diff options
Diffstat (limited to 'tools/perf/util')
90 files changed, 2588 insertions, 300 deletions
diff --git a/tools/perf/util/Build b/tools/perf/util/Build index e3e12f9d4733..8c0d9f368ebc 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -10,6 +10,7 @@ perf-y += db-export.o perf-y += env.o perf-y += event.o perf-y += evlist.o +perf-y += evlist-hybrid.o perf-y += sideband_evlist.o perf-y += evsel.o perf-y += evsel_fprintf.o @@ -23,6 +24,7 @@ perf-y += llvm-utils.o perf-y += mmap.o perf-y += memswap.o perf-y += parse-events.o +perf-y += parse-events-hybrid.o perf-y += perf_regs.o perf-y += path.o perf-y += print_binary.o @@ -69,6 +71,7 @@ perf-y += parse-events-bison.o perf-y += pmu.o perf-y += pmu-flex.o perf-y += pmu-bison.o +perf-y += pmu-hybrid.o perf-y += trace-event-read.o perf-y += trace-event-info.o perf-y += trace-event-scripting.o @@ -102,6 +105,7 @@ perf-y += rwsem.o perf-y += thread-stack.o perf-y += spark.o perf-y += topdown.o +perf-y += iostat.o perf-y += stream.o perf-$(CONFIG_AUXTRACE) += auxtrace.o perf-$(CONFIG_AUXTRACE) += intel-pt-decoder/ @@ -164,6 +168,7 @@ perf-$(CONFIG_LIBUNWIND_X86) += libunwind/x86_32.o perf-$(CONFIG_LIBUNWIND_AARCH64) += libunwind/arm64.o perf-$(CONFIG_LIBBABELTRACE) += data-convert-bt.o +perf-y += data-convert-json.o perf-y += scripting-engines/ diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index e60841b86d27..abe1499a9164 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1161,6 +1161,7 @@ struct annotate_args { s64 offset; char *line; int line_nr; + char *fileloc; }; static void annotation_line__init(struct annotation_line *al, @@ -1170,6 +1171,7 @@ static void annotation_line__init(struct annotation_line *al, al->offset = args->offset; al->line = strdup(args->line); al->line_nr = args->line_nr; + al->fileloc = args->fileloc; al->data_nr = nr; } @@ -1366,7 +1368,6 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start { struct disasm_line *dl = container_of(al, struct disasm_line, al); static const char *prev_line; - static const char *prev_color; if (al->offset != -1) { double max_percent = 0.0; @@ -1405,20 +1406,6 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start color = get_percent_color(max_percent); - /* - * Also color the filename and line if needed, with - * the same color than the percentage. Don't print it - * twice for close colored addr with the same filename:line - */ - if (al->path) { - if (!prev_line || strcmp(prev_line, al->path) - || color != prev_color) { - color_fprintf(stdout, color, " %s", al->path); - prev_line = al->path; - prev_color = color; - } - } - for (i = 0; i < nr_percent; i++) { struct annotation_data *data = &al->data[i]; double percent; @@ -1439,6 +1426,19 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start printf(" : "); disasm_line__print(dl, start, addr_fmt_width); + + /* + * Also color the filename and line if needed, with + * the same color than the percentage. Don't print it + * twice for close colored addr with the same filename:line + */ + if (al->path) { + if (!prev_line || strcmp(prev_line, al->path)) { + color_fprintf(stdout, color, " // %s", al->path); + prev_line = al->path; + } + } + printf("\n"); } else if (max_lines && printed >= max_lines) return 1; @@ -1454,7 +1454,7 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start if (!*al->line) printf(" %*s:\n", width, " "); else - printf(" %*s: %*s %s\n", width, " ", addr_fmt_width, " ", al->line); + printf(" %*s: %-*d %s\n", width, " ", addr_fmt_width, al->line_nr, al->line); } return 0; @@ -1482,7 +1482,7 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start */ static int symbol__parse_objdump_line(struct symbol *sym, struct annotate_args *args, - char *parsed_line, int *line_nr) + char *parsed_line, int *line_nr, char **fileloc) { struct map *map = args->ms.map; struct annotation *notes = symbol__annotation(sym); @@ -1494,6 +1494,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, /* /filename:linenr ? Save line number and ignore. */ if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) { *line_nr = atoi(parsed_line + match[1].rm_so); + *fileloc = strdup(parsed_line); return 0; } @@ -1513,6 +1514,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, args->offset = offset; args->line = parsed_line; args->line_nr = *line_nr; + args->fileloc = *fileloc; args->ms.sym = sym; dl = disasm_line__new(args); @@ -1807,6 +1809,7 @@ static int symbol__disassemble_bpf(struct symbol *sym, args->offset = -1; args->line = strdup(srcline); args->line_nr = 0; + args->fileloc = NULL; args->ms.sym = sym; dl = disasm_line__new(args); if (dl) { @@ -1818,6 +1821,7 @@ static int symbol__disassemble_bpf(struct symbol *sym, args->offset = pc; args->line = buf + prev_buf_size; args->line_nr = 0; + args->fileloc = NULL; args->ms.sym = sym; dl = disasm_line__new(args); if (dl) @@ -1852,6 +1856,7 @@ symbol__disassemble_bpf_image(struct symbol *sym, args->offset = -1; args->line = strdup("to be implemented"); args->line_nr = 0; + args->fileloc = NULL; dl = disasm_line__new(args); if (dl) annotation_line__add(&dl->al, ¬es->src->source); @@ -1933,6 +1938,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) bool delete_extract = false; bool decomp = false; int lineno = 0; + char *fileloc = NULL; int nline; char *line; size_t line_len; @@ -2060,7 +2066,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) * See disasm_line__new() and struct disasm_line::line_nr. */ if (symbol__parse_objdump_line(sym, args, expanded_line, - &lineno) < 0) + &lineno, &fileloc) < 0) break; nline++; } @@ -3144,6 +3150,10 @@ static int annotation__config(const char *var, const char *value, void *data) opt->use_offset = perf_config_bool("use_offset", value); } else if (!strcmp(var, "annotate.disassembler_style")) { opt->disassembler_style = value; + } else if (!strcmp(var, "annotate.demangle")) { + symbol_conf.demangle = perf_config_bool("demangle", value); + } else if (!strcmp(var, "annotate.demangle_kernel")) { + symbol_conf.demangle_kernel = perf_config_bool("demangle_kernel", value); } else { pr_debug("%s variable unknown, ignoring...", var); } diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 096cdaf21b01..3757416bcf46 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -84,6 +84,7 @@ struct annotation_options { print_lines, full_path, show_linenr, + show_fileloc, show_nr_jumps, show_minmax_cycle, show_asm_raw, @@ -136,6 +137,7 @@ struct annotation_line { s64 offset; char *line; int line_nr; + char *fileloc; int jump_sources; float ipc; u64 cycles; diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 9087f1bffd3d..fbb3c4057c30 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -671,7 +671,7 @@ int bpf__probe(struct bpf_object *obj) * After probing, let's consider prologue, which * adds program fetcher to BPF programs. * - * hook_load_preprocessorr() hooks pre-processor + * hook_load_preprocessor() hooks pre-processor * to bpf_program, let it generate prologue * dynamically during loading. */ diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index 04f89120b323..ddb52f748c8e 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -5,6 +5,7 @@ #include <assert.h> #include <limits.h> #include <unistd.h> +#include <sys/file.h> #include <sys/time.h> #include <sys/resource.h> #include <linux/err.h> @@ -12,14 +13,24 @@ #include <bpf/bpf.h> #include <bpf/btf.h> #include <bpf/libbpf.h> +#include <api/fs/fs.h> +#include <perf/bpf_perf.h> #include "bpf_counter.h" #include "counts.h" #include "debug.h" #include "evsel.h" +#include "evlist.h" #include "target.h" +#include "cpumap.h" +#include "thread_map.h" #include "bpf_skel/bpf_prog_profiler.skel.h" +#include "bpf_skel/bperf_u.h" +#include "bpf_skel/bperf_leader.skel.h" +#include "bpf_skel/bperf_follower.skel.h" + +#define ATTR_MAP_SIZE 16 static inline void *u64_to_ptr(__u64 ptr) { @@ -204,6 +215,17 @@ static int bpf_program_profiler__enable(struct evsel *evsel) return 0; } +static int bpf_program_profiler__disable(struct evsel *evsel) +{ + struct bpf_counter *counter; + + list_for_each_entry(counter, &evsel->bpf_counter_list, list) { + assert(counter->skel != NULL); + bpf_prog_profiler_bpf__detach(counter->skel); + } + return 0; +} + static int bpf_program_profiler__read(struct evsel *evsel) { // perf_cpu_map uses /sys/devices/system/cpu/online @@ -269,22 +291,527 @@ static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu, struct bpf_counter_ops bpf_program_profiler_ops = { .load = bpf_program_profiler__load, .enable = bpf_program_profiler__enable, + .disable = bpf_program_profiler__disable, .read = bpf_program_profiler__read, .destroy = bpf_program_profiler__destroy, .install_pe = bpf_program_profiler__install_pe, }; +static __u32 bpf_link_get_id(int fd) +{ + struct bpf_link_info link_info = {0}; + __u32 link_info_len = sizeof(link_info); + + bpf_obj_get_info_by_fd(fd, &link_info, &link_info_len); + return link_info.id; +} + +static __u32 bpf_link_get_prog_id(int fd) +{ + struct bpf_link_info link_info = {0}; + __u32 link_info_len = sizeof(link_info); + + bpf_obj_get_info_by_fd(fd, &link_info, &link_info_len); + return link_info.prog_id; +} + +static __u32 bpf_map_get_id(int fd) +{ + struct bpf_map_info map_info = {0}; + __u32 map_info_len = sizeof(map_info); + + bpf_obj_get_info_by_fd(fd, &map_info, &map_info_len); + return map_info.id; +} + +static bool bperf_attr_map_compatible(int attr_map_fd) +{ + struct bpf_map_info map_info = {0}; + __u32 map_info_len = sizeof(map_info); + int err; + + err = bpf_obj_get_info_by_fd(attr_map_fd, &map_info, &map_info_len); + + if (err) + return false; + return (map_info.key_size == sizeof(struct perf_event_attr)) && + (map_info.value_size == sizeof(struct perf_event_attr_map_entry)); +} + +static int bperf_lock_attr_map(struct target *target) +{ + char path[PATH_MAX]; + int map_fd, err; + + if (target->attr_map) { + scnprintf(path, PATH_MAX, "%s", target->attr_map); + } else { + scnprintf(path, PATH_MAX, "%s/fs/bpf/%s", sysfs__mountpoint(), + BPF_PERF_DEFAULT_ATTR_MAP_PATH); + } + + if (access(path, F_OK)) { + map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, + sizeof(struct perf_event_attr), + sizeof(struct perf_event_attr_map_entry), + ATTR_MAP_SIZE, 0); + if (map_fd < 0) + return -1; + + err = bpf_obj_pin(map_fd, path); + if (err) { + /* someone pinned the map in parallel? */ + close(map_fd); + map_fd = bpf_obj_get(path); + if (map_fd < 0) + return -1; + } + } else { + map_fd = bpf_obj_get(path); + if (map_fd < 0) + return -1; + } + + if (!bperf_attr_map_compatible(map_fd)) { + close(map_fd); + return -1; + + } + err = flock(map_fd, LOCK_EX); + if (err) { + close(map_fd); + return -1; + } + return map_fd; +} + +/* trigger the leader program on a cpu */ +static int bperf_trigger_reading(int prog_fd, int cpu) +{ + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .ctx_in = NULL, + .ctx_size_in = 0, + .flags = BPF_F_TEST_RUN_ON_CPU, + .cpu = cpu, + .retval = 0, + ); + + return bpf_prog_test_run_opts(prog_fd, &opts); +} + +static int bperf_check_target(struct evsel *evsel, + struct target *target, + enum bperf_filter_type *filter_type, + __u32 *filter_entry_cnt) +{ + if (evsel->leader->core.nr_members > 1) { + pr_err("bpf managed perf events do not yet support groups.\n"); + return -1; + } + + /* determine filter type based on target */ + if (target->system_wide) { + *filter_type = BPERF_FILTER_GLOBAL; + *filter_entry_cnt = 1; + } else if (target->cpu_list) { + *filter_type = BPERF_FILTER_CPU; + *filter_entry_cnt = perf_cpu_map__nr(evsel__cpus(evsel)); + } else if (target->tid) { + *filter_type = BPERF_FILTER_PID; + *filter_entry_cnt = perf_thread_map__nr(evsel->core.threads); + } else if (target->pid || evsel->evlist->workload.pid != -1) { + *filter_type = BPERF_FILTER_TGID; + *filter_entry_cnt = perf_thread_map__nr(evsel->core.threads); + } else { + pr_err("bpf managed perf events do not yet support these targets.\n"); + return -1; + } + + return 0; +} + +static struct perf_cpu_map *all_cpu_map; + +static int bperf_reload_leader_program(struct evsel *evsel, int attr_map_fd, + struct perf_event_attr_map_entry *entry) +{ + struct bperf_leader_bpf *skel = bperf_leader_bpf__open(); + int link_fd, diff_map_fd, err; + struct bpf_link *link = NULL; + + if (!skel) { + pr_err("Failed to open leader skeleton\n"); + return -1; + } + + bpf_map__resize(skel->maps.events, libbpf_num_possible_cpus()); + err = bperf_leader_bpf__load(skel); + if (err) { + pr_err("Failed to load leader skeleton\n"); + goto out; + } + + err = -1; + link = bpf_program__attach(skel->progs.on_switch); + if (!link) { + pr_err("Failed to attach leader program\n"); + goto out; + } + + link_fd = bpf_link__fd(link); + diff_map_fd = bpf_map__fd(skel->maps.diff_readings); + entry->link_id = bpf_link_get_id(link_fd); + entry->diff_map_id = bpf_map_get_id(diff_map_fd); + err = bpf_map_update_elem(attr_map_fd, &evsel->core.attr, entry, BPF_ANY); + assert(err == 0); + + evsel->bperf_leader_link_fd = bpf_link_get_fd_by_id(entry->link_id); + assert(evsel->bperf_leader_link_fd >= 0); + + /* + * save leader_skel for install_pe, which is called within + * following evsel__open_per_cpu call + */ + evsel->leader_skel = skel; + evsel__open_per_cpu(evsel, all_cpu_map, -1); + +out: + bperf_leader_bpf__destroy(skel); + bpf_link__destroy(link); + return err; +} + +static int bperf__load(struct evsel *evsel, struct target *target) +{ + struct perf_event_attr_map_entry entry = {0xffffffff, 0xffffffff}; + int attr_map_fd, diff_map_fd = -1, err; + enum bperf_filter_type filter_type; + __u32 filter_entry_cnt, i; + + if (bperf_check_target(evsel, target, &filter_type, &filter_entry_cnt)) + return -1; + + if (!all_cpu_map) { + all_cpu_map = perf_cpu_map__new(NULL); + if (!all_cpu_map) + return -1; + } + + evsel->bperf_leader_prog_fd = -1; + evsel->bperf_leader_link_fd = -1; + + /* + * Step 1: hold a fd on the leader program and the bpf_link, if + * the program is not already gone, reload the program. + * Use flock() to ensure exclusive access to the perf_event_attr + * map. + */ + attr_map_fd = bperf_lock_attr_map(target); + if (attr_map_fd < 0) { + pr_err("Failed to lock perf_event_attr map\n"); + return -1; + } + + err = bpf_map_lookup_elem(attr_map_fd, &evsel->core.attr, &entry); + if (err) { + err = bpf_map_update_elem(attr_map_fd, &evsel->core.attr, &entry, BPF_ANY); + if (err) + goto out; + } + + evsel->bperf_leader_link_fd = bpf_link_get_fd_by_id(entry.link_id); + if (evsel->bperf_leader_link_fd < 0 && + bperf_reload_leader_program(evsel, attr_map_fd, &entry)) + goto out; + + /* + * The bpf_link holds reference to the leader program, and the + * leader program holds reference to the maps. Therefore, if + * link_id is valid, diff_map_id should also be valid. + */ + evsel->bperf_leader_prog_fd = bpf_prog_get_fd_by_id( + bpf_link_get_prog_id(evsel->bperf_leader_link_fd)); + assert(evsel->bperf_leader_prog_fd >= 0); + + diff_map_fd = bpf_map_get_fd_by_id(entry.diff_map_id); + assert(diff_map_fd >= 0); + + /* + * bperf uses BPF_PROG_TEST_RUN to get accurate reading. Check + * whether the kernel support it + */ + err = bperf_trigger_reading(evsel->bperf_leader_prog_fd, 0); + if (err) { + pr_err("The kernel does not support test_run for raw_tp BPF programs.