thread *thread, } if (symbols) thread__find_symbol(thread, *cpumode, ip, &al); + else + thread__find_map(thread, *cpumode, ip, &al); } if (al.sym != NULL) { diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 432399cbe5dd..09c9cc326c08 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -1136,8 +1136,13 @@ struct map *maps__find_next_entry(struct maps *maps, struct map *map) struct map *result = NULL; down_read(maps__lock(maps)); + while (!maps__maps_by_address_sorted(maps)) { + up_read(maps__lock(maps)); + maps__sort_by_address(maps); + down_read(maps__lock(maps)); + } i = maps__by_address_index(maps, map); - if (i < maps__nr_maps(maps)) + if (++i < maps__nr_maps(maps)) result = map__get(maps__maps_by_address(maps)[i]); up_read(maps__lock(maps)); diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index bf5090f5220b..9c4adfb45f62 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -189,7 +189,7 @@ static bool perf_pmu__mem_events_supported(const char *mnt, struct perf_pmu *pmu if (!e->event_name) return true; - scnprintf(path, PATH_MAX, "%s/devices/%s/events/%s", mnt, pmu->name, e->event_name); + scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/events/%s", mnt, pmu->name, e->event_name); return !stat(path, &st); } diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index cb185c5659d6..68f5de2d79c7 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -266,11 +266,16 @@ pid_t nsinfo__pid(const struct nsinfo *nsi) return RC_CHK_ACCESS(nsi)->pid; } -pid_t nsinfo__in_pidns(const struct nsinfo *nsi) +bool nsinfo__in_pidns(const struct nsinfo *nsi) { return RC_CHK_ACCESS(nsi)->in_pidns; } +void nsinfo__set_in_pidns(struct nsinfo *nsi) +{ + RC_CHK_ACCESS(nsi)->in_pidns = true; +} + void nsinfo__mountns_enter(struct nsinfo *nsi, struct nscookie *nc) { diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index 8c0731c6cbb7..e95c79b80e27 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -58,7 +58,8 @@ void nsinfo__clear_need_setns(struct nsinfo *nsi); pid_t nsinfo__tgid(const struct nsinfo *nsi); pid_t nsinfo__nstgid(const struct nsinfo *nsi); pid_t nsinfo__pid(const struct nsinfo *nsi); -pid_t nsinfo__in_pidns(const struct nsinfo *nsi); +bool nsinfo__in_pidns(const struct nsinfo *nsi); +void nsinfo__set_in_pidns(struct nsinfo *nsi); void nsinfo__mountns_enter(struct nsinfo *nsi, struct nscookie *nc); void nsinfo__mountns_exit(struct nscookie *nc); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 61bdda01a05a..8b4e346808b4 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -33,12 +33,12 @@ #define UNIT_MAX_LEN 31 /* max length for event unit name */ enum event_source { - /* An event loaded from /sys/devices/<pmu>/events. */ + /* An event loaded from /sys/bus/event_source/devices/<pmu>/events. */ EVENT_SRC_SYSFS, /* An event loaded from a CPUID matched json file. */ EVENT_SRC_CPU_JSON, /* - * An event loaded from a /sys/devices/<pmu>/identifier matched json + * An event loaded from a /sys/bus/event_source/devices/<pmu>/identifier matched json * file. */ EVENT_SRC_SYS_JSON, @@ -593,7 +593,7 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, }; if (pmu_events_table__find_event(pmu->events_table, pmu, name, update_alias, &data) == 0) - pmu->cpu_json_aliases++; + pmu->cpu_common_json_aliases++; } pmu->sysfs_aliases++; break; @@ -1807,9 +1807,10 @@ size_t perf_pmu__num_events(struct perf_pmu *pmu) if (pmu->cpu_aliases_added) nr += pmu->cpu_json_aliases; else if (pmu->events_table) - nr += pmu_events_table__num_events(pmu->events_table, pmu) - pmu->cpu_json_aliases; + nr += pmu_events_table__num_events(pmu->events_table, pmu) - + pmu->cpu_common_json_aliases; else - assert(pmu->cpu_json_aliases == 0); + assert(pmu->cpu_json_aliases == 0 && pmu->cpu_common_json_aliases == 0); return pmu->selectable ? nr + 1 : nr; } diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 4397c48ad569..bcd278b9b546 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -131,6 +131,11 @@ struct perf_pmu { uint32_t cpu_json_aliases; /** @sys_json_aliases: Number of json event aliases loaded matching the PMU's identifier. */ uint32_t sys_json_aliases; + /** + * @cpu_common_json_aliases: Number of json events that overlapped with sysfs when + * loading all sysfs events. + */ + uint32_t cpu_common_json_aliases; /** @sysfs_aliases_loaded: Are sysfs aliases loaded from disk? */ bool sysfs_aliases_loaded; /** diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c index d7d67e09d759..362596ed2729 100644 --- a/tools/perf/util/pmus.c +++ b/tools/perf/util/pmus.c @@ -701,11 +701,25 @@ char *perf_pmus__default_pmu_name(void) struct perf_pmu *evsel__find_pmu(const struct evsel *evsel) { struct perf_pmu *pmu = evsel->pmu; + bool legacy_core_type; - if (!pmu) { - pmu = perf_pmus__find_by_type(evsel->core.attr.type); - ((struct evsel *)evsel)->pmu = pmu; + if (pmu) + return pmu; + + pmu = perf_pmus__find_by_type(evsel->core.attr.type); + legacy_core_type = + evsel->core.attr.type == PERF_TYPE_HARDWARE || + evsel->core.attr.type == PERF_TYPE_HW_CACHE; + if (!pmu && legacy_core_type) { + if (perf_pmus__supports_extended_type()) { + u32 type = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT; + + pmu = perf_pmus__find_by_type(type); + } else { + pmu = perf_pmus__find_core_pmu(); + } } + ((struct evsel *)evsel)->pmu = pmu; return pmu; } diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index 81e0135cddf0..a1c71d9793bd 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -282,6 +282,7 @@ bool is_event_supported(u8 type, u64 config) ret = evsel__open(evsel, NULL, tmap) >= 0; } + evsel__close(evsel); evsel__delete(evsel); } diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index ee3d43a7ba45..e7f36ea9e2fa 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -79,7 +79,7 @@ struct pyrf_event { }; #define sample_members \ - sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"), \ + sample_member_def(sample_ip, ip, T_ULONGLONG, "event ip"), \ sample_member_def(sample_pid, pid, T_INT, "event pid"), \ sample_member_def(sample_tid, tid, T_INT, "event tid"), \ sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"), \ @@ -512,6 +512,11 @@ static PyObject *pyrf_event__new(union perf_event *event) event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)) return NULL; + // FIXME this better be dynamic or we need to parse everything + // before calling perf_mmap__consume(), including tracepoint fields. + if (sizeof(pevent->event) < event->header.size) + return NULL; + ptype = pyrf_event__type[event->header.type]; pevent = PyObject_New(struct pyrf_event, ptype); if (pevent != NULL) @@ -1011,20 +1016,22 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, evsel = evlist__event2evsel(evlist, event); if (!evsel) { + Py_DECREF(pyevent); Py_INCREF(Py_None); return Py_None; } pevent->evsel = evsel; - err = evsel__parse_sample(evsel, event, &pevent->sample); - - /* Consume the even only after we parsed it out. */ perf_mmap__consume(&md->core); - if (err) + err = evsel__parse_sample(evsel, &pevent->event, &pevent->sample); + if (err) { + Py_DECREF(pyevent); return PyErr_Format(PyExc_OSError, "perf: can't parse sample, err=%d", err); + } + return pyevent; } end: diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 99376c12dd8e..7c49997fab3a 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -154,6 +154,7 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type { const struct evsel *cur; int evsel_ctx = evsel_context(evsel); + struct perf_pmu *evsel_pmu = evsel__find_pmu(evsel); evlist__for_each_entry(evsel->evlist, cur) { struct perf_stat_aggr *aggr; @@ -180,7 +181,7 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type * Except the SW CLOCK events, * ignore if not the PMU we're looking for. */ - if ((type != STAT_NSECS) && (evsel->pmu != cur->pmu)) + if ((type != STAT_NSECS) && (evsel_pmu != evsel__find_pmu(cur))) continue; aggr = &cur->stats->aggr[aggr_idx]; diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index c6f369b5d893..36c1d3090689 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -90,11 +90,23 @@ int filename__read_build_id(const char *filename, struct build_id *bid) { FILE *fp; int ret = -1; - bool need_swap = false; + bool need_swap = false, elf32; u8 e_ident[EI_NIDENT]; - size_t buf_size; - void *buf; int i; + union { + struct { + Elf32_Ehdr ehdr32; + Elf32_Phdr *phdr32; + }; + struct { + Elf64_Ehdr ehdr64; + Elf64_Phdr *phdr64; + }; + } hdrs; + void *phdr; + size_t phdr_size; + void *buf = NULL; + size_t buf_size = 0; fp = fopen(filename, "r"); if (fp == NULL) @@ -108,117 +120,79 @@ int filename__read_build_id(const char *filename, struct build_id *bid) goto out; need_swap = check_need_swap(e_ident[EI_DATA]); + elf32 = e_ident[EI_CLASS] == ELFCLASS32; - /* for simplicity */ - fseek(fp, 0, SEEK_SET); - - if (e_ident[EI_CLASS] == ELFCLASS32) { - Elf32_Ehdr ehdr; - Elf32_Phdr *phdr; - - if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) - goto out; + if (fread(elf32 ? (void *)&hdrs.ehdr32 : (void *)&hdrs.ehdr64, + elf32 ? sizeof(hdrs.ehdr32) : sizeof(hdrs.ehdr64), + 1, fp) != 1) + goto out; - if (need_swap) { - ehdr.e_phoff = bswap_32(ehdr.e_phoff); - ehdr.e_phentsize = bswap_16(ehdr.e_phentsize); - ehdr.e_phnum = bswap_16(ehdr.e_phnum); + if (need_swap) { + if (elf32) { + hdrs.ehdr32.e_phoff = bswap_32(hdrs.ehdr32.e_phoff); + hdrs.ehdr32.e_phentsize = bswap_16(hdrs.ehdr32.e_phentsize); + hdrs.ehdr32.e_phnum = bswap_16(hdrs.ehdr32.e_phnum); + } else { + hdrs.ehdr64.e_phoff = bswap_64(hdrs.ehdr64.e_phoff); + hdrs.ehdr64.e_phentsize = bswap_16(hdrs.ehdr64.e_phentsize); + hdrs.ehdr64.e_phnum = bswap_16(hdrs.ehdr64.e_phnum); } + } + phdr_size = elf32 ? hdrs.ehdr32.e_phentsize * hdrs.ehdr32.e_phnum + : hdrs.ehdr64.e_phentsize * hdrs.ehdr64.e_phnum; + phdr = malloc(phdr_size); + if (phdr == NULL) + goto out; - buf_size = ehdr.e_phentsize * ehdr.e_phnum; - buf = malloc(buf_size); - if (buf == NULL) - goto out; - - fseek(fp, ehdr.e_phoff, SEEK_SET); - if (fread(buf, buf_size, 1, fp) != 1) - goto out_free; - - for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { - void *tmp; - long offset; - - if (need_swap) { - phdr->p_type = bswap_32(phdr->p_type); - phdr->p_offset = bswap_32(phdr->p_offset); - phdr->p_filesz = bswap_32(phdr->p_filesz); - } - - if (phdr->p_type != PT_NOTE) - continue; - - buf_size = phdr->p_filesz; - offset = phdr->p_offset; - tmp = realloc(buf, buf_size); - if (tmp == NULL) - goto out_free; - - buf = tmp; - fseek(fp, offset, SEEK_SET); - if (fread(buf, buf_size, 1, fp) != 1) - goto out_free; + fseek(fp, elf32 ? hdrs.ehdr32.e_phoff : hdrs.ehdr64.e_phoff, SEEK_SET); + if (fread(phdr, phdr_size, 1, fp) != 1) + goto out_free; - ret = read_build_id(buf, buf_size, bid, need_swap); - if (ret == 0) { - ret = bid->size; - break; - } - } - } else { - Elf64_Ehdr ehdr; - Elf64_Phdr *phdr; + if (elf32) + hdrs.phdr32 = phdr; + else + hdrs.phdr64 = phdr; - if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) - goto out; + for (i = 0; i < elf32 ? hdrs.ehdr32.e_phnum : hdrs.ehdr64.e_phnum; i++) { + size_t p_filesz; if (need_swap) { - ehdr.e_phoff = bswap_64(ehdr.e_phoff); - ehdr.e_phentsize = bswap_16(ehdr.e_phentsize); - ehdr.e_phnum = bswap_16(ehdr.e_phnum); + if (elf32) { + hdrs.phdr32[i].p_type = bswap_32(hdrs.phdr32[i].p_type); + hdrs.phdr32[i].p_offset = bswap_32(hdrs.phdr32[i].p_offset); + hdrs.phdr32[i].p_filesz = bswap_32(hdrs.phdr32[i].p_offset); + } else { + hdrs.phdr64[i].p_type = bswap_32(hdrs.phdr64[i].p_type); + hdrs.phdr64[i].p_offset = bswap_64(hdrs.phdr64[i].p_offset); + hdrs.phdr64[i].p_filesz = bswap_64(hdrs.phdr64[i].p_filesz); + } } + if ((elf32 ? hdrs.phdr32[i].p_type : hdrs.phdr64[i].p_type) != PT_NOTE) + continue; - buf_size = ehdr.e_phentsize * ehdr.e_phnum; - buf = malloc(buf_size); - if (buf == NULL) - goto out; - - fseek(fp, ehdr.e_phoff, SEEK_SET); - if (fread(buf, buf_size, 1, fp) != 1) - goto out_free; - - for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) { + p_filesz = elf32 ? hdrs.phdr32[i].p_filesz : hdrs.phdr64[i].p_filesz; + if (p_filesz > buf_size) { void *tmp; - long offset; - - if (need_swap) { - phdr->p_type = bswap_32(phdr->p_type); - phdr->p_offset = bswap_64(phdr->p_offset); - phdr->p_filesz = bswap_64(phdr->p_filesz); - } - if (phdr->p_type != PT_NOTE) - continue; - - buf_size = phdr->p_filesz; - offset = phdr->p_offset; + buf_size = p_filesz; tmp = realloc(buf, buf_size); if (tmp == NULL) goto out_free; - buf = tmp; - fseek(fp, offset, SEEK_SET); - if (fread(buf, buf_size, 1, fp) != 1) - goto out_free; + } + fseek(fp, elf32 ? hdrs.phdr32[i].p_offset : hdrs.phdr64[i].p_offset, SEEK_SET); + if (fread(buf, p_filesz, 1, fp) != 1) + goto out_free; - ret = read_build_id(buf, buf_size, bid, need_swap); - if (ret == 0) { - ret = bid->size; - break; - } + ret = read_build_id(buf, p_filesz, bid, need_swap); + if (ret == 0) { + ret = bid->size; + break; } } out_free: free(buf); + free(phdr); out: fclose(fp); return ret; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 3bbf173ad822..c0ec5ed4f1aa 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1405,6 +1405,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, goto out_err; } } + map__zput(new_node->map); free(new_node); } diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 0ffdd52d86d7..309d573eac9a 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -406,7 +406,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bo } void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, - struct addr_location *al) + bool symbols, struct addr_location *al) { size_t i; const u8 cpumodes[] = { @@ -417,7 +417,11 @@ void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, }; for (i = 0; i < ARRAY_SIZE(cpumodes); i++) { - thread__find_symbol(thread, cpumodes[i], addr, al); + if (symbols) + thread__find_symbol(thread, cpumodes[i], addr, al); + else + thread__find_map(thread, cpumodes[i], addr, al); + if (al->map) break; } diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 6cbf6eb2812e..1fb32e7d62a4 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -122,7 +122,7 @@ struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al); void thread__find_cpumode_addr_location(struct thread *thread, u64 addr, - struct addr_location *al); + bool symbols, struct addr_location *al); int thread__memcpy(struct thread *thread, struct machine *machine, void *buf, u64 ip, int len, bool *is64bit); diff --git a/tools/perf/util/units.c b/tools/perf/util/units.c index 32c39cfe209b..4c6a86e1cb54 100644 --- a/tools/perf/util/units.c +++ b/tools/perf/util/units.c @@ -64,7 +64,7 @@ unsigned long convert_unit(unsigned long value, char *unit) int unit_number__scnprintf(char *buf, size_t size, u64 n) { - char unit[4] = "BKMG"; + char unit[] = "BKMG"; int i = 0; while (((n / 1024) > 1) && (i < 3)) { |