\n" + "Therefore, --use-bpf might show inaccurate readings\n"); + goto out; + } + + /* Step 2: load the follower skeleton */ + evsel->follower_skel = bperf_follower_bpf__open(); + if (!evsel->follower_skel) { + pr_err("Failed to open follower skeleton\n"); + goto out; + } + + /* attach fexit program to the leader program */ + bpf_program__set_attach_target(evsel->follower_skel->progs.fexit_XXX, + evsel->bperf_leader_prog_fd, "on_switch"); + + /* connect to leader diff_reading map */ + bpf_map__reuse_fd(evsel->follower_skel->maps.diff_readings, diff_map_fd); + + /* set up reading map */ + bpf_map__set_max_entries(evsel->follower_skel->maps.accum_readings, + filter_entry_cnt); + /* set up follower filter based on target */ + bpf_map__set_max_entries(evsel->follower_skel->maps.filter, + filter_entry_cnt); + err = bperf_follower_bpf__load(evsel->follower_skel); + if (err) { + pr_err("Failed to load follower skeleton\n"); + bperf_follower_bpf__destroy(evsel->follower_skel); + evsel->follower_skel = NULL; + goto out; + } + + for (i = 0; i < filter_entry_cnt; i++) { + int filter_map_fd; + __u32 key; + + if (filter_type == BPERF_FILTER_PID || + filter_type == BPERF_FILTER_TGID) + key = evsel->core.threads->map[i].pid; + else if (filter_type == BPERF_FILTER_CPU) + key = evsel->core.cpus->map[i]; + else + break; + + filter_map_fd = bpf_map__fd(evsel->follower_skel->maps.filter); + bpf_map_update_elem(filter_map_fd, &key, &i, BPF_ANY); + } + + evsel->follower_skel->bss->type = filter_type; + + err = bperf_follower_bpf__attach(evsel->follower_skel); + +out: + if (err && evsel->bperf_leader_link_fd >= 0) + close(evsel->bperf_leader_link_fd); + if (err && evsel->bperf_leader_prog_fd >= 0) + close(evsel->bperf_leader_prog_fd); + if (diff_map_fd >= 0) + close(diff_map_fd); + + flock(attr_map_fd, LOCK_UN); + close(attr_map_fd); + + return err; +} + +static int bperf__install_pe(struct evsel *evsel, int cpu, int fd) +{ + struct bperf_leader_bpf *skel = evsel->leader_skel; + + return bpf_map_update_elem(bpf_map__fd(skel->maps.events), + &cpu, &fd, BPF_ANY); +} + +/* + * trigger the leader prog on each cpu, so the accum_reading map could get + * the latest readings. + */ +static int bperf_sync_counters(struct evsel *evsel) +{ + int num_cpu, i, cpu; + + num_cpu = all_cpu_map->nr; + for (i = 0; i < num_cpu; i++) { + cpu = all_cpu_map->map[i]; + bperf_trigger_reading(evsel->bperf_leader_prog_fd, cpu); + } + return 0; +} + +static int bperf__enable(struct evsel *evsel) +{ + evsel->follower_skel->bss->enabled = 1; + return 0; +} + +static int bperf__disable(struct evsel *evsel) +{ + evsel->follower_skel->bss->enabled = 0; + return 0; +} + +static int bperf__read(struct evsel *evsel) +{ + struct bperf_follower_bpf *skel = evsel->follower_skel; + __u32 num_cpu_bpf = cpu__max_cpu(); + struct bpf_perf_event_value values[num_cpu_bpf]; + int reading_map_fd, err = 0; + __u32 i, j, num_cpu; + + bperf_sync_counters(evsel); + reading_map_fd = bpf_map__fd(skel->maps.accum_readings); + + for (i = 0; i < bpf_map__max_entries(skel->maps.accum_readings); i++) { + __u32 cpu; + + err = bpf_map_lookup_elem(reading_map_fd, &i, values); + if (err) + goto out; + switch (evsel->follower_skel->bss->type) { + case BPERF_FILTER_GLOBAL: + assert(i == 0); + + num_cpu = all_cpu_map->nr; + for (j = 0; j < num_cpu; j++) { + cpu = all_cpu_map->map[j]; + perf_counts(evsel->counts, cpu, 0)->val = values[cpu].counter; + perf_counts(evsel->counts, cpu, 0)->ena = values[cpu].enabled; + perf_counts(evsel->counts, cpu, 0)->run = values[cpu].running; + } + break; + case BPERF_FILTER_CPU: + cpu = evsel->core.cpus->map[i]; + perf_counts(evsel->counts, i, 0)->val = values[cpu].counter; + perf_counts(evsel->counts, i, 0)->ena = values[cpu].enabled; + perf_counts(evsel->counts, i, 0)->run = values[cpu].running; + break; + case BPERF_FILTER_PID: + case BPERF_FILTER_TGID: + perf_counts(evsel->counts, 0, i)->val = 0; + perf_counts(evsel->counts, 0, i)->ena = 0; + perf_counts(evsel->counts, 0, i)->run = 0; + + for (cpu = 0; cpu < num_cpu_bpf; cpu++) { + perf_counts(evsel->counts, 0, i)->val += values[cpu].counter; + perf_counts(evsel->counts, 0, i)->ena += values[cpu].enabled; + perf_counts(evsel->counts, 0, i)->run += values[cpu].running; + } + break; + default: + break; + } + } +out: + return err; +} + +static int bperf__destroy(struct evsel *evsel) +{ + bperf_follower_bpf__destroy(evsel->follower_skel); + close(evsel->bperf_leader_prog_fd); + close(evsel->bperf_leader_link_fd); + return 0; +} + +/* + * bperf: share hardware PMCs with BPF + * + * perf uses performance monitoring counters (PMC) to monitor system + * performance. The PMCs are limited hardware resources. For example, + * Intel CPUs have 3x fixed PMCs and 4x programmable PMCs per cpu. + * + * Modern data center systems use these PMCs in many different ways: + * system level monitoring, (maybe nested) container level monitoring, per + * process monitoring, profiling (in sample mode), etc. In some cases, + * there are more active perf_events than available hardware PMCs. To allow + * all perf_events to have a chance to run, it is necessary to do expensive + * time multiplexing of events. + * + * On the other hand, many monitoring tools count the common metrics + * (cycles, instructions). It is a waste to have multiple tools create + * multiple perf_events of "cycles" and occupy multiple PMCs. + * + * bperf tries to reduce such wastes by allowing multiple perf_events of + * "cycles" or "instructions" (at different scopes) to share PMUs. Instead + * of having each perf-stat session to read its own perf_events, bperf uses + * BPF programs to read the perf_events and aggregate readings to BPF maps. + * Then, the perf-stat session(s) reads the values from these BPF maps. + * + * || + * shared progs and maps <- || -> per session progs and maps + * || + * --------------- || + * | perf_events | || + * --------------- fexit || ----------------- + * | --------||----> | follower prog | + * --------------- / || --- ----------------- + * cs -> | leader prog |/ ||/ | | + * --> --------------- /|| -------------- ------------------ + * / | | / || | filter map | | accum_readings | + * / ------------ ------------ || -------------- ------------------ + * | | prev map | | diff map | || | + * | ------------ ------------ || | + * \ || | + * = \ ==================================================== | ============ + * \ / user space + * \ / + * \ / + * BPF_PROG_TEST_RUN BPF_MAP_LOOKUP_ELEM + * \ / + * \ / + * \------ perf-stat ----------------------/ + * + * The figure above shows the architecture of bperf. Note that the figure + * is divided into 3 regions: shared progs and maps (top left), per session + * progs and maps (top right), and user space (bottom). + * + * The leader prog is triggered on each context switch (cs). The leader + * prog reads perf_events and stores the difference (current_reading - + * previous_reading) to the diff map. For the same metric, e.g. "cycles", + * multiple perf-stat sessions share the same leader prog. + * + * Each perf-stat session creates a follower prog as fexit program to the + * leader prog. It is possible to attach up to BPF_MAX_TRAMP_PROGS (38) + * follower progs to the same leader prog. The follower prog checks current + * task and processor ID to decide whether to add the value from the diff + * map to its accumulated reading map (accum_readings). + * + * Finally, perf-stat user space reads the value from accum_reading map. + * + * Besides context switch, it is also necessary to trigger the leader prog + * before perf-stat reads the value. Otherwise, the accum_reading map may + * not have the latest reading from the perf_events. This is achieved by + * triggering the event via sys_bpf(BPF_PROG_TEST_RUN) to each CPU. + * + * Comment before the definition of struct perf_event_attr_map_entry + * describes how different sessions of perf-stat share information about + * the leader prog. + */ + +struct bpf_counter_ops bperf_ops = { + .load = bperf__load, + .enable = bperf__enable, + .disable = bperf__disable, + .read = bperf__read, + .install_pe = bperf__install_pe, + .destroy = bperf__destroy, +}; + +static inline bool bpf_counter_skip(struct evsel *evsel) +{ + return list_empty(&evsel->bpf_counter_list) && + evsel->follower_skel == NULL; +} + int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd) { - if (list_empty(&evsel->bpf_counter_list)) + if (bpf_counter_skip(evsel)) return 0; return evsel->bpf_counter_ops->install_pe(evsel, cpu, fd); } int bpf_counter__load(struct evsel *evsel, struct target *target) { - if (target__has_bpf(target)) + if (target->bpf_str) evsel->bpf_counter_ops = &bpf_program_profiler_ops; + else if (target->use_bpf || evsel->bpf_counter || + evsel__match_bpf_counter_events(evsel->name)) + evsel->bpf_counter_ops = &bperf_ops; if (evsel->bpf_counter_ops) return evsel->bpf_counter_ops->load(evsel, target); @@ -293,21 +820,28 @@ int bpf_counter__load(struct evsel *evsel, struct target *target) int bpf_counter__enable(struct evsel *evsel) { - if (list_empty(&evsel->bpf_counter_list)) + if (bpf_counter_skip(evsel)) return 0; return evsel->bpf_counter_ops->enable(evsel); } +int bpf_counter__disable(struct evsel *evsel) +{ + if (bpf_counter_skip(evsel)) + return 0; + return evsel->bpf_counter_ops->disable(evsel); +} + int bpf_counter__read(struct evsel *evsel) { - if (list_empty(&evsel->bpf_counter_list)) + if (bpf_counter_skip(evsel)) return -EAGAIN; return evsel->bpf_counter_ops->read(evsel); } void bpf_counter__destroy(struct evsel *evsel) { - if (list_empty(&evsel->bpf_counter_list)) + if (bpf_counter_skip(evsel)) return; evsel->bpf_counter_ops->destroy(evsel); evsel->bpf_counter_ops = NULL; diff --git a/tools/perf/util/bpf_counter.h b/tools/perf/util/bpf_counter.h index 2eca210e5dc1..d6d907c3dcf9 100644 --- a/tools/perf/util/bpf_counter.h +++ b/tools/perf/util/bpf_counter.h @@ -18,6 +18,7 @@ typedef int (*bpf_counter_evsel_install_pe_op)(struct evsel *evsel, struct bpf_counter_ops { bpf_counter_evsel_target_op load; bpf_counter_evsel_op enable; + bpf_counter_evsel_op disable; bpf_counter_evsel_op read; bpf_counter_evsel_op destroy; bpf_counter_evsel_install_pe_op install_pe; @@ -32,13 +33,14 @@ struct bpf_counter { int bpf_counter__load(struct evsel *evsel, struct target *target); int bpf_counter__enable(struct evsel *evsel); +int bpf_counter__disable(struct evsel *evsel); int bpf_counter__read(struct evsel *evsel); void bpf_counter__destroy(struct evsel *evsel); int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd); #else /* HAVE_BPF_SKEL */ -#include<linux/err.h> +#include <linux/err.h> static inline int bpf_counter__load(struct evsel *evsel __maybe_unused, struct target *target __maybe_unused) @@ -51,6 +53,11 @@ static inline int bpf_counter__enable(struct evsel *evsel __maybe_unused) return 0; } +static inline int bpf_counter__disable(struct evsel *evsel __maybe_unused) +{ + return 0; +} + static inline int bpf_counter__read(struct evsel *evsel __maybe_unused) { return -EAGAIN; diff --git a/tools/perf/util/bpf_skel/bperf.h b/tools/perf/util/bpf_skel/bperf.h new file mode 100644 index 000000000000..186a5551ddb9 --- /dev/null +++ b/tools/perf/util/bpf_skel/bperf.h @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2021 Facebook + +#ifndef __BPERF_STAT_H +#define __BPERF_STAT_H + +typedef struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} reading_map; + +#endif /* __BPERF_STAT_H */ diff --git a/tools/perf/util/bpf_skel/bperf_follower.bpf.c b/tools/perf/util/bpf_skel/bperf_follower.bpf.c new file mode 100644 index 000000000000..b8fa3cb2da23 --- /dev/null +++ b/tools/perf/util/bpf_skel/bperf_follower.bpf.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2021 Facebook +#include <linux/bpf.h> +#include <linux/perf_event.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bperf.h" +#include "bperf_u.h" + +reading_map diff_readings SEC(".maps"); +reading_map accum_readings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} filter SEC(".maps"); + +enum bperf_filter_type type = 0; +int enabled = 0; + +SEC("fexit/XXX") +int BPF_PROG(fexit_XXX) +{ + struct bpf_perf_event_value *diff_val, *accum_val; + __u32 filter_key, zero = 0; + __u32 *accum_key; + + if (!enabled) + return 0; + + switch (type) { + case BPERF_FILTER_GLOBAL: + accum_key = &zero; + goto do_add; + case BPERF_FILTER_CPU: + filter_key = bpf_get_smp_processor_id(); + break; + case BPERF_FILTER_PID: + filter_key = bpf_get_current_pid_tgid() & 0xffffffff; + break; + case BPERF_FILTER_TGID: + filter_key = bpf_get_current_pid_tgid() >> 32; + break; + default: + return 0; + } + + accum_key = bpf_map_lookup_elem(&filter, &filter_key); + if (!accum_key) + return 0; + +do_add: + diff_val = bpf_map_lookup_elem(&diff_readings, &zero); + if (!diff_val) + return 0; + + accum_val = bpf_map_lookup_elem(&accum_readings, accum_key); + if (!accum_val) + return 0; + + accum_val->counter += diff_val->counter; + accum_val->enabled += diff_val->enabled; + accum_val->running += diff_val->running; + + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/perf/util/bpf_skel/bperf_leader.bpf.c b/tools/perf/util/bpf_skel/bperf_leader.bpf.c new file mode 100644 index 000000000000..4f70d1459e86 --- /dev/null +++ b/tools/perf/util/bpf_skel/bperf_leader.bpf.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2021 Facebook +#include <linux/bpf.h> +#include <linux/perf_event.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bperf.h" + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(int)); + __uint(map_flags, BPF_F_PRESERVE_ELEMS); +} events SEC(".maps"); + +reading_map prev_readings SEC(".maps"); +reading_map diff_readings SEC(".maps"); + +SEC("raw_tp/sched_switch") +int BPF_PROG(on_switch) +{ + struct bpf_perf_event_value val, *prev_val, *diff_val; + __u32 key = bpf_get_smp_processor_id(); + __u32 zero = 0; + long err; + + prev_val = bpf_map_lookup_elem(&prev_readings, &zero); + if (!prev_val) + return 0; + + diff_val = bpf_map_lookup_elem(&diff_readings, &zero); + if (!diff_val) + return 0; + + err = bpf_perf_event_read_value(&events, key, &val, sizeof(val)); + if (err) + return 0; + + diff_val->counter = val.counter - prev_val->counter; + diff_val->enabled = val.enabled - prev_val->enabled; + diff_val->running = val.running - prev_val->running; + *prev_val = val; + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/perf/util/bpf_skel/bperf_u.h b/tools/perf/util/bpf_skel/bperf_u.h new file mode 100644 index 000000000000..1ce0c2c905c1 --- /dev/null +++ b/tools/perf/util/bpf_skel/bperf_u.h @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2021 Facebook + +#ifndef __BPERF_STAT_U_H +#define __BPERF_STAT_U_H + +enum bperf_filter_type { + BPERF_FILTER_GLOBAL = 1, + BPERF_FILTER_CPU, + BPERF_FILTER_PID, + BPERF_FILTER_TGID, +}; + +#endif /* __BPERF_STAT_U_H */ diff --git a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c index c7cec92d0236..ab12b4c4ece2 100644 --- a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c +++ b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c @@ -52,7 +52,7 @@ int BPF_PROG(fentry_XXX) static inline void fexit_update_maps(struct bpf_perf_event_value *after) { - struct bpf_perf_event_value *before, diff, *accum; + struct bpf_perf_event_value *before, diff; __u32 zero = 0; before = bpf_map_lookup_elem(&fentry_readings, &zero); @@ -78,7 +78,6 @@ int BPF_PROG(fexit_XXX) { struct bpf_perf_event_value reading; __u32 cpu = bpf_get_smp_processor_id(); - __u32 one = 1, zero = 0; int err; /* read all events before updating the maps, to reduce error */ diff --git a/tools/perf/util/call-path.h b/tools/perf/util/call-path.h index 6b3229106f16..5875cfc8106e 100644 --- a/tools/perf/util/call-path.h +++ b/tools/perf/util/call-path.h @@ -23,7 +23,7 @@ * @children: tree of call paths of functions called * * In combination with the call_return structure, the call_path structure - * defines a context-sensitve call-graph. + * defines a context-sensitive call-graph. */ struct call_path { struct call_path *parent; diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 1b60985690bb..8e2777133bd9 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -877,7 +877,7 @@ append_chain_children(struct callchain_node *root, if (!node) return -1; - /* lookup in childrens */ + /* lookup in children */ while (*p) { enum match_result ret; diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 6984c77068a3..63d472b336de 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -18,6 +18,7 @@ #include "util/hist.h" /* perf_hist_config */ #include "util/llvm-utils.h" /* perf_llvm_config */ #include "util/stat.h" /* perf_stat__set_big_num */ +#include "util/evsel.h" /* evsel__hw_names, evsel__use_bpf_counters */ #include "build-id.h" #include "debug.h" #include "config.h" @@ -457,6 +458,12 @@ static int perf_stat_config(const char *var, const char *value) if (!strcmp(var, "stat.big-num")) perf_stat__set_big_num(perf_config_bool(var, value)); + if (!strcmp(var, "stat.no-csv-summary")) + perf_stat__set_no_csv_summary(perf_config_bool(var, value)); + + if (!strcmp(var, "stat.bpf-counter-events")) + evsel__bpf_counter_events = strdup(value); + /* Add other config variables here. */ return 0; } @@ -699,7 +706,7 @@ static int collect_config(const char *var, const char *value, /* perf_config_set can contain both user and system config items. * So we should know where each value is from. * The classification would be needed when a particular config file - * is overwrited by setting feature i.e. set_config(). + * is overwritten by setting feature i.e. set_config(). */ if (strcmp(config_file_name, perf_etc_perfconfig()) == 0) { section->from_system_config = true; diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 3f4bc4050477..059bcec3f651 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -6,6 +6,7 @@ * Author: Mathieu Poirier <mathieu.poirier@linaro.org> */ +#include <linux/coresight-pmu.h> #include <linux/err.h> #include <linux/list.h> #include <linux/zalloc.h> @@ -316,7 +317,7 @@ cs_etm_decoder__do_hard_timestamp(struct cs_etm_queue *etmq, * This is the first timestamp we've seen since the beginning of traces * or a discontinuity. Since timestamps packets are generated *after* * range packets have been generated, we need to estimate the time at - * which instructions started by substracting the number of instructions + * which instructions started by subtracting the number of instructions * executed to the timestamp. */ packet_queue->timestamp = elem->timestamp - packet_queue->instr_count; @@ -491,13 +492,42 @@ cs_etm_decoder__set_tid(struct cs_etm_queue *etmq, const ocsd_generic_trace_elem *elem, const uint8_t trace_chan_id) { - pid_t tid; + pid_t tid = -1; + static u64 pid_fmt; + int ret; - /* Ignore PE_CONTEXT packets that don't have a valid contextID */ - if (!elem->context.ctxt_id_valid) + /* + * As all the ETMs run at the same exception level, the system should + * have the same PID format crossing CPUs. So cache the PID format + * and reuse it for sequential decoding. + */ + if (!pid_fmt) { + ret = cs_etm__get_pid_fmt(trace_chan_id, &pid_fmt); + if (ret) + return OCSD_RESP_FATAL_SYS_ERR; + } + + /* + * Process the PE_CONTEXT packets if we have a valid contextID or VMID. + * If the kernel is running at EL2, the PID is traced in CONTEXTIDR_EL2 + * as VMID, Bit ETM_OPT_CTXTID2 is set in this case. + */ + switch (pid_fmt) { + case BIT(ETM_OPT_CTXTID): + if (elem->context.ctxt_id_valid) + tid = elem->context.context_id; + break; + case BIT(ETM_OPT_CTXTID2): + if (elem->context.vmid_valid) + tid = elem->context.vmid; + break; + default: + break; + } + + if (tid == -1) return OCSD_RESP_CONT; - tid = elem->context.context_id; if (cs_etm__etmq_set_tid(etmq, tid, trace_chan_id)) return OCSD_RESP_FATAL_SYS_ERR; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index a2a369e2fbb6..7e63e7dedc33 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -7,6 +7,7 @@ */ #include <linux/bitops.h> +#include <linux/coresight-pmu.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/log2.h> @@ -156,11 +157,52 @@ int cs_etm__get_cpu(u8 trace_chan_id, int *cpu) return 0; } +/* + * The returned PID format is presented by two bits: + * + * Bit ETM_OPT_CTXTID: CONTEXTIDR or CONTEXTIDR_EL1 is traced; + * Bit ETM_OPT_CTXTID2: CONTEXTIDR_EL2 is traced. + * + * It's possible that the two bits ETM_OPT_CTXTID and ETM_OPT_CTXTID2 + * are enabled at the same time when the session runs on an EL2 kernel. + * This means the CONTEXTIDR_EL1 and CONTEXTIDR_EL2 both will be + * recorded in the trace data, the tool will selectively use + * CONTEXTIDR_EL2 as PID. + */ +int cs_etm__get_pid_fmt(u8 trace_chan_id, u64 *pid_fmt) +{ + struct int_node *inode; + u64 *metadata, val; + + inode = intlist__find(traceid_list, trace_chan_id); + if (!inode) + return -EINVAL; + + metadata = inode->priv; + + if (metadata[CS_ETM_MAGIC] == __perf_cs_etmv3_magic) { + val = metadata[CS_ETM_ETMCR]; + /* CONTEXTIDR is traced */ + if (val & BIT(ETM_OPT_CTXTID)) + *pid_fmt = BIT(ETM_OPT_CTXTID); + } else { + val = metadata[CS_ETMV4_TRCCONFIGR]; + /* CONTEXTIDR_EL2 is traced */ + if (val & (BIT(ETM4_CFG_BIT_VMID) | BIT(ETM4_CFG_BIT_VMID_OPT))) + *pid_fmt = BIT(ETM_OPT_CTXTID2); + /* CONTEXTIDR_EL1 is traced */ + else if (val & BIT(ETM4_CFG_BIT_CTXTID)) + *pid_fmt = BIT(ETM_OPT_CTXTID); + } + + return 0; +} + void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq, u8 trace_chan_id) { /* - * Wnen a timestamp packet is encountered the backend code + * When a timestamp packet is encountered the backend code * is stopped so that the front end has time to process packets * that were accumulated in the traceID queue. Since there can * be more than one channel per cs_etm_queue, we need to specify @@ -1655,7 +1697,7 @@ static bool cs_etm__is_svc_instr(struct cs_etm_queue *etmq, u8 trace_chan_id, * | 1 1 0 1 1 1 1 1 | imm8 | * +-----------------+--------+ * - * According to the specifiction, it only defines SVC for T32 + * According to the specification, it only defines SVC for T32 * with 16 bits instruction and has no definition for 32bits; * so below only read 2 bytes as instruction size for T32. */ @@ -1887,7 +1929,7 @@ static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq, /* * If the previous packet is an exception return packet - * and the return address just follows SVC instuction, + * and the return address just follows SVC instruction, * it needs to calibrate the previous packet sample flags * as PERF_IP_FLAG_SYSCALLRET. */ @@ -1961,7 +2003,7 @@ static int cs_etm__set_sample_flags(struct cs_etm_queue *etmq, * contain exception type related info so we cannot decide * the exception type purely based on exception return packet. * If we record the exception number from exception packet and - * reuse it for excpetion return packet, this is not reliable + * reuse it for exception return packet, this is not reliable * due the trace can be discontinuity or the interrupt can * be nested, thus the recorded exception number cannot be * used for exception return packet for these two cases. @@ -2435,7 +2477,7 @@ static bool cs_etm__is_timeless_decoding(struct cs_etm_auxtrace *etm) } static const char * const cs_etm_global_header_fmts[] = { - [CS_HEADER_VERSION_0] = " Header version %llx\n", + [CS_HEADER_VERSION] = " Header version %llx\n", [CS_PMU_TYPE_CPUS] = " PMU type/num cpus %llx\n", [CS_ETM_SNAPSHOT] = " Snapshot %llx\n", }; @@ -2443,6 +2485,7 @@ static const char * const cs_etm_global_header_fmts[] = { static const char * const cs_etm_priv_fmts[] = { [CS_ETM_MAGIC] = " Magic number %llx\n", [CS_ETM_CPU] = " CPU %lld\n", + [CS_ETM_NR_TRC_PARAMS] = " NR_TRC_PARAMS %llx\n", [CS_ETM_ETMCR] = " ETMCR %llx\n", [CS_ETM_ETMTRACEIDR] = " ETMTRACEIDR %llx\n", [CS_ETM_ETMCCER] = " ETMCCER %llx\n", @@ -2452,6 +2495,7 @@ static const char * const cs_etm_priv_fmts[] = { static const char * const cs_etmv4_priv_fmts[] = { [CS_ETM_MAGIC] = " Magic number %llx\n", [CS_ETM_CPU] = " CPU %lld\n", + [CS_ETM_NR_TRC_PARAMS] = " NR_TRC_PARAMS %llx\n", [CS_ETMV4_TRCCONFIGR] = " TRCCONFIGR %llx\n", [CS_ETMV4_TRCTRACEIDR] = " TRCTRACEIDR %llx\n", [CS_ETMV4_TRCIDR0] = " TRCIDR0 %llx\n", @@ -2461,26 +2505,167 @@ static const char * const cs_etmv4_priv_fmts[] = { [CS_ETMV4_TRCAUTHSTATUS] = " TRCAUTHSTATUS %llx\n", }; -static void cs_etm__print_auxtrace_info(__u64 *val, int num) +static const char * const param_unk_fmt = + " Unknown parameter [%d] %llx\n"; +static const char * const magic_unk_fmt = + " Magic number Unknown %llx\n"; + +static int cs_etm__print_cpu_metadata_v0(__u64 *val, int *offset) { - int i, j, cpu = 0; + int i = *offset, j, nr_params = 0, fmt_offset; + __u64 magic; - for (i = 0; i < CS_HEADER_VERSION_0_MAX; i++) - fprintf(stdout, cs_etm_global_header_fmts[i], val[i]); + /* check magic value */ + magic = val[i + CS_ETM_MAGIC]; + if ((magic != __perf_cs_etmv3_magic) && + (magic != __perf_cs_etmv4_magic)) { + /* failure - note bad magic value */ + fprintf(stdout, magic_unk_fmt, magic); + return -EINVAL; + } + + /* print common header block */ + fprintf(stdout, cs_etm_priv_fmts[CS_ETM_MAGIC], val[i++]); + fprintf(stdout, cs_etm_priv_fmts[CS_ETM_CPU], val[i++]); + + if (magic == __perf_cs_etmv3_magic) { + nr_params = CS_ETM_NR_TRC_PARAMS_V0; + fmt_offset = CS_ETM_ETMCR; + /* after common block, offset format index past NR_PARAMS */ + for (j = fmt_offset; j < nr_params + fmt_offset; j++, i++) + fprintf(stdout, cs_etm_priv_fmts[j], val[i]); + } else if (magic == __perf_cs_etmv4_magic) { + nr_params = CS_ETMV4_NR_TRC_PARAMS_V0; + fmt_offset = CS_ETMV4_TRCCONFIGR; + /* after common block, offset format index past NR_PARAMS */ + for (j = fmt_offset; j < nr_params + fmt_offset; j++, i++) + fprintf(stdout, cs_etmv4_priv_fmts[j], val[i]); + } + *offset = i; + return 0; +} + +static int cs_etm__print_cpu_metadata_v1(__u64 *val, int *offset) +{ + int i = *offset, j, total_params = 0; + __u64 magic; + + magic = val[i + CS_ETM_MAGIC]; + /* total params to print is NR_PARAMS + common block size for v1 */ + total_params = val[i + CS_ETM_NR_TRC_PARAMS] + CS_ETM_COMMON_BLK_MAX_V1; - for (i = CS_HEADER_VERSION_0_MAX; cpu < num; cpu++) { - if (val[i] == __perf_cs_etmv3_magic) - for (j = 0; j < CS_ETM_PRIV_MAX; j++, i++) + if (magic == __perf_cs_etmv3_magic) { + for (j = 0; j < total_params; j++, i++) { + /* if newer record - could be excess params */ + if (j >= CS_ETM_PRIV_MAX) + fprintf(stdout, param_unk_fmt, j, val[i]); + else fprintf(stdout, cs_etm_priv_fmts[j], val[i]); - else if (val[i] == __perf_cs_etmv4_magic) - for (j = 0; j < CS_ETMV4_PRIV_MAX; j++, i++) + } + } else if (magic == __perf_cs_etmv4_magic) { + for (j = 0; j < total_params; j++, i++) { + /* if newer record - could be excess params */ + if (j >= CS_ETMV4_PRIV_MAX) + fprintf(stdout, param_unk_fmt, j, val[i]); + else fprintf(stdout, cs_etmv4_priv_fmts[j], val[i]); - else - /* failure.. return */ + } + } else { + /* failure - note bad magic value and error out */ + fprintf(stdout, magic_unk_fmt, magic); + return -EINVAL; + } + *offset = i; + return 0; +} + +static void cs_etm__print_auxtrace_info(__u64 *val, int num) +{ + int i, cpu = 0, version, err; + + /* bail out early on bad header version */ + version = val[0]; + if (version > CS_HEADER_CURRENT_VERSION) { + /* failure.. return */ + fprintf(stdout, " Unknown Header Version = %x, ", version); + fprintf(stdout, "Version supported <= %x\n", CS_HEADER_CURRENT_VERSION); + return; + } + + for (i = 0; i < CS_HEADER_VERSION_MAX; i++) + fprintf(stdout, cs_etm_global_header_fmts[i], val[i]); + + for (i = CS_HEADER_VERSION_MAX; cpu < num; cpu++) { + if (version == 0) + err = cs_etm__print_cpu_metadata_v0(val, &i); + else if (version == 1) + err = cs_etm__print_cpu_metadata_v1(val, &i); + if (err) return; } } +/* + * Read a single cpu parameter block from the auxtrace_info priv block. + * + * For version 1 there is a per cpu nr_params entry. If we are handling + * version 1 file, then there may be less, the same, or more params + * indicated by this value than the compile time number we understand. + * + * For a version 0 info block, there are a fixed number, and we need to + * fill out the nr_param value in the metadata we create. + */ +static u64 *cs_etm__create_meta_blk(u64 *buff_in, int *buff_in_offset, + int out_blk_size, int nr_params_v0) +{ + u64 *metadata = NULL; + int hdr_version; + int nr_in_params, nr_out_params, nr_cmn_params; + int i, k; + + metadata = zalloc(sizeof(*metadata) * out_blk_size); + if (!metadata) + return NULL; + + /* read block current index & version */ + i = *buff_in_offset; + hdr_version = buff_in[CS_HEADER_VERSION]; + + if (!hdr_version) { + /* read version 0 info block into a version 1 metadata block */ + nr_in_params = nr_params_v0; + metadata[CS_ETM_MAGIC] = buff_in[i + CS_ETM_MAGIC]; + metadata[CS_ETM_CPU] = buff_in[i + CS_ETM_CPU]; + metadata[CS_ETM_NR_TRC_PARAMS] = nr_in_params; + /* remaining block params at offset +1 from source */ + for (k = CS_ETM_COMMON_BLK_MAX_V1 - 1; k < nr_in_params; k++) + metadata[k + 1] = buff_in[i + k]; + /* version 0 has 2 common params */ + nr_cmn_params = 2; + } else { + /* read version 1 info block - input and output nr_params may differ */ + /* version 1 has 3 common params */ + nr_cmn_params = 3; + nr_in_params = buff_in[i + CS_ETM_NR_TRC_PARAMS]; + + /* if input has more params than output - skip excess */ + nr_out_params = nr_in_params + nr_cmn_params; + if (nr_out_params > out_blk_size) + nr_out_params = out_blk_size; + + for (k = CS_ETM_MAGIC; k < nr_out_params; k++) + metadata[k] = buff_in[i + k]; + + /* record the actual nr params we copied */ + metadata[CS_ETM_NR_TRC_PARAMS] = nr_out_params - nr_cmn_params; + } + + /* adjust in offset by number of in params used */ + i += nr_in_params + nr_cmn_params; + *buff_in_offset = i; + return metadata; +} + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session) { @@ -2492,11 +2677,12 @@ int cs_etm__process_auxtrace_info(union perf_event *event, int info_header_size; int total_size = auxtrace_info->header.size; int priv_size = 0; - int num_cpu; - int err = 0, idx = -1; - int i, j, k; + int num_cpu, trcidr_idx; + int err = 0; + int i, j; u64 *ptr, *hdr = NULL; u64 **metadata = NULL; + u64 hdr_version; /* * sizeof(auxtrace_info_event::type) + @@ -2512,16 +2698,21 @@ int cs_etm__process_auxtrace_info(union perf_event *event, /* First the global part */ ptr = (u64 *) auxtrace_info->priv; - /* Look for version '0' of the header */ - if (ptr[0] != 0) + /* Look for version of the header */ + hdr_version = ptr[0]; + if (hdr_version > CS_HEADER_CURRENT_VERSION) { + /* print routine will print an error on bad version */ + if (dump_trace) + cs_etm__print_auxtrace_info(auxtrace_info->priv, 0); return -EINVAL; + } - hdr = zalloc(sizeof(*hdr) * CS_HEADER_VERSION_0_MAX); + hdr = zalloc(sizeof(*hdr) * CS_HEADER_VERSION_MAX); if (!hdr) return -ENOMEM; /* Extract header information - see cs-etm.h for format */ - for (i = 0; i < CS_HEADER_VERSION_0_MAX; i++) + for (i = 0; i < CS_HEADER_VERSION_MAX; i++) hdr[i] = ptr[i]; num_cpu = hdr[CS_PMU_TYPE_CPUS] & 0xffffffff; pmu_type = (unsigned int) ((hdr[CS_PMU_TYPE_CPUS] >> 32) & @@ -2552,35 +2743,31 @@ int cs_etm__process_auxtrace_info(union perf_event *event, */ for (j = 0; j < num_cpu; j++) { if (ptr[i] == __perf_cs_etmv3_magic) { - metadata[j] = zalloc(sizeof(*metadata[j]) * - CS_ETM_PRIV_MAX); - if (!metadata[j]) { - err = -ENOMEM; - goto err_free_metadata; - } - for (k = 0; k < CS_ETM_PRIV_MAX; k++) - metadata[j][k] = ptr[i + k]; + metadata[j] = + cs_etm__create_meta_blk(ptr, &i, + CS_ETM_PRIV_MAX, + CS_ETM_NR_TRC_PARAMS_V0); /* The traceID is our handle */ - idx = metadata[j][CS_ETM_ETMTRACEIDR]; - i += CS_ETM_PRIV_MAX; + trcidr_idx = CS_ETM_ETMTRACEIDR; + } else if (ptr[i] == __perf_cs_etmv4_magic) { - metadata[j] = zalloc(sizeof(*metadata[j]) * - CS_ETMV4_PRIV_MAX); - if (!metadata[j]) { - err = -ENOMEM; - goto err_free_metadata; - } - for (k = 0; k < CS_ETMV4_PRIV_MAX; k++) - metadata[j][k] = ptr[i + k]; + metadata[j] = + cs_etm__create_meta_blk(ptr, &i, + CS_ETMV4_PRIV_MAX, + CS_ETMV4_NR_TRC_PARAMS_V0); /* The traceID is our handle */ - idx = metadata[j][CS_ETMV4_TRCTRACEIDR]; - i += CS_ETMV4_PRIV_MAX; + trcidr_idx = CS_ETMV4_TRCTRACEIDR; + } + + if (!metadata[j]) { + err = -ENOMEM; + goto err_free_metadata; } /* Get an RB node for this CPU */ - inode = intlist__findnew(traceid_list, idx); + inode = intlist__findnew(traceid_list, metadata[j][trcidr_idx]); /* Something went wrong, no need to continue */ if (!inode) { @@ -2601,7 +2788,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event, } /* - * Each of CS_HEADER_VERSION_0_MAX, CS_ETM_PRIV_MAX and + * Each of CS_HEADER_VERSION_MAX, CS_ETM_PRIV_MAX and * CS_ETMV4_PRIV_MAX mark how many double words are in the * global metadata, and each cpu's metadata respectively. * The following tests if the correct number of double words was @@ -2703,6 +2890,12 @@ err_free_traceid_list: intlist__delete(traceid_list); err_free_hdr: zfree(&hdr); - + /* + * At this point, as a minimum we have valid header. Dump the rest of + * the info section - the print routines will error out on structural + * issues. + */ + if (dump_trace) + cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu); return err; } diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 4ad925d6d799..36428918411e 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -12,28 +12,43 @@ struct perf_session; -/* Versionning header in case things need tro change in the future. That way +/* + * Versioning header in case things need to change in the future. That way * decoding of old snapshot is still possible. */ enum { /* Starting with 0x0 */ - CS_HEADER_VERSION_0, + CS_HEADER_VERSION, /* PMU->type (32 bit), total # of CPUs (32 bit) */ CS_PMU_TYPE_CPUS, CS_ETM_SNAPSHOT, - CS_HEADER_VERSION_0_MAX, + CS_HEADER_VERSION_MAX, }; +/* + * Update the version for new format. + * + * New version 1 format adds a param count to the per cpu metadata. + * This allows easy adding of new metadata parameters. + * Requires that new params always added after current ones. + * Also allows client reader to handle file versions that are different by + * checking the number of params in the file vs the number expected. + */ +#define CS_HEADER_CURRENT_VERSION 1 + /* Beginning of header common to both ETMv3 and V4 */ enum { CS_ETM_MAGIC, CS_ETM_CPU, + /* Number of trace config params in following ETM specific block */ + CS_ETM_NR_TRC_PARAMS, + CS_ETM_COMMON_BLK_MAX_V1, }; /* ETMv3/PTM metadata */ enum { /* Dynamic, configurable parameters */ - CS_ETM_ETMCR = CS_ETM_CPU + 1, + CS_ETM_ETMCR = CS_ETM_COMMON_BLK_MAX_V1, CS_ETM_ETMTRACEIDR, /* RO, taken from sysFS */ CS_ETM_ETMCCER, @@ -41,10 +56,13 @@ enum { CS_ETM_PRIV_MAX, }; +/* define fixed version 0 length - allow new format reader to read old files. */ +#define CS_ETM_NR_TRC_PARAMS_V0 (CS_ETM_ETMIDR - CS_ETM_ETMCR + 1) + /* ETMv4 metadata */ enum { /* Dynamic, configurable parameters */ - CS_ETMV4_TRCCONFIGR = CS_ETM_CPU + 1, + CS_ETMV4_TRCCONFIGR = CS_ETM_COMMON_BLK_MAX_V1, CS_ETMV4_TRCTRACEIDR, /* RO, taken from sysFS */ CS_ETMV4_TRCIDR0, @@ -55,9 +73,12 @@ enum { CS_ETMV4_PRIV_MAX, }; +/* define fixed version 0 length - allow new format reader to read old files. */ +#define CS_ETMV4_NR_TRC_PARAMS_V0 (CS_ETMV4_TRCAUTHSTATUS - CS_ETMV4_TRCCONFIGR + 1) + /* * ETMv3 exception encoding number: - * See Embedded Trace Macrocell spcification (ARM IHI 0014Q) + * See Embedded Trace Macrocell specification (ARM IHI 0014Q) * table 7-12 Encoding of Exception[3:0] for non-ARMv7-M processors. */ enum { @@ -162,7 +183,7 @@ struct cs_etm_packet_queue { #define BMVAL(val, lsb, msb) ((val & GENMASK(msb, lsb)) >> lsb) -#define CS_ETM_HEADER_SIZE (CS_HEADER_VERSION_0_MAX * sizeof(u64)) +#define CS_ETM_HEADER_SIZE (CS_HEADER_VERSION_MAX * sizeof(u64)) #define __perf_cs_etmv3_magic 0x3030303030303030ULL #define __perf_cs_etmv4_magic 0x4040404040404040ULL @@ -173,6 +194,7 @@ struct cs_etm_packet_queue { int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session); int cs_etm__get_cpu(u8 trace_chan_id, int *cpu); +int cs_etm__get_pid_fmt(u8 trace_chan_id, u64 *pid_fmt); int cs_etm__etmq_set_tid(struct cs_etm_queue *etmq, pid_t tid, u8 trace_chan_id); bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq); diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 8b67bd97d122..cace349fb700 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -21,7 +21,7 @@ #include <babeltrace/ctf/events.h> #include <traceevent/event-parse.h> #include "asm/bug.h" -#include "data-convert-bt.h" +#include "data-convert.h" #include "session.h" #include "debug.h" #include "tool.h" @@ -949,7 +949,7 @@ static char *change_name(char *name, char *orig_name, int dup) /* * Add '_' prefix to potential keywork. According to * Mathieu Desnoyers (https://lore.kernel.org/lkml/1074266107.40857.1422045946295.JavaMail.zimbra@efficios.com), - * futher CTF spec updating may require us to use '$'. + * further CTF spec updating may require us to use '$'. */ if (dup < 0) len = strlen(name) + sizeof("_"); diff --git a/tools/perf/util/data-convert-bt.h b/tools/perf/util/data-convert-bt.h deleted file mode 100644 index 821674d63c4e..000000000000 --- a/tools/perf/util/data-convert-bt.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#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, - struct perf_data_convert_opts *opts); - -#endif /* HAVE_LIBBABELTRACE_SUPPORT */ -#endif /* __DATA_CONVERT_BT_H */ diff --git a/tools/perf/util/data-convert-json.c b/tools/perf/util/data-convert-json.c new file mode 100644 index 000000000000..355cd1948bdf --- /dev/null +++ b/tools/perf/util/data-convert-json.c @@ -0,0 +1,384 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * JSON export. + * + * Copyright (C) 2021, CodeWeavers Inc. <nfraser@codeweavers.com> + */ + +#include "data-convert.h" + +#include <fcntl.h> +#include <inttypes.h> +#include <sys/stat.h> +#include <unistd.h> + +#include "linux/compiler.h" +#include "linux/err.h" +#include "util/auxtrace.h" +#include "util/debug.h" +#include "util/dso.h" +#include "util/event.h" +#include "util/evsel.h" +#include "util/evlist.h" +#include "util/header.h" +#include "util/map.h" +#include "util/session.h" +#include "util/symbol.h" +#include "util/thread.h" +#include "util/tool.h" + +struct convert_json { + struct perf_tool tool; + FILE *out; + bool first; + u64 events_count; +}; + +// Outputs a JSON-encoded string surrounded by quotes with characters escaped. +static void output_json_string(FILE *out, const char *s) +{ + fputc('"', out); + while (*s) { + switch (*s) { + + // required escapes with special forms as per RFC 8259 + case '"': fputs("\\\"", out); break; + case '\\': fputs("\\\\", out); break; + case '\b': fputs("\\b", out); break; + case '\f': fputs("\\f", out); break; + case '\n': fputs("\\n", out); break; + case '\r': fputs("\\r", out); break; + case '\t': fputs("\\t", out); break; + + default: + // all other control characters must be escaped by hex code + if (*s <= 0x1f) + fprintf(out, "\\u%04x", *s); + else + fputc(*s, out); + break; + } + + ++s; + } + fputc('"', out); +} + +// Outputs an optional comma, newline and indentation to delimit a new value +// from the previous one in a JSON object or array. +static void output_json_delimiters(FILE *out, bool comma, int depth) +{ + int i; + + if (comma) + fputc(',', out); + fputc('\n', out); + for (i = 0; i < depth; ++i) + fputc('\t', out); +} + +// Outputs a printf format string (with delimiter) as a JSON value. +__printf(4, 5) +static void output_json_format(FILE *out, bool comma, int depth, const char *format, ...) +{ + va_list args; + + output_json_delimiters(out, comma, depth); + va_start(args, format); + vfprintf(out, format, args); + va_end(args); +} + +// Outputs a JSON key-value pair where the value is a string. +static void output_json_key_string(FILE *out, bool comma, int depth, + const char *key, const char *value) +{ + output_json_delimiters(out, comma, depth); + output_json_string(out, key); + fputs(": ", out); + output_json_string(out, value); +} + +// Outputs a JSON key-value pair where the value is a printf format string. +__printf(5, 6) +static void output_json_key_format(FILE *out, bool comma, int depth, + const char *key, const char *format, ...) +{ + va_list args; + + output_json_delimiters(out, comma, depth); + output_json_string(out, key); + fputs(": ", out); + va_start(args, format); + vfprintf(out, format, args); + va_end(args); +} + +static void output_sample_callchain_entry(struct perf_tool *tool, + u64 ip, struct addr_location *al) +{ + struct convert_json *c = container_of(tool, struct convert_json, tool); + FILE *out = c->out; + + output_json_format(out, false, 4, "{"); + output_json_key_format(out, false, 5, "ip", "\"0x%" PRIx64 "\"", ip); + + if (al && al->sym && al->sym->namelen) { + fputc(',', out); + output_json_key_string(out, false, 5, "symbol", al->sym->name); + + if (al->map && al->map->dso) { + const char *dso = al->map->dso->short_name; + + if (dso && strlen(dso) > 0) { + fputc(',', out); + output_json_key_string(out, false, 5, "dso", dso); + } + } + } + + output_json_format(out, false, 4, "}"); +} + +static int process_sample_event(struct perf_tool *tool, + union perf_event *event __maybe_unused, + struct perf_sample *sample, + struct evsel *evsel __maybe_unused, + struct machine *machine) +{ + struct convert_json *c = container_of(tool, struct convert_json, tool); + FILE *out = c->out; + struct addr_location al, tal; + u8 cpumode = PERF_RECORD_MISC_USER; + + if (machine__resolve(machine, &al, sample) < 0) { + pr_err("Sample resolution failed!\n"); + return -1; + } + + ++c->events_count; + + if (c->first) + c->first = false; + else + fputc(',', out); + output_json_format(out, false, 2, "{"); + + output_json_key_format(out, false, 3, "timestamp", "%" PRIi64, sample->time); + output_json_key_format(out, true, 3, "pid", "%i", al.thread->pid_); + output_json_key_format(out, true, 3, "tid", "%i", al.thread->tid); + + if (al.thread->cpu >= 0) + output_json_key_format(out, true, 3, "cpu", "%i", al.thread->cpu); + + output_json_key_string(out, true, 3, "comm", thread__comm_str(al.thread)); + + output_json_key_format(out, true, 3, "callchain", "["); + if (sample->callchain) { + unsigned int i; + bool ok; + bool first_callchain = true; + + for (i = 0; i < sample->callchain->nr; ++i) { + u64 ip = sample->callchain->ips[i]; + + if (ip >= PERF_CONTEXT_MAX) { + switch (ip) { + case PERF_CONTEXT_HV: + cpumode = PERF_RECORD_MISC_HYPERVISOR; + break; + case PERF_CONTEXT_KERNEL: + cpumode = PERF_RECORD_MISC_KERNEL; + break; + case PERF_CONTEXT_USER: + cpumode = PERF_RECORD_MISC_USER; + break; + default: + pr_debug("invalid callchain context: %" + PRId64 "\n", (s64) ip); + break; + } + continue; + } + + if (first_callchain) + first_callchain = false; + else + fputc(',', out); + + ok = thread__find_symbol(al.thread, cpumode, ip, &tal); + output_sample_callchain_entry(tool, ip, ok ? &tal : NULL); + } + } else { + output_sample_callchain_entry(tool, sample->ip, &al); + } + output_json_format(out, false, 3, "]"); + + output_json_format(out, false, 2, "}"); + return 0; +} + +static void output_headers(struct perf_session *session, struct convert_json *c) +{ + struct stat st; + struct perf_header *header = &session->header; + int ret; + int fd = perf_data__fd(session->data); + int i; + FILE *out = c->out; + + output_json_key_format(out, false, 2, "header-version", "%u", header->version); + + ret = fstat(fd, &st); + if (ret >= 0) { + time_t stctime = st.st_mtime; + char buf[256]; + + strftime(buf, sizeof(buf), "%FT%TZ", gmtime(&stctime)); + output_json_key_string(out, true, 2, "captured-on", buf); + } else { + pr_debug("Failed to get mtime of source file, not writing captured-on"); + } + + output_json_key_format(out, true, 2, "data-offset", "%" PRIu64, header->data_offset); + output_json_key_format(out, true, 2, "data-size", "%" PRIu64, header->data_size); + output_json_key_format(out, true, 2, "feat-offset", "%" PRIu64, header->feat_offset); + + output_json_key_string(out, true, 2, "hostname", header->env.hostname); + output_json_key_string(out, true, 2, "os-release", header->env.os_release); + output_json_key_string(out, true, 2, "arch", header->env.arch); + + output_json_key_string(out, true, 2, "cpu-desc", header->env.cpu_desc); + output_json_key_string(out, true, 2, "cpuid", header->env.cpuid); + output_json_key_format(out, true, 2, "nrcpus-online", "%u", header->env.nr_cpus_online); + output_json_key_format(out, true, 2, "nrcpus-avail", "%u", header->env.nr_cpus_avail); + + if (header->env.clock.enabled) { + output_json_key_format(out, true, 2, "clockid", + "%u", header->env.clock.clockid); + output_json_key_format(out, true, 2, "clock-time", + "%" PRIu64, header->env.clock.clockid_ns); + output_json_key_format(out, true, 2, "real-time", + "%" PRIu64, header->env.clock.tod_ns); + } + + output_json_key_string(out, true, 2, "perf-version", header->env.version); + + output_json_key_format(out, true, 2, "cmdline", "["); + for (i = 0; i < header->env.nr_cmdline; i++) { + output_json_delimiters(out, i != 0, 3); + output_json_string(c->out, header->env.cmdline_argv[i]); + } + output_json_format(out, false, 2, "]"); +} + +int bt_convert__perf2json(const char *input_name, const char *output_name, + struct perf_data_convert_opts *opts __maybe_unused) +{ + struct perf_session *session; + int fd; + int ret = -1; + + struct convert_json c = { + .tool = { + .sample = process_sample_event, + .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, + .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, + .cgroup = perf_event__process_cgroup, + .exit = perf_event__process_exit, + .fork = perf_event__process_fork, + .lost = perf_event__process_lost, + .tracing_data = perf_event__process_tracing_data, + .build_id = perf_event__process_build_id, + .id_index = perf_event__process_id_index, + .auxtrace_info = perf_event__process_auxtrace_info, + .auxtrace = perf_event__process_auxtrace, + .event_update = perf_event__process_event_update, + .ordered_events = true, + .ordering_requires_timestamps = true, + }, + .first = true, + .events_count = 0, + }; + + struct perf_data data = { + .mode = PERF_DATA_MODE_READ, + .path = input_name, + .force = opts->force, + }; + + if (opts->all) { + pr_err("--all is currently unsupported for JSON output.\n"); + goto err; + } + if (opts->tod) { + pr_err("--tod is currently unsupported for JSON output.\n"); + goto err; + } + + fd = open(output_name, O_CREAT | O_WRONLY | (opts->force ? O_TRUNC : O_EXCL), 0666); + if (fd == -1) { + if (errno == EEXIST) + pr_err("Output file exists. Use --force to overwrite it.\n"); + else + pr_err("Error opening output file!\n"); + goto err; + } + + c.out = fdopen(fd, "w"); + if (!c.out) { + fprintf(stderr, "Error opening output file!\n"); + close(fd); + goto err; + } + + session = perf_session__new(&data, false, &c.tool); + if (IS_ERR(session)) { + fprintf(stderr, "Error creating perf session!\n"); + goto err_fclose; + } + + if (symbol__init(&session->header.env) < 0) { + fprintf(stderr, "Symbol init error!\n"); + goto err_session_delete; + } + + // The opening brace is printed manually because it isn't delimited from a + // previous value (i.e. we don't want a leading newline) + fputc('{', c.out); + + // Version number for future-proofing. Most additions should be able to be + // done in a backwards-compatible way so this should only need to be bumped + // if some major breaking change must be made. + output_json_format(c.out, false, 1, "\"linux-perf-json-version\": 1"); + + // Output headers + output_json_format(c.out, true, 1, "\"headers\": {"); + output_headers(session, &c); + output_json_format(c.out, false, 1, "}"); + + // Output samples + output_json_format(c.out, true, 1, "\"samples\": ["); + perf_session__process_events(session); + output_json_format(c.out, false, 1, "]"); + output_json_format(c.out, false, 0, "}"); + fputc('\n', c.out); + + fprintf(stderr, + "[ perf data convert: Converted '%s' into JSON data '%s' ]\n", + data.path, output_name); + + fprintf(stderr, + "[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples) ]\n", + (ftell(c.out)) / 1024.0 / 1024.0, c.events_count); + + ret = 0; +err_session_delete: + perf_session__delete(session); +err_fclose: + fclose(c.out); +err: + return ret; +} diff --git a/tools/perf/util/data-convert.h b/tools/perf/util/data-convert.h index feab5f114e37..1b4c5f598415 100644 --- a/tools/perf/util/data-convert.h +++ b/tools/perf/util/data-convert.h @@ -2,10 +2,20 @@ #ifndef __DATA_CONVERT_H #define __DATA_CONVERT_H +#include <stdbool.h> + struct perf_data_convert_opts { bool force; bool all; bool tod; }; +#ifdef HAVE_LIBBABELTRACE_SUPPORT +int bt_convert__perf2ctf(const char *input_name, const char *to_ctf, + struct perf_data_convert_opts *opts); +#endif /* HAVE_LIBBABELTRACE_SUPPORT */ + +int bt_convert__perf2json(const char *input_name, const char *to_ctf, + struct perf_data_convert_opts *opts); + #endif /* __DATA_CONVERT_H */ diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c index 39c05200ed65..ddf33d58bcd3 100644 --- a/tools/perf/util/demangle-java.c +++ b/tools/perf/util/demangle-java.c @@ -147,7 +147,7 @@ error: * Demangle Java function signature (openJDK, not GCJ) * input: * str: string to parse. String is not modified - * flags: comobination of JAVA_DEMANGLE_* flags to modify demangling + * flags: combination of JAVA_DEMANGLE_* flags to modify demangling * return: * if input can be demangled, then a newly allocated string is returned. * if input cannot be demangled, then NULL is returned @@ -164,7 +164,7 @@ java_demangle_sym(const char *str, int flags) if (!str) return NULL; - /* find start of retunr type */ + /* find start of return type */ p = strrchr(str, ')'); if (!p) return NULL; diff --git a/tools/perf/util/demangle-ocaml.c b/tools/perf/util/demangle-ocaml.c index 3df14e67c622..9d707bb60b4b 100644 --- a/tools/perf/util/demangle-ocaml.c +++ b/tools/perf/util/demangle-ocaml.c @@ -64,17 +64,5 @@ ocaml_demangle_sym(const char *sym) } result[j] = '\0'; - /* scan backwards to remove an "_" followed by decimal digits */ - if (j != 0 && isdigit(result[j - 1])) { - while (--j) { - if (!isdigit(result[j])) { - break; - } - } - if (result[j] == '_') { - result[j] = '\0'; - } - } - return result; } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index cd2fe64a3c5d..52e7101c5609 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -216,7 +216,7 @@ struct dso { /* dso__for_each_symbol - iterate over the symbols of given type * - * @dso: the 'struct dso *' in which symbols itereated + * @dso: the 'struct dso *' in which symbols are iterated * @pos: the 'struct symbol *' to use as a loop cursor * @n: the 'struct rb_node *' to use as a temporary storage */ diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 7b2d471a6419..b2f4920e19a6 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -91,7 +91,7 @@ static Dwarf_Line *cu_getsrc_die(Dwarf_Die *cu_die, Dwarf_Addr addr) return NULL; } while (laddr == addr); l++; - /* Going foward to find the statement line */ + /* Going forward to find the statement line */ do { line = dwarf_onesrcline(lines, l++); if (!line || dwarf_lineaddr(line, &laddr) != 0 || @@ -177,7 +177,7 @@ int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, * die_get_linkage_name - Get the linkage name of the object * @dw_die: A DIE of the object * - * Get the linkage name attiribute of given @dw_die. + * Get the linkage name attribute of given @dw_die. * For C++ binary, the linkage name will be the mangled symbol. */ const char *die_get_linkage_name(Dwarf_Die *dw_die) @@ -739,7 +739,7 @@ static int __die_walk_instances_cb(Dwarf_Die *inst, void *data) * @data: user data * * Walk on the instances of give @in_die. @in_die must be an inlined function - * declartion. This returns the return value of @callback if it returns + * declaration. This returns the return value of @callback if it returns * non-zero value, or -ENOENT if there is no instance. */ int die_walk_instances(Dwarf_Die *or_die, int (*callback)(Dwarf_Die *, void *), diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index 506006e0cf66..cb99646843a9 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -22,7 +22,7 @@ const char *cu_get_comp_dir(Dwarf_Die *cu_die); int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr, const char **fname, int *lineno); -/* Walk on funcitons at given address */ +/* Walk on functions at given address */ int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, int (*callback)(Dwarf_Die *, void *), void *data); diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c index 1b49ecee5aff..3fa4486742cd 100644 --- a/tools/perf/util/dwarf-regs.c +++ b/tools/perf/util/dwarf-regs.c @@ -24,6 +24,7 @@ #include "../arch/s390/include/dwarf-regs-table.h" #include "../arch/sparc/include/dwarf-regs-table.h" #include "../arch/xtensa/include/dwarf-regs-table.h" +#include "../arch/mips/include/dwarf-regs-table.h" #define __get_dwarf_regstr(tbl, n) (((n) < ARRAY_SIZE(tbl)) ? (tbl)[(n)] : NULL) @@ -53,6 +54,8 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine) return __get_dwarf_regstr(sparc_regstr_tbl, n); case EM_XTENSA: return __get_dwarf_regstr(xtensa_regstr_tbl, n); + case EM_MIPS: + return __get_dwarf_regstr(mips_regstr_tbl, n); default: pr_err("ELF MACHINE %x is not supported.\n", machine); } diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index f603edbbbc6f..8a62fb39e365 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -147,6 +147,7 @@ struct perf_sample { u8 cpumode; u16 misc; u16 ins_lat; + u16 p_stage_cyc; bool no_hw_idx; /* No hw_idx collected in branch_stack */ char insn[MAX_INSN]; void *raw_data; @@ -427,5 +428,7 @@ char *get_page_size_name(u64 size, char *str); void arch_perf_parse_sample_weight(struct perf_sample *data, const __u64 *array, u64 type); void arch_perf_synthesize_sample_weight(const struct perf_sample *data, __u64 *array, u64 type); +const char *arch_perf_header_entry(const char *se_header); +int arch_support_sort_key(const char *sort_key); #endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/events_stats.h b/tools/perf/util/events_stats.h index 859cb34fcff2..3480bafd414b 100644 --- a/tools/perf/util/events_stats.h +++ b/tools/perf/util/events_stats.h @@ -21,20 +21,17 @@ * all struct perf_record_lost_samples.lost fields reported. * * The total_period is needed because by default auto-freq is used, so - * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get + * multiplying nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get * the total number of low level events, it is necessary to to sum all struct * perf_record_sample.period and stash the result in total_period. */ struct events_stats { - u64 total_period; - u64 total_non_filtered_period; u64 total_lost; u64 total_lost_samples; u64 total_aux_lost; u64 total_aux_partial; u64 total_invalid_chains; u32 nr_events[PERF_RECORD_HEADER_MAX]; - u32 nr_non_filtered_samples; u32 nr_lost_warned; u32 nr_unknown_events; u32 nr_invalid_chains; @@ -44,8 +41,16 @@ struct events_stats { u32 nr_proc_map_timeout; }; +struct hists_stats { + u64 total_period; + u64 total_non_filtered_period; + u32 nr_samples; + u32 nr_non_filtered_samples; +}; + void events_stats__inc(struct events_stats *stats, u32 type); -size_t events_stats__fprintf(struct events_stats *stats, FILE *fp); +size_t events_stats__fprintf(struct events_stats *stats, FILE *fp, + bool skip_empty); #endif /* __PERF_EVENTS_STATS_ */ diff --git a/tools/perf/util/evlist-hybrid.c b/tools/perf/util/evlist-hybrid.c new file mode 100644 index 000000000000..db3f5fbdebe1 --- /dev/null +++ b/tools/perf/util/evlist-hybrid.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <errno.h> +#include <inttypes.h> +#include "cpumap.h" +#include "evlist.h" +#include "evsel.h" +#include "../perf.h" +#include "util/pmu-hybrid.h" +#include "util/evlist-hybrid.h" +#include "debug.h" +#include <unistd.h> +#include <stdlib.h> +#include <linux/err.h> +#include <linux/string.h> +#include <perf/evlist.h> +#include <perf/evsel.h> +#include <perf/cpumap.h> + +int evlist__add_default_hybrid(struct evlist *evlist, bool precise) +{ + struct evsel *evsel; + struct perf_pmu *pmu; + __u64 config; + struct perf_cpu_map *cpus; + + perf_pmu__for_each_hybrid_pmu(pmu) { + config = PERF_COUNT_HW_CPU_CYCLES | + ((__u64)pmu->type << PERF_PMU_TYPE_SHIFT); + evsel = evsel__new_cycles(precise, PERF_TYPE_HARDWARE, + config); + if (!evsel) + return -ENOMEM; + + cpus = perf_cpu_map__get(pmu->cpus); + evsel->core.cpus = cpus; + evsel->core.own_cpus = perf_cpu_map__get(cpus); + evsel->pmu_name = strdup(pmu->name); + evlist__add(evlist, evsel); + } + + return 0; +} + +static bool group_hybrid_conflict(struct evsel *leader) +{ + struct evsel *pos, *prev = NULL; + + for_each_group_evsel(pos, leader) { + if (!evsel__is_hybrid(pos)) + continue; + + if (prev && strcmp(prev->pmu_name, pos->pmu_name)) + return true; + + prev = pos; + } + + return false; +} + +void evlist__warn_hybrid_group(struct evlist *evlist) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel__is_group_leader(evsel) && + evsel->core.nr_members > 1 && + group_hybrid_conflict(evsel)) { + pr_warning("WARNING: events in group from " + "different hybrid PMUs!\n"); + return; + } + } +} + +bool evlist__has_hybrid(struct evlist *evlist) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (evsel->pmu_name && + perf_pmu__is_hybrid(evsel->pmu_name)) { + return true; + } + } + + return false; +} diff --git a/tools/perf/util/evlist-hybrid.h b/tools/perf/util/evlist-hybrid.h new file mode 100644 index 000000000000..19f74b4c340a --- /dev/null +++ b/tools/perf/util/evlist-hybrid.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_EVLIST_HYBRID_H +#define __PERF_EVLIST_HYBRID_H + +#include <linux/compiler.h> +#include <linux/kernel.h> +#include "evlist.h" +#include <unistd.h> + +int evlist__add_default_hybrid(struct evlist *evlist, bool precise); +void evlist__warn_hybrid_group(struct evlist *evlist); +bool evlist__has_hybrid(struct evlist *evlist); + +#endif /* __PERF_EVLIST_HYBRID_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 882cd1f721d9..6e5c41528c7d 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -17,6 +17,7 @@ #include "evsel.h" #include "debug.h" #include "units.h" +#include "bpf_counter.h" #include <internal/lib.h> // page_size #include "affinity.h" #include "../perf.h" @@ -25,6 +26,7 @@ #include "util/string2.h" #include "util/perf_api_probe.h" #include "util/evsel_fprintf.h" +#include "util/evlist-hybrid.h" #include <signal.h> #include <unistd.h> #include <sched.h> @@ -36,6 +38,7 @@ #include <fcntl.h> #include <sys/ioctl.h> #include <sys/mman.h> +#include <sys/prctl.h> #include <linux/bitops.h> #include <linux/hash.h> @@ -246,8 +249,10 @@ void evlist__set_leader(struct evlist *evlist) int __evlist__add_default(struct evlist *evlist, bool precise) { - struct evsel *evsel = evsel__new_cycles(precise); + struct evsel *evsel; + evsel = evsel__new_cycles(precise, PERF_TYPE_HARDWARE, + PERF_COUNT_HW_CPU_CYCLES); if (evsel == NULL) return -ENOMEM; @@ -420,6 +425,9 @@ static void __evlist__disable(struct evlist *evlist, char *evsel_name) if (affinity__setup(&affinity) < 0) return; + evlist__for_each_entry(evlist, pos) + bpf_counter__disable(pos); + /* Disable 'immediate' events last */ for (imm = 0; imm <= 1; imm++) { evlist__for_each_cpu(evlist, i, cpu) { @@ -1209,7 +1217,7 @@ bool evlist__valid_read_format(struct evlist *evlist) } } - /* PERF_SAMPLE_READ imples PERF_FORMAT_ID. */ + /* PERF_SAMPLE_READ implies PERF_FORMAT_ID. */ if ((sample_type & PERF_SAMPLE_READ) && !(read_format & PERF_FORMAT_ID)) { return false; @@ -1406,6 +1414,13 @@ int evlist__prepare_workload(struct evlist *evlist, struct target *target, const fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC); /* + * Change the name of this process not to confuse --exclude-perf users + * that sees 'perf' in the window up to the execvp() and thinks that + * perf samples are not being excluded. + */ + prctl(PR_SET_NAME, "perf-exec"); + + /* * Tell the parent we're ready to go */ close(child_ready_pipe[1]); @@ -2130,3 +2145,22 @@ struct evsel *evlist__find_evsel(struct evlist *evlist, int idx) } return NULL; } + +int evlist__scnprintf_evsels(struct evlist *evlist, size_t size, char *bf) +{ + struct evsel *evsel; + int printed = 0; + + evlist__for_each_entry(evlist, evsel) { + if (evsel__is_dummy_event(evsel)) + continue; + if (size > (strlen(evsel__name(evsel)) + (printed ? 2 : 1))) { + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "," : "", evsel__name(evsel)); + } else { + printed += scnprintf(bf + printed, size - printed, "%s...", printed ? "," : ""); + break; + } + } + + return printed; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index b695ffaae519..a8b97b50cceb 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -365,4 +365,6 @@ int evlist__ctlfd_ack(struct evlist *evlist); #define EVLIST_DISABLED_MSG "Events disabled\n" struct evsel *evlist__find_evsel(struct evlist *evlist, int idx); + +int evlist__scnprintf_evsels(struct evlist *evlist, size_t size, char *bf); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 7ecbc8e2fbfa..4a3cd1b5bb33 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -47,6 +47,7 @@ #include "memswap.h" #include "util.h" #include "hashmap.h" +#include "pmu-hybrid.h" #include "../perf-sys.h" #include "util/parse-branch-options.h" #include <internal/xyarray.h> @@ -295,11 +296,11 @@ static bool perf_event_can_profile_kernel(void) return perf_event_paranoid_check(1); } -struct evsel *evsel__new_cycles(bool precise) +struct evsel *evsel__new_cycles(bool precise, __u32 type, __u64 config) { struct perf_event_attr attr = { - .type = PERF_TYPE_HARDWARE, - .config = PERF_COUNT_HW_CPU_CYCLES, + .type = type, + .config = config, .exclude_kernel = !perf_event_can_profile_kernel(), }; struct evsel *evsel; @@ -492,6 +493,28 @@ const char *evsel__hw_names[PERF_COUNT_HW_MAX] = { "ref-cycles", }; +char *evsel__bpf_counter_events; + +bool evsel__match_bpf_counter_events(const char *name) +{ + int name_len; + bool match; + char *ptr; + + if (!evsel__bpf_counter_events) + return false; + + ptr = strstr(evsel__bpf_counter_events, name); + name_len = strlen(name); + + /* check name matches a full token in evsel__bpf_counter_events */ + match = (ptr != NULL) && + ((ptr == evsel__bpf_counter_events) || (*(ptr - 1) == ',')) && + ((*(ptr + name_len) == ',') || (*(ptr + name_len) == '\0')); + + return match; +} + static const char *__evsel__hw_name(u64 config) { if (config < PERF_COUNT_HW_MAX && evsel__hw_names[config]) @@ -621,7 +644,7 @@ const char *evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX][EVSEL__MAX_AL #define COP(x) (1 << x) /* - * cache operartion stat + * cache operation stat * L1I : Read and prefetch only * ITLB and BPU : Read-only */ @@ -2275,7 +2298,7 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, /* * Undo swap of u64, then swap on individual u32s, * get the size of the raw area and undo all of the - * swap. The pevent interface handles endianity by + * swap. The pevent interface handles endianness by * itself. */ if (swapped) { @@ -2797,3 +2820,8 @@ void evsel__zero_per_pkg(struct evsel *evsel) hashmap__clear(evsel->per_pkg_mask); } } + +bool evsel__is_hybrid(struct evsel *evsel) +{ + return evsel->pmu_name && perf_pmu__is_hybrid(evsel->pmu_name); +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 6026487353dd..75cf5dbfe208 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -20,6 +20,8 @@ union perf_event; struct bpf_counter_ops; struct target; struct hashmap; +struct bperf_leader_bpf; +struct bperf_follower_bpf; typedef int (evsel__sb_cb_t)(union perf_event *event, void *data); @@ -80,6 +82,7 @@ struct evsel { bool auto_merge_stats; bool collect_stat; bool weak_group; + bool bpf_counter; int bpf_fd; struct bpf_object *bpf_obj; }; @@ -113,6 +116,7 @@ struct evsel { bool merged_stat; bool reset_group; bool errored; + bool use_config_name; struct hashmap *per_pkg_mask; struct evsel *leader; struct list_head config_terms; @@ -130,8 +134,24 @@ struct evsel { * See also evsel__has_callchain(). */ __u64 synth_sample_type; - struct list_head bpf_counter_list; + + /* + * bpf_counter_ops serves two use cases: + * 1. perf-stat -b counting events used byBPF programs + * 2. perf-stat --use-bpf use BPF programs to aggregate counts + */ struct bpf_counter_ops *bpf_counter_ops; + + /* for perf-stat -b */ + struct list_head bpf_counter_list; + + /* for perf-stat --use-bpf */ + int bperf_leader_prog_fd; + int bperf_leader_link_fd; + union { + struct bperf_leader_bpf *leader_skel; + struct bperf_follower_bpf *follower_skel; + }; }; struct perf_missing_features { @@ -157,7 +177,6 @@ struct perf_missing_features { extern struct perf_missing_features perf_missing_features; struct perf_cpu_map; -struct target; struct thread_map; struct record_opts; @@ -202,7 +221,7 @@ static inline struct evsel *evsel__newtp(const char *sys, const char *name) return evsel__newtp_idx(sys, name, 0); } -struct evsel *evsel__new_cycles(bool precise); +struct evsel *evsel__new_cycles(bool precise, __u32 type, __u64 config); struct tep_event *event_format__new(const char *sys, const char *name); @@ -222,6 +241,11 @@ void evsel__calc_id_pos(struct evsel *evsel); bool evsel__is_cache_op_valid(u8 type, u8 op); +static inline bool evsel__is_bpf(struct evsel *evsel) +{ + return evsel->bpf_counter_ops != NULL; +} + #define EVSEL__MAX_ALIASES 8 extern const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX][EVSEL__MAX_ALIASES]; @@ -229,6 +253,9 @@ extern const char *evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX][EVSEL__MAX_ALI extern const char *evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX][EVSEL__MAX_ALIASES]; extern const char *evsel__hw_names[PERF_COUNT_HW_MAX]; extern const char *evsel__sw_names[PERF_COUNT_SW_MAX]; +extern char *evsel__bpf_counter_events; +bool evsel__match_bpf_counter_events(const char *name); + int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size); const char *evsel__name(struct evsel *evsel); @@ -435,4 +462,5 @@ struct perf_env *evsel__env(struct evsel *evsel); int evsel__store_ids(struct evsel *evsel, struct evlist *evlist); void evsel__zero_per_pkg(struct evsel *evsel); +bool evsel__is_hybrid(struct evsel *evsel); #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index dcf8d19b83c8..85df3e4771e4 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -3,7 +3,7 @@ #define PARSE_CTX_H 1 // There are fixes that need to land upstream before we can use libbpf's headers, -// for now use our copy uncoditionally, since the data structures at this point +// for now use our copy unconditionally, since the data structures at this point // are exactly the same, no problem. //#ifdef HAVE_LIBBPF_SUPPORT //#include <bpf/hashmap.h> diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 20effdff76ce..aa1e42518d37 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -127,7 +127,7 @@ static int __do_write_buf(struct feat_fd *ff, const void *buf, size_t size) return 0; } -/* Return: 0 if succeded, -ERR if failed. */ +/* Return: 0 if succeeded, -ERR if failed. */ int do_write(struct feat_fd *ff, const void *buf, size_t size) { if (!ff->buf) @@ -135,7 +135,7 @@ int do_write(struct feat_fd *ff, const void *buf, size_t size) return __do_write_buf(ff, buf, size); } -/* Return: 0 if succeded, -ERR if failed. */ +/* Return: 0 if succeeded, -ERR if failed. */ static int do_write_bitmap(struct feat_fd *ff, unsigned long *set, u64 size) { u64 *p = (u64 *) set; @@ -154,7 +154,7 @@ static int do_write_bitmap(struct feat_fd *ff, unsigned long *set, u64 size) return 0; } -/* Return: 0 if succeded, -ERR if failed. */ +/* Return: 0 if succeeded, -ERR if failed. */ int write_padded(struct feat_fd *ff, const void *bf, size_t count, size_t count_aligned) { @@ -170,7 +170,7 @@ int write_padded(struct feat_fd *ff, const void *bf, #define string_size(str) \ (PERF_ALIGN((strlen(str) + 1), NAME_ALIGN) + sizeof(u32)) -/* Return: 0 if succeded, -ERR if failed. */ +/* Return: 0 if succeeded, -ERR if failed. */ static int do_write_string(struct feat_fd *ff, const char *str) { u32 len, olen; @@ -266,7 +266,7 @@ static char *do_read_string(struct feat_fd *ff) return NULL; } -/* Return: 0 if succeded, -ERR if failed. */ +/* Return: 0 if succeeded, -ERR if failed. */ static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize) { unsigned long *set; @@ -2874,7 +2874,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) int err = -1; if (ff->ph->needs_swap) { - pr_warning("interpreting bpf_prog_info from systems with endianity is not yet supported\n"); + pr_warning("interpreting bpf_prog_info from systems with endianness is not yet supported\n"); return 0; } @@ -2942,7 +2942,7 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) int err = -1; if (ff->ph->needs_swap) { - pr_warning("interpreting btf from systems with endianity is not yet supported\n"); + pr_warning("interpreting btf from systems with endianness is not yet supported\n"); return 0; } @@ -3481,11 +3481,11 @@ static const size_t attr_pipe_abi_sizes[] = { }; /* - * In the legacy pipe format, there is an implicit assumption that endiannesss + * In the legacy pipe format, there is an implicit assumption that endianness * between host recording the samples, and host parsing the samples is the * same. This is not always the case given that the pipe output may always be * redirected into a file and analyzed on a different machine with possibly a - * different endianness and perf_event ABI revsions in the perf tool itself. + * different endianness and perf_event ABI revisions in the perf tool itself. */ static int try_all_pipe_abis(uint64_t hdr_sz, struct perf_header *ph) { diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index c82f5fc26af8..65fe65ba03c2 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -211,6 +211,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_MEM_BLOCKED, 10); hists__new_col_len(hists, HISTC_LOCAL_INS_LAT, 13); hists__new_col_len(hists, HISTC_GLOBAL_INS_LAT, 13); + hists__new_col_len(hists, HISTC_P_STAGE_CYC, 13); if (symbol_conf.nanosecs) hists__new_col_len(hists, HISTC_TIME, 16); else @@ -289,13 +290,14 @@ static long hist_time(unsigned long htime) } static void he_stat__add_period(struct he_stat *he_stat, u64 period, - u64 weight, u64 ins_lat) + u64 weight, u64 ins_lat, u64 p_stage_cyc) { he_stat->period += period; he_stat->weight += weight; he_stat->nr_events += 1; he_stat->ins_lat += ins_lat; + he_stat->p_stage_cyc += p_stage_cyc; } static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src) @@ -308,6 +310,7 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src) dest->nr_events += src->nr_events; dest->weight += src->weight; dest->ins_lat += src->ins_lat; + dest->p_stage_cyc += src->p_stage_cyc; } static void he_stat__decay(struct he_stat *he_stat) @@ -597,6 +600,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, u64 period = entry->stat.period; u64 weight = entry->stat.weight; u64 ins_lat = entry->stat.ins_lat; + u64 p_stage_cyc = entry->stat.p_stage_cyc; bool leftmost = true; p = &hists->entries_in->rb_root.rb_node; @@ -615,11 +619,11 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, if (!cmp) { if (sample_self) { - he_stat__add_period(&he->stat, period, weight, ins_lat); + he_stat__add_period(&he->stat, period, weight, ins_lat, p_stage_cyc); hist_entry__add_callchain_period(he, period); } if (symbol_conf.cumulate_callchain) - he_stat__add_period(he->stat_acc, period, weight, ins_lat); + he_stat__add_period(he->stat_acc, period, weight, ins_lat, p_stage_cyc); /* * This mem info was allocated from sample__resolve_mem @@ -731,6 +735,7 @@ __hists__add_entry(struct hists *hists, .period = sample->period, .weight = sample->weight, .ins_lat = sample->ins_lat, + .p_stage_cyc = sample->p_stage_cyc, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent) | al->filtered, @@ -2320,14 +2325,19 @@ void events_stats__inc(struct events_stats *stats, u32 type) ++stats->nr_events[type]; } -void hists__inc_nr_events(struct hists *hists, u32 type) +static void hists_stats__inc(struct hists_stats *stats) { - events_stats__inc(&hists->stats, type); + ++stats->nr_samples; +} + +void hists__inc_nr_events(struct hists *hists) +{ + hists_stats__inc(&hists->stats); } void hists__inc_nr_samples(struct hists *hists, bool filtered) { - events_stats__inc(&hists->stats, PERF_RECORD_SAMPLE); + hists_stats__inc(&hists->stats); if (!filtered) hists->stats.nr_non_filtered_samples++; } @@ -2666,14 +2676,21 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, } } -size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp) +size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp, + bool skip_empty) { struct evsel *pos; size_t ret = 0; evlist__for_each_entry(evlist, pos) { + struct hists *hists = evsel__hists(pos); + + if (skip_empty && !hists->stats.nr_samples) + continue; + ret += fprintf(fp, "%s stats:\n", evsel__name(pos)); - ret += events_stats__fprintf(&evsel__hists(pos)->stats, fp); + ret += fprintf(fp, "%16s events: %10d\n", + "SAMPLE", hists->stats.nr_samples); } return ret; @@ -2693,7 +2710,7 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh const struct dso *dso = hists->dso_filter; struct thread *thread = hists->thread_filter; int socket_id = hists->socket_filter; - unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE]; + unsigned long nr_samples = hists->stats.nr_samples; u64 nr_events = hists->stats.total_period; struct evsel *evsel = hists_to_evsel(hists); const char *ev_name = evsel__name(evsel); @@ -2720,7 +2737,7 @@ int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool sh nr_samples += pos_hists->stats.nr_non_filtered_samples; nr_events += pos_hists->stats.total_non_filtered_period; } else { - nr_samples += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE]; + nr_samples += pos_hists->stats.nr_samples; nr_events += pos_hists->stats.total_period; } } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 3c537232294b..5343b62476e6 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -75,6 +75,7 @@ enum hist_column { HISTC_MEM_BLOCKED, HISTC_LOCAL_INS_LAT, HISTC_GLOBAL_INS_LAT, + HISTC_P_STAGE_CYC, HISTC_NR_COLS, /* Last entry */ }; @@ -95,7 +96,7 @@ struct hists { const char *uid_filter_str; const char *symbol_filter_str; pthread_mutex_t lock; - struct events_stats stats; + struct hists_stats stats; u64 event_stream; u16 col_len[HISTC_NR_COLS]; bool has_callchains; @@ -195,13 +196,14 @@ struct hist_entry *hists__get_entry(struct hists *hists, int idx); u64 hists__total_period(struct hists *hists); void hists__reset_stats(struct hists *hists); void hists__inc_stats(struct hists *hists, struct hist_entry *h); -void hists__inc_nr_events(struct hists *hists, u32 type); +void hists__inc_nr_events(struct hists *hists); void hists__inc_nr_samples(struct hists *hists, bool filtered); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, bool ignore_callchains); -size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp); +size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp, + bool skip_empty); void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index f6e28ac231b7..8658d42ce57a 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -3569,7 +3569,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event, /* * Since this thread will not be kept in any rbtree not in a * list, initialize its list node so that at thread__put() the - * current thread lifetime assuption is kept and we don't segfault + * current thread lifetime assumption is kept and we don't segfault * at list_del_init(). */ INIT_LIST_HEAD(&pt->unknown_thread->node); diff --git a/tools/perf/util/iostat.c b/tools/perf/util/iostat.c new file mode 100644 index 000000000000..57dd49da28fe --- /dev/null +++ b/tools/perf/util/iostat.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "util/iostat.h" +#include "util/debug.h" + +enum iostat_mode_t iostat_mode = IOSTAT_NONE; + +__weak int iostat_prepare(struct evlist *evlist __maybe_unused, + struct perf_stat_config *config __maybe_unused) +{ + return -1; +} + +__weak int iostat_parse(const struct option *opt __maybe_unused, + const char *str __maybe_unused, + int unset __maybe_unused) +{ + pr_err("iostat mode is not supported on current platform\n"); + return -1; +} + +__weak void iostat_list(struct evlist *evlist __maybe_unused, + struct perf_stat_config *config __maybe_unused) +{ +} + +__weak void iostat_release(struct evlist *evlist __maybe_unused) +{ +} + +__weak void iostat_print_header_prefix(struct perf_stat_config *config __maybe_unused) +{ +} + +__weak void iostat_print_metric(struct perf_stat_config *config __maybe_unused, + struct evsel *evsel __maybe_unused, + struct perf_stat_output_ctx *out __maybe_unused) +{ +} + +__weak void iostat_prefix(struct evlist *evlist __maybe_unused, + struct perf_stat_config *config __maybe_unused, + char *prefix __maybe_unused, + struct timespec *ts __maybe_unused) +{ +} + +__weak void iostat_print_counters(struct evlist *evlist __maybe_unused, + struct perf_stat_config *config __maybe_unused, + struct timespec *ts __maybe_unused, + char *prefix __maybe_unused, + iostat_print_counter_t print_cnt_cb __maybe_unused) +{ +} diff --git a/tools/perf/util/iostat.h b/tools/perf/util/iostat.h new file mode 100644 index 000000000000..23c1c46a331a --- /dev/null +++ b/tools/perf/util/iostat.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * perf iostat + * + * Copyright (C) 2020, Intel Corporation + * + * Authors: Alexander Antonov <alexander.antonov@linux.intel.com> + */ + +#ifndef _IOSTAT_H +#define _IOSTAT_H + +#include <subcmd/parse-options.h> +#include "util/stat.h" +#include "util/parse-events.h" +#include "util/evlist.h" + +struct option; +struct perf_stat_config; +struct evlist; +struct timespec; + +enum iostat_mode_t { + IOSTAT_NONE = -1, + IOSTAT_RUN = 0, + IOSTAT_LIST = 1 +}; + +extern enum iostat_mode_t iostat_mode; + +typedef void (*iostat_print_counter_t)(struct perf_stat_config *, struct evsel *, char *); + +int iostat_prepare(struct evlist *evlist, struct perf_stat_config *config); +int iostat_parse(const struct option *opt, const char *str, + int unset __maybe_unused); +void iostat_list(struct evlist *evlist, struct perf_stat_config *config); +void iostat_release(struct evlist *evlist); +void iostat_prefix(struct evlist *evlist, struct perf_stat_config *config, + char *prefix, struct timespec *ts); +void iostat_print_header_prefix(struct perf_stat_config *config); +void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel, + struct perf_stat_output_ctx *out); +void iostat_print_counters(struct evlist *evlist, + struct perf_stat_config *config, struct timespec *ts, + char *prefix, iostat_print_counter_t print_cnt_cb); + +#endif /* _IOSTAT_H */ diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 9760d8e7b386..917a9c707371 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -396,21 +396,31 @@ static pid_t jr_entry_tid(struct jit_buf_desc *jd, union jr_entry *jr) static uint64_t convert_timestamp(struct jit_buf_desc *jd, uint64_t timestamp) { - struct perf_tsc_conversion tc; + struct perf_tsc_conversion tc = { .time_shift = 0, }; + struct perf_record_time_conv *time_conv = &jd->session->time_conv; if (!jd->use_arch_timestamp) return timestamp; - tc.time_shift = jd->session->time_conv.time_shift; - tc.time_mult = jd->session->time_conv.time_mult; - tc.time_zero = jd->session->time_conv.time_zero; - tc.time_cycles = jd->session->time_conv.time_cycles; - tc.time_mask = jd->session->time_conv.time_mask; - tc.cap_user_time_zero = jd->session->time_conv.cap_user_time_zero; - tc.cap_user_time_short = jd->session->time_conv.cap_user_time_short; + tc.time_shift = time_conv->time_shift; + tc.time_mult = time_conv->time_mult; + tc.time_zero = time_conv->time_zero; - if (!tc.cap_user_time_zero) - return 0; + /* + * The event TIME_CONV was extended for the fields from "time_cycles" + * when supported cap_user_time_short, for backward compatibility, + * checks the event size and assigns these extended fields if these + * fields are contained in the event. + */ + if (event_contains(*time_conv, time_cycles)) { + tc.time_cycles = time_conv->time_cycles; + tc.time_mask = time_conv->time_mask; + tc.cap_user_time_zero = time_conv->cap_user_time_zero; + tc.cap_user_time_short = time_conv->cap_user_time_short; + + if (!tc.cap_user_time_zero) + return 0; + } return tsc_to_perf_time(timestamp, &tc); } diff --git a/tools/perf/util/levenshtein.c b/tools/perf/util/levenshtein.c index a217ecf0359d..6a6712635aa4 100644 --- a/tools/perf/util/levenshtein.c +++ b/tools/perf/util/levenshtein.c @@ -30,7 +30,7 @@ * * It does so by calculating the costs of the path ending in characters * i (in string1) and j (in string2), respectively, given that the last - * operation is a substition, a swap, a deletion, or an insertion. + * operation is a substitution, a swap, a deletion, or an insertion. * * This implementation allows the costs to be weighted: * diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c index 6b4e5a0892f8..c397be0c2e32 100644 --- a/tools/perf/util/libunwind/arm64.c +++ b/tools/perf/util/libunwind/arm64.c @@ -4,7 +4,7 @@ * 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 + * name and the definition 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. * diff --git a/tools/perf/util/libunwind/x86_32.c b/tools/perf/util/libunwind/x86_32.c index 21c216c40a3b..b2b92d030aef 100644 --- a/tools/perf/util/libunwind/x86_32.c +++ b/tools/perf/util/libunwind/x86_32.c @@ -4,7 +4,7 @@ * 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 + * name and the definition 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. * diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index dbdffb6673fe..3ceaf7ef3301 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -471,7 +471,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf, /* * This is an optional work. Even it fail we can continue our - * work. Needn't to check error return. + * work. Needn't check error return. */ llvm__get_kbuild_opts(&kbuild_dir, &kbuild_include_opts); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b5c2d8be4144..3ff4936a15a4 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -905,7 +905,7 @@ static struct map *machine__addnew_module_map(struct machine *machine, u64 start maps__insert(&machine->kmaps, map); - /* Put the map here because maps__insert alread got it */ + /* Put the map here because maps__insert already got it */ map__put(map); out: /* put the dso here, corresponding to machine__findnew_module_dso */ @@ -1952,7 +1952,7 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event * maps because that is what the kernel just did. * * But when synthesizing, this should not be done. If we do, we end up - * with overlapping maps as we process the sythesized MMAP2 events that + * with overlapping maps as we process the synthesized MMAP2 events that * get delivered shortly thereafter. * * Use the FORK event misc flags in an internal way to signal this @@ -2038,8 +2038,8 @@ int machine__process_event(struct machine *machine, union perf_event *event, static bool symbol__match_regex(struct symbol *sym, regex_t *regex) { if (!regexec(regex, sym->name, 0, NULL, 0)) - return 1; - return 0; + return true; + return false; } static void ip__resolve_ams(struct thread *thread, @@ -2518,7 +2518,7 @@ static bool has_stitched_lbr(struct thread *thread, /* * Check if there are identical LBRs between two samples. - * Identicall LBRs must have same from, to and flags values. Also, + * Identical LBRs must have same from, to and flags values. Also, * they have to be saved in the same LBR registers (same physical * index). * @@ -2588,7 +2588,7 @@ err: } /* - * Recolve LBR callstack chain sample + * Resolve LBR callstack chain sample * Return: * 1 on success get LBR callchain information * 0 no available LBR callchain information, should try fp diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 9f32825c98d8..d32f5b28c1fb 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -75,7 +75,7 @@ struct thread; /* map__for_each_symbol - iterate over the symbols in the given map * - * @map: the 'struct map *' in which symbols itereated + * @map: the 'struct map *' in which symbols are iterated * @pos: the 'struct symbol *' to use as a loop cursor * @n: the 'struct rb_node *' to use as a temporary storage * Note: caller must ensure map->dso is not NULL (map is loaded). @@ -86,7 +86,7 @@ struct thread; /* map__for_each_symbol_with_name - iterate over the symbols in the given map * that have the given name * - * @map: the 'struct map *' in which symbols itereated + * @map: the 'struct map *' in which symbols are iterated * @sym_name: the symbol name * @pos: the 'struct symbol *' to use as a loop cursor */ diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h index 755cef7e0625..cacdebd65b8a 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -44,7 +44,6 @@ bool is_mem_loads_aux_event(struct evsel *leader); void perf_mem_events__list(void); -struct mem_info; int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info); int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info); int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info); @@ -81,7 +80,7 @@ struct c2c_stats { u32 rmt_dram; /* count of loads miss to remote DRAM */ u32 blk_data; /* count of loads blocked by data */ u32 blk_addr; /* count of loads blocked by address conflict */ - u32 nomap; /* count of load/stores with no phys adrs */ + u32 nomap; /* count of load/stores with no phys addrs */ u32 noparse; /* count of unparsable data sources */ }; diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 26c990e32378..8336dd8e8098 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -181,7 +181,7 @@ static bool evsel_same_pmu(struct evsel *ev1, struct evsel *ev2) * @pctx: the parse context for the metric expression. * @metric_no_merge: don't attempt to share events for the metric with other * metrics. - * @has_constraint: is there a contraint on the group of events? In which case + * @has_constraint: is there a constraint on the group of events? In which case * the events won't be grouped. * @metric_events: out argument, null terminated array of evsel's associated * with the metric. @@ -618,7 +618,7 @@ static int metricgroup__print_sys_event_iter(struct pmu_event *pe, void *data) void metricgroup__print(bool metrics, bool metricgroups, char *filter, bool raw, bool details) { - struct pmu_events_map *map = perf_pmu__find_map(NULL); + struct pmu_events_map *map = pmu_events_map__find(); struct pmu_event *pe; int i; struct rblist groups; @@ -900,7 +900,8 @@ static int __add_metric(struct list_head *metric_list, (match_metric(__pe->metric_group, __metric) || \ match_metric(__pe->metric_name, __metric))) -static struct pmu_event *find_metric(const char *metric, struct pmu_events_map *map) +struct pmu_event *metricgroup__find_metric(const char *metric, + struct pmu_events_map *map) { struct pmu_event *pe; int i; @@ -985,7 +986,7 @@ static int __resolve_metric(struct metric *m, struct expr_id *parent; struct pmu_event *pe; - pe = find_metric(cur->key, map); + pe = metricgroup__find_metric(cur->key, map); if (!pe) continue; @@ -1253,8 +1254,7 @@ int metricgroup__parse_groups(const struct option *opt, struct rblist *metric_events) { struct evlist *perf_evlist = *(struct evlist **)opt->value; - struct pmu_events_map *map = perf_pmu__find_map(NULL); - + struct pmu_events_map *map = pmu_events_map__find(); return parse_groups(perf_evlist, str, metric_no_group, metric_no_merge, NULL, metric_events, map); @@ -1273,7 +1273,7 @@ int metricgroup__parse_groups_test(struct evlist *evlist, bool metricgroup__has_metric(const char *metric) { - struct pmu_events_map *map = perf_pmu__find_map(NULL); + struct pmu_events_map *map = pmu_events_map__find(); struct pmu_event *pe; int i; diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index ed1b9392e624..cc4a92492a61 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -9,7 +9,6 @@ struct evlist; struct evsel; -struct evlist; struct option; struct rblist; struct pmu_events_map; @@ -44,7 +43,8 @@ int metricgroup__parse_groups(const struct option *opt, bool metric_no_group, bool metric_no_merge, struct rblist *metric_events); - +struct pmu_event *metricgroup__find_metric(const char *metric, + struct pmu_events_map *map); int metricgroup__parse_groups_test(struct evlist *evlist, struct pmu_events_map *map, const char *str, diff --git a/tools/perf/util/parse-events-hybrid.c b/tools/perf/util/parse-events-hybrid.c new file mode 100644 index 000000000000..10160ab126f9 --- /dev/null +++ b/tools/perf/util/parse-events-hybrid.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/err.h> +#include <linux/zalloc.h> +#include <errno.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <sys/param.h> +#include "evlist.h" +#include "evsel.h" +#include "parse-events.h" +#include "parse-events-hybrid.h" +#include "debug.h" +#include "pmu.h" +#include "pmu-hybrid.h" +#include "perf.h" + +static void config_hybrid_attr(struct perf_event_attr *attr, + int type, int pmu_type) +{ + /* + * attr.config layout for type PERF_TYPE_HARDWARE and + * PERF_TYPE_HW_CACHE + * + * PERF_TYPE_HARDWARE: 0xEEEEEEEE000000AA + * AA: hardware event ID + * EEEEEEEE: PMU type ID + * PERF_TYPE_HW_CACHE: 0xEEEEEEEE00DDCCBB + * BB: hardware cache ID + * CC: hardware cache op ID + * DD: hardware cache op result ID + * EEEEEEEE: PMU type ID + * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied. + */ + attr->type = type; + attr->config = attr->config | ((__u64)pmu_type << PERF_PMU_TYPE_SHIFT); +} + +static int create_event_hybrid(__u32 config_type, int *idx, + struct list_head *list, + struct perf_event_attr *attr, char *name, + struct list_head *config_terms, + struct perf_pmu *pmu) +{ + struct evsel *evsel; + __u32 type = attr->type; + __u64 config = attr->config; + + config_hybrid_attr(attr, config_type, pmu->type); + evsel = parse_events__add_event_hybrid(list, idx, attr, name, + pmu, config_terms); + if (evsel) + evsel->pmu_name = strdup(pmu->name); + else + return -ENOMEM; + + attr->type = type; + attr->config = config; + return 0; +} + +static int pmu_cmp(struct parse_events_state *parse_state, + struct perf_pmu *pmu) +{ + if (!parse_state->hybrid_pmu_name) + return 0; + + return strcmp(parse_state->hybrid_pmu_name, pmu->name); +} + +static int add_hw_hybrid(struct parse_events_state *parse_state, + struct list_head *list, struct perf_event_attr *attr, + char *name, struct list_head *config_terms) +{ + struct perf_pmu *pmu; + int ret; + + perf_pmu__for_each_hybrid_pmu(pmu) { + if (pmu_cmp(parse_state, pmu)) + continue; + + ret = create_event_hybrid(PERF_TYPE_HARDWARE, + &parse_state->idx, list, attr, name, + config_terms, pmu); + if (ret) + return ret; + } + + return 0; +} + +static int create_raw_event_hybrid(int *idx, struct list_head *list, + struct perf_event_attr *attr, char *name, + struct list_head *config_terms, + struct perf_pmu *pmu) +{ + struct evsel *evsel; + + attr->type = pmu->type; + evsel = parse_events__add_event_hybrid(list, idx, attr, name, + pmu, config_terms); + if (evsel) + evsel->pmu_name = strdup(pmu->name); + else + return -ENOMEM; + + return 0; +} + +static int add_raw_hybrid(struct parse_events_state *parse_state, + struct list_head *list, struct perf_event_attr *attr, + char *name, struct list_head *config_terms) +{ + struct perf_pmu *pmu; + int ret; + + perf_pmu__for_each_hybrid_pmu(pmu) { + if (pmu_cmp(parse_state, pmu)) + continue; + + ret = create_raw_event_hybrid(&parse_state->idx, list, attr, + name, config_terms, pmu); + if (ret) + return ret; + } + + return 0; +} + +int parse_events__add_numeric_hybrid(struct parse_events_state *parse_state, + struct list_head *list, + struct perf_event_attr *attr, + char *name, struct list_head *config_terms, + bool *hybrid) +{ + *hybrid = false; + if (attr->type == PERF_TYPE_SOFTWARE) + return 0; + + if (!perf_pmu__has_hybrid()) + return 0; + + *hybrid = true; + if (attr->type != PERF_TYPE_RAW) { + return add_hw_hybrid(parse_state, list, attr, name, + config_terms); + } + + return add_raw_hybrid(parse_state, list, attr, name, + config_terms); +} + +int parse_events__add_cache_hybrid(struct list_head *list, int *idx, + struct perf_event_attr *attr, char *name, + struct list_head *config_terms, + bool *hybrid, + struct parse_events_state *parse_state) +{ + struct perf_pmu *pmu; + int ret; + + *hybrid = false; + if (!perf_pmu__has_hybrid()) + return 0; + + *hybrid = true; + perf_pmu__for_each_hybrid_pmu(pmu) { + if (pmu_cmp(parse_state, pmu)) + continue; + + ret = create_event_hybrid(PERF_TYPE_HW_CACHE, idx, list, + attr, name, config_terms, pmu); + if (ret) + return ret; + } + + return 0; +} diff --git a/tools/perf/util/parse-events-hybrid.h b/tools/perf/util/parse-events-hybrid.h new file mode 100644 index 000000000000..f33bd67aa851 --- /dev/null +++ b/tools/perf/util/parse-events-hybrid.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_PARSE_EVENTS_HYBRID_H +#define __PERF_PARSE_EVENTS_HYBRID_H + +#include <linux/list.h> +#include <stdbool.h> +#include <linux/types.h> +#include <linux/perf_event.h> +#include <string.h> + +int parse_events__add_numeric_hybrid(struct parse_events_state *parse_state, + struct list_head *list, + struct perf_event_attr *attr, + char *name, struct list_head *config_terms, + bool *hybrid); + +int parse_events__add_cache_hybrid(struct list_head *list, int *idx, + struct perf_event_attr *attr, char *name, + struct list_head *config_terms, + bool *hybrid, + struct parse_events_state *parse_state); + +#endif /* __PERF_PARSE_EVENTS_HYBRID_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index c0c0fab22cb8..4dad14265b81 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -37,6 +37,8 @@ #include "util/evsel_config.h" #include "util/event.h" #include "util/pfm.h" +#include "util/parse-events-hybrid.h" +#include "util/pmu-hybrid.h" #include "perf.h" #define MAX_NAME_LEN 100 @@ -47,6 +49,9 @@ extern int parse_events_debug; int parse_events_parse(void *parse_state, void *scanner); static int get_config_terms(struct list_head *head_config, struct list_head *head_terms __maybe_unused); +static int parse_events__with_hybrid_pmu(struct parse_events_state *parse_state, + const char *str, char *pmu_name, + struct list_head *list); static struct perf_pmu_event_symbol *perf_pmu_events_list; /* @@ -452,14 +457,16 @@ static int config_attr(struct perf_event_attr *attr, int parse_events_add_cache(struct list_head *list, int *idx, char *type, char *op_result1, char *op_result2, struct parse_events_error *err, - struct list_head *head_config) + struct list_head *head_config, + struct parse_events_state *parse_state) { struct perf_event_attr attr; LIST_HEAD(config_terms); char name[MAX_NAME_LEN], *config_name; int cache_type = -1, cache_op = -1, cache_result = -1; char *op_result[2] = { op_result1, op_result2 }; - int i, n; + int i, n, ret; + bool hybrid; /* * No fallback - if we cannot get a clear cache type @@ -519,6 +526,13 @@ int parse_events_add_cache(struct list_head *list, int *idx, if (get_config_terms(head_config, &config_terms)) return -ENOMEM; } + + ret = parse_events__add_cache_hybrid(list, idx, &attr, + config_name ? : name, &config_terms, + &hybrid, parse_state); + if (hybrid) + return ret; + return add_event(list, idx, &attr, config_name ? : name, &config_terms); } @@ -846,9 +860,9 @@ split_bpf_config_terms(struct list_head *evt_head_config, struct parse_events_term *term, *temp; /* - * Currectly, all possible user config term + * Currently, all possible user config term * belong to bpf object. parse_events__is_hardcoded_term() - * happends to be a good flag. + * happens to be a good flag. * * See parse_events_config_bpf() and * config_term_tracepoint(). @@ -898,7 +912,7 @@ int parse_events_load_bpf(struct parse_events_state *parse_state, /* * Caller doesn't know anything about obj_head_config, - * so combine them together again before returnning. + * so combine them together again before returning. */ if (head_config) list_splice_tail(&obj_head_config, head_config); @@ -1185,10 +1199,10 @@ do { \ } /* - * Check term availbility after basic checking so + * Check term availability after basic checking so * PARSE_EVENTS__TERM_TYPE_USER can be found and filtered. * - * If check availbility at the entry of this function, + * If check availability at the entry of this function, * user will see "'<sysfs term>' is not usable in 'perf stat'" * if an invalid config term is provided for legacy events * (for example, instructions/badterm/...), which is confusing. @@ -1419,6 +1433,8 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, { struct perf_event_attr attr; LIST_HEAD(config_terms); + bool hybrid; + int ret; memset(&attr, 0, sizeof(attr)); attr.type = type; @@ -1433,6 +1449,12 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, return -ENOMEM; } + ret = parse_events__add_numeric_hybrid(parse_state, list, &attr, + get_config_name(head_config), + &config_terms, &hybrid); + if (hybrid) + return ret; + return add_event(list, &parse_state->idx, &attr, get_config_name(head_config), &config_terms); } @@ -1456,6 +1478,33 @@ static bool config_term_percore(struct list_head *config_terms) return false; } +static int parse_events__inside_hybrid_pmu(struct parse_events_state *parse_state, + struct list_head *list, char *name, + struct list_head *head_config) +{ + struct parse_events_term *term; + int ret = -1; + + if (parse_state->fake_pmu || !head_config || list_empty(head_config) || + !perf_pmu__is_hybrid(name)) { + return -1; + } + + /* + * More than one term in list. + */ + if (head_config->next && head_config->next->next != head_config) + return -1; + + term = list_first_entry(head_config, struct parse_events_term, list); + if (term && term->config && strcmp(term->config, "event")) { + ret = parse_events__with_hybrid_pmu(parse_state, term->config, + name, list); + } + + return ret; +} + int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config, @@ -1549,6 +1598,11 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (pmu->default_config && get_config_chgs(pmu, head_config, &config_terms)) return -ENOMEM; + if (!parse_events__inside_hybrid_pmu(parse_state, list, name, + head_config)) { + return 0; + } + if (!parse_state->fake_pmu && perf_pmu__config(pmu, &attr, head_config, parse_state->error)) { struct evsel_config_term *pos, *tmp; @@ -1567,6 +1621,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (!evsel) return -ENOMEM; + if (evsel->name) + evsel->use_config_name = true; + evsel->pmu_name = name ? strdup(name) : NULL; evsel->use_uncore_alias = use_uncore_alias; evsel->percore = config_term_percore(&evsel->config_terms); @@ -1804,6 +1861,7 @@ struct event_modifier { int pinned; int weak; int exclusive; + int bpf_counter; }; static int get_event_modifier(struct event_modifier *mod, char *str, @@ -1824,6 +1882,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str, int exclude = eu | ek | eh; int exclude_GH = evsel ? evsel->exclude_GH : 0; int weak = 0; + int bpf_counter = 0; memset(mod, 0, sizeof(*mod)); @@ -1867,6 +1926,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str, exclusive = 1; } else if (*str == 'W') { weak = 1; + } else if (*str == 'b') { + bpf_counter = 1; } else break; @@ -1898,6 +1959,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str, mod->sample_read = sample_read; mod->pinned = pinned; mod->weak = weak; + mod->bpf_counter = bpf_counter; mod->exclusive = exclusive; return 0; @@ -1912,7 +1974,7 @@ static int check_modifier(char *str) char *p = str; /* The sizeof includes 0 byte as well. */ - if (strlen(str) > (sizeof("ukhGHpppPSDIWe") - 1)) + if (strlen(str) > (sizeof("ukhGHpppPSDIWeb") - 1)) return -1; while (*p) { @@ -1953,6 +2015,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) evsel->sample_read = mod.sample_read; evsel->precise_max = mod.precise_max; evsel->weak_group = mod.weak; + evsel->bpf_counter = mod.bpf_counter; if (evsel__is_group_leader(evsel)) { evsel->core.attr.pinned = mod.pinned; @@ -2162,6 +2225,33 @@ int parse_events_terms(struct list_head *terms, const char *str) return ret; } +static int parse_events__with_hybrid_pmu(struct parse_events_state *parse_state, + const char *str, char *pmu_name, + struct list_head *list) +{ + struct parse_events_state ps = { + .list = LIST_HEAD_INIT(ps.list), + .stoken = PE_START_EVENTS, + .hybrid_pmu_name = pmu_name, + .idx = parse_state->idx, + }; + int ret; + + ret = parse_events__scanner(str, &ps); + perf_pmu__parse_cleanup(); + + if (!ret) { + if (!list_empty(&ps.list)) { + list_splice(&ps.list, list); + parse_state->idx = ps.idx; + return 0; + } else + return -1; + } + + return ret; +} + int __parse_events(struct evlist *evlist, const char *str, struct parse_events_error *err, struct perf_pmu *fake_pmu) { @@ -3185,3 +3275,12 @@ char *parse_events_formats_error_string(char *additional_terms) fail: return NULL; } + +struct evsel *parse_events__add_event_hybrid(struct list_head *list, int *idx, + struct perf_event_attr *attr, + char *name, struct perf_pmu *pmu, + struct list_head *config_terms) +{ + return __add_event(list, idx, attr, true, name, pmu, + config_terms, false, NULL); +} diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index e80c9b74f2f2..bf6e41aa9b6a 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -138,6 +138,7 @@ struct parse_events_state { struct list_head *terms; int stoken; struct perf_pmu *fake_pmu; + char *hybrid_pmu_name; }; void parse_events__handle_error(struct parse_events_error *err, int idx, @@ -188,7 +189,8 @@ int parse_events_add_tool(struct parse_events_state *parse_state, int parse_events_add_cache(struct list_head *list, int *idx, char *type, char *op_result1, char *op_result2, struct parse_events_error *error, - struct list_head *head_config); + struct list_head *head_config, + struct parse_events_state *parse_state); int parse_events_add_breakpoint(struct list_head *list, int *idx, u64 addr, char *type, u64 len); int parse_events_add_pmu(struct parse_events_state *parse_state, @@ -263,4 +265,9 @@ static inline bool is_sdt_event(char *str __maybe_unused) int perf_pmu__test_parse_init(void); +struct evsel *parse_events__add_event_hybrid(struct list_head *list, int *idx, + struct perf_event_attr *attr, + char *name, struct perf_pmu *pmu, + struct list_head *config_terms); + #endif /* __PERF_PARSE_EVENTS_H */ diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 0b36285a9435..fb8646cc3e83 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -210,7 +210,7 @@ name_tag [\'][a-zA-Z_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\'] name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]* drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)? /* If you add a modifier you need to update check_modifier() */ -modifier_event [ukhpPGHSDIWe]+ +modifier_event [ukhpPGHSDIWeb]+ modifier_bp [rwx]{1,3} %% diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index d57ac86ce7ca..aba12a4d488e 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -454,7 +454,8 @@ PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_e list = alloc_list(); ABORT_ON(!list); - err = parse_events_add_cache(list, &parse_state->idx, $1, $3, $5, error, $6); + err = parse_events_add_cache(list, &parse_state->idx, $1, $3, $5, error, $6, + parse_state); parse_events_terms__delete($6); free($1); free($3); @@ -475,7 +476,8 @@ PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config list = alloc_list(); ABORT_ON(!list); - err = parse_events_add_cache(list, &parse_state->idx, $1, $3, NULL, error, $4); + err = parse_events_add_cache(list, &parse_state->idx, $1, $3, NULL, error, $4, + parse_state); parse_events_terms__delete($4); free($1); free($3); @@ -495,7 +497,8 @@ PE_NAME_CACHE_TYPE opt_event_config list = alloc_list(); ABORT_ON(!list); - err = parse_events_add_cache(list, &parse_state->idx, $1, NULL, NULL, error, $2); + err = parse_events_add_cache(list, &parse_state->idx, $1, NULL, NULL, error, $2, + parse_state); parse_events_terms__delete($2); free($1); if (err) { diff --git a/tools/perf/util/pmu-hybrid.c b/tools/perf/util/pmu-hybrid.c new file mode 100644 index 000000000000..f51ccaac60ee --- /dev/null +++ b/tools/perf/util/pmu-hybrid.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/list.h> +#include <linux/compiler.h> +#include <linux/string.h> +#include <linux/zalloc.h> +#include <sys/types.h> +#include <errno.h> +#include <fcntl.h> +#include <sys/stat.h> +#include <unistd.h> +#include <stdio.h> +#include <stdbool.h> +#include <stdarg.h> +#include <locale.h> +#include <api/fs/fs.h> +#include "fncache.h" +#include "pmu-hybrid.h" + +LIST_HEAD(perf_pmu__hybrid_pmus); + +bool perf_pmu__hybrid_mounted(const char *name) +{ + char path[PATH_MAX]; + const char *sysfs; + FILE *file; + int n, cpu; + + if (strncmp(name, "cpu_", 4)) + return false; + + sysfs = sysfs__mountpoint(); + if (!sysfs) + return false; + + snprintf(path, PATH_MAX, CPUS_TEMPLATE_CPU, sysfs, name); + if (!file_available(path)) + return false; + + file = fopen(path, "r"); + if (!file) + return false; + + n = fscanf(file, "%u", &cpu); + fclose(file); + if (n <= 0) + return false; + + return true; +} + +struct perf_pmu *perf_pmu__find_hybrid_pmu(const char *name) +{ + struct perf_pmu *pmu; + + if (!name) + return NULL; + + perf_pmu__for_each_hybrid_pmu(pmu) { + if (!strcmp(name, pmu->name)) + return pmu; + } + + return NULL; +} + +bool perf_pmu__is_hybrid(const char *name) +{ + return perf_pmu__find_hybrid_pmu(name) != NULL; +} + +char *perf_pmu__hybrid_type_to_pmu(const char *type) +{ + char *pmu_name = NULL; + + if (asprintf(&pmu_name, "cpu_%s", type) < 0) + return NULL; + + if (perf_pmu__is_hybrid(pmu_name)) + return pmu_name; + + /* + * pmu may be not scanned, check the sysfs. + */ + if (perf_pmu__hybrid_mounted(pmu_name)) + return pmu_name; + + free(pmu_name); + return NULL; +} diff --git a/tools/perf/util/pmu-hybrid.h b/tools/perf/util/pmu-hybrid.h new file mode 100644 index 000000000000..d0fa7bc50a76 --- /dev/null +++ b/tools/perf/util/pmu-hybrid.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PMU_HYBRID_H +#define __PMU_HYBRID_H + +#include <linux/perf_event.h> +#include <linux/compiler.h> +#include <linux/list.h> +#include <stdbool.h> +#include "pmu.h" + +extern struct list_head perf_pmu__hybrid_pmus; + +#define perf_pmu__for_each_hybrid_pmu(pmu) \ + list_for_each_entry(pmu, &perf_pmu__hybrid_pmus, hybrid_list) + +bool perf_pmu__hybrid_mounted(const char *name); + +struct perf_pmu *perf_pmu__find_hybrid_pmu(const char *name); +bool perf_pmu__is_hybrid(const char *name); +char *perf_pmu__hybrid_type_to_pmu(const char *type); + +#endif /* __PMU_HYBRID_H */ diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 46fd0f998484..88c8ecdc60b0 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -25,6 +25,7 @@ #include "string2.h" #include "strbuf.h" #include "fncache.h" +#include "pmu-hybrid.h" struct perf_pmu perf_pmu__fake; @@ -39,6 +40,7 @@ int perf_pmu_parse(struct list_head *list, char *name); extern FILE *perf_pmu_in; static LIST_HEAD(pmus); +static bool hybrid_scanned; /* * Parse & process all the sysfs attributes located under @@ -283,6 +285,7 @@ void perf_pmu_free_alias(struct perf_pmu_alias *newalias) zfree(&newalias->str); zfree(&newalias->metric_expr); zfree(&newalias->metric_name); + zfree(&newalias->pmu_name); parse_events_terms__purge(&newalias->terms); free(newalias); } @@ -297,6 +300,10 @@ static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias, list_for_each_entry(a, alist, list) { if (!strcasecmp(newalias->name, a->name)) { + if (newalias->pmu_name && a->pmu_name && + !strcasecmp(newalias->pmu_name, a->pmu_name)) { + continue; + } perf_pmu_update_alias(a, newalias); perf_pmu_free_alias(newalias); return true; @@ -306,18 +313,27 @@ static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias, } static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, - char *desc, char *val, - char *long_desc, char *topic, - char *unit, char *perpkg, - char *metric_expr, - char *metric_name, - char *deprecated) + char *desc, char *val, struct pmu_event *pe) { struct parse_events_term *term; struct perf_pmu_alias *alias; int ret; int num; char newval[256]; + char *long_desc = NULL, *topic = NULL, *unit = NULL, *perpkg = NULL, + *metric_expr = NULL, *metric_name = NULL, *deprecated = NULL, + *pmu_name = NULL; + + if (pe) { + long_desc = (char *)pe->long_desc; + topic = (char *)pe->topic; + unit = (char *)pe->unit; + perpkg = (char *)pe->perpkg; + metric_expr = (char *)pe->metric_expr; + metric_name = (char *)pe->metric_name; + deprecated = (char *)pe->deprecated; + pmu_name = (char *)pe->pmu; + } alias = malloc(sizeof(*alias)); if (!alias) @@ -382,6 +398,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, } alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1; alias->str = strdup(newval); + alias->pmu_name = pmu_name ? strdup(pmu_name) : NULL; if (deprecated) alias->deprecated = true; @@ -406,8 +423,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI /* Remove trailing newline from sysfs file */ strim(buf); - return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL, - NULL, NULL, NULL, NULL); + return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL); } static inline bool pmu_alias_info_file(char *name) @@ -599,7 +615,6 @@ static struct perf_cpu_map *__pmu_cpumask(const char *path) */ #define SYS_TEMPLATE_ID "./bus/event_source/devices/%s/identifier" #define CPUS_TEMPLATE_UNCORE "%s/bus/event_source/devices/%s/cpumask" -#define CPUS_TEMPLATE_CPU "%s/bus/event_source/devices/%s/cpus" static struct perf_cpu_map *pmu_cpumask(const char *name) { @@ -631,6 +646,9 @@ static bool pmu_is_uncore(const char *name) char path[PATH_MAX]; const char *sysfs; + if (perf_pmu__hybrid_mounted(name)) + return false; + sysfs = sysfs__mountpoint(); snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name); return file_available(path); @@ -717,6 +735,11 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu) return map; } +struct pmu_events_map *__weak pmu_events_map__find(void) +{ + return perf_pmu__find_map(NULL); +} + bool pmu_uncore_alias_match(const char *pmu_name, const char *name) { char *tmp = NULL, *tok, *str; @@ -793,11 +816,7 @@ new_alias: /* need type casts to override 'const' */ __perf_pmu__new_alias(head, NULL, (char *)pe->name, (char *)pe->desc, (char *)pe->event, - (char *)pe->long_desc, (char *)pe->topic, - (char *)pe->unit, (char *)pe->perpkg, - (char *)pe->metric_expr, - (char *)pe->metric_name, - (char *)pe->deprecated); + pe); } } @@ -864,13 +883,7 @@ static int pmu_add_sys_aliases_iter_fn(struct pmu_event *pe, void *data) (char *)pe->name, (char *)pe->desc, (char *)pe->event, - (char *)pe->long_desc, - (char *)pe->topic, - (char *)pe->unit, - (char *)pe->perpkg, - (char *)pe->metric_expr, - (char *)pe->metric_name, - (char *)pe->deprecated); + pe); } return 0; @@ -942,6 +955,7 @@ static struct perf_pmu *pmu_lookup(const char *name) pmu->is_uncore = pmu_is_uncore(name); if (pmu->is_uncore) pmu->id = pmu_id(name); + pmu->is_hybrid = perf_pmu__hybrid_mounted(name); pmu->max_precise = pmu_max_precise(name); pmu_add_cpu_aliases(&aliases, pmu); pmu_add_sys_aliases(&aliases, pmu); @@ -953,6 +967,9 @@ static struct perf_pmu *pmu_lookup(const char *name) list_splice(&aliases, &pmu->aliases); list_add_tail(&pmu->list, &pmus); + if (pmu->is_hybrid) + list_add_tail(&pmu->hybrid_list, &perf_pmu__hybrid_pmus); + pmu->default_config = perf_pmu__get_default_config(pmu); return pmu; @@ -1069,7 +1086,7 @@ int perf_pmu__format_type(struct list_head *formats, const char *name) /* * Sets value based on the format definition (format parameter) - * and unformated value (value parameter). + * and unformatted value (value parameter). */ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v, bool zero) @@ -1408,7 +1425,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, } /* - * if no unit or scale foundin aliases, then + * if no unit or scale found in aliases, then * set defaults as for evsel * unit cannot left to NULL */ @@ -1845,3 +1862,13 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, "'%llx' not supported by kernel)!\n", name ?: "N/A", buf, config); } + +bool perf_pmu__has_hybrid(void) +{ + if (!hybrid_scanned) { + hybrid_scanned = true; + perf_pmu__scan(NULL); + } + + return !list_empty(&perf_pmu__hybrid_pmus); +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 160b0f561771..a790ef758171 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -5,6 +5,7 @@ #include <linux/bitmap.h> #include <linux/compiler.h> #include <linux/perf_event.h> +#include <linux/list.h> #include <stdbool.h> #include "parse-events.h" #include "pmu-events/pmu-events.h" @@ -19,6 +20,7 @@ enum { #define PERF_PMU_FORMAT_BITS 64 #define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/" +#define CPUS_TEMPLATE_CPU "%s/bus/event_source/devices/%s/cpus" struct perf_event_attr; @@ -34,6 +36,7 @@ struct perf_pmu { __u32 type; bool selectable; bool is_uncore; + bool is_hybrid; bool auxtrace; int max_precise; struct perf_event_attr *default_config; @@ -42,6 +45,7 @@ struct perf_pmu { struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */ struct list_head caps; /* HEAD struct perf_pmu_caps -> list */ struct list_head list; /* ELEM */ + struct list_head hybrid_list; }; extern struct perf_pmu perf_pmu__fake; @@ -72,6 +76,7 @@ struct perf_pmu_alias { bool deprecated; char *metric_expr; char *metric_name; + char *pmu_name; }; struct perf_pmu *perf_pmu__find(const char *name); @@ -114,6 +119,7 @@ void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu, struct pmu_events_map *map); struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu); +struct pmu_events_map *pmu_events_map__find(void); bool pmu_uncore_alias_match(const char *pmu_name, const char *name); void perf_pmu_free_alias(struct perf_pmu_alias *alias); @@ -126,4 +132,6 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu); void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, char *name); +bool perf_pmu__has_hybrid(void); + #endif /* __PMU_H */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index a9cff3a50ddf..a78c8d59a555 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -3228,7 +3228,7 @@ errout: return err; } -/* Concatinate two arrays */ +/* Concatenate two arrays */ static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b) { void *ret; @@ -3258,7 +3258,7 @@ concat_probe_trace_events(struct probe_trace_event **tevs, int *ntevs, if (*ntevs + ntevs2 > probe_conf.max_probes) ret = -E2BIG; else { - /* Concatinate the array of probe_trace_event */ + /* Concatenate the array of probe_trace_event */ new_tevs = memcat(*tevs, (*ntevs) * sizeof(**tevs), *tevs2, ntevs2 * sizeof(**tevs2)); if (!new_tevs) diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 1b118c9c86a6..866f2d514d72 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -164,7 +164,7 @@ static struct probe_trace_arg_ref *alloc_trace_arg_ref(long offs) /* * Convert a location into trace_arg. * If tvar == NULL, this just checks variable can be converted. - * If fentry == true and vr_die is a parameter, do huristic search + * If fentry == true and vr_die is a parameter, do heuristic search * for the location fuzzed by function entry mcount. */ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr, @@ -498,7 +498,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, " nor array.\n", varname); return -EINVAL; } - /* While prcessing unnamed field, we don't care about this */ + /* While processing unnamed field, we don't care about this */ if (field->ref && dwarf_diename(vr_die)) { pr_err("Semantic error: %s must be referred by '.'\n", field->name); @@ -1832,7 +1832,7 @@ static int line_range_walk_cb(const char *fname, int lineno, (lf->lno_s > lineno || lf->lno_e < lineno)) return 0; - /* Make sure this line can be reversable */ + /* Make sure this line can be reversible */ if (cu_find_lineinfo(&lf->cu_die, addr, &__fname, &__lineno) > 0 && (lineno != __lineno || strcmp(fname, __fname))) return 0; diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 845dd46e3c61..d7c976671e3a 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -37,3 +37,5 @@ util/units.c util/affinity.c util/rwsem.c util/hashmap.c +util/pmu-hybrid.c +util/fncache.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 278abecb5bdf..412f8e79e409 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -90,6 +90,7 @@ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, */ void bpf_counter__destroy(struct evsel *evsel); int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd); +int bpf_counter__disable(struct evsel *evsel); void bpf_counter__destroy(struct evsel *evsel __maybe_unused) { @@ -100,6 +101,11 @@ int bpf_counter__install_pe(struct evsel *evsel __maybe_unused, int cpu __maybe_ return 0; } +int bpf_counter__disable(struct evsel *evsel __maybe_unused) +{ + return 0; +} + /* * Support debug printing even though util/debug.c is not linked. That means * implementing 'verbose' and 'eprintf'. diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c index 078a71773565..8130b56aa04b 100644 --- a/tools/perf/util/s390-cpumsf.c +++ b/tools/perf/util/s390-cpumsf.c @@ -45,7 +45,7 @@ * the data portion is mmap()'ed. * * To sort the queues in chronological order, all queue access is controlled - * by the auxtrace_heap. This is basicly a stack, each stack element has two + * by the auxtrace_heap. This is basically a stack, each stack element has two * entries, the queue number and a time stamp. However the stack is sorted by * the time stamps. The highest time stamp is at the bottom the lowest * (nearest) time stamp is at the top. That sort order is maintained at all @@ -65,11 +65,11 @@ * stamp of the last processed entry of the auxtrace_buffer replaces the * current auxtrace_heap top. * - * 3. Auxtrace_queues might run of out data and are feeded by the + * 3. Auxtrace_queues might run of out data and are fed by the * PERF_RECORD_AUXTRACE handling, see s390_cpumsf_process_auxtrace_event(). * * Event Generation - * Each sampling-data entry in the auxilary trace data generates a perf sample. + * Each sampling-data entry in the auxiliary trace data generates a perf sample. * This sample is filled * with data from the auxtrace such as PID/TID, instruction address, CPU state, * etc. This sample is processed with perf_session__deliver_synth_event() to @@ -575,7 +575,7 @@ static unsigned long long get_trailer_time(const unsigned char *buf) * pointer to the queue, the second parameter is the time stamp. This * is the time stamp: * - of the event that triggered this processing. - * - or the time stamp when the last proccesing of this queue stopped. + * - or the time stamp when the last processing of this queue stopped. * In this case it stopped at a 4KB page boundary and record the * position on where to continue processing on the next invocation * (see buffer->use_data and buffer->use_size). @@ -640,7 +640,7 @@ static int s390_cpumsf_samples(struct s390_cpumsf_queue *sfq, u64 *ts) goto out; } - pos += dsdes; /* Skip diagnositic entry */ + pos += dsdes; /* Skip diagnostic entry */ /* Check for trailer entry */ if (!s390_cpumsf_reached_trailer(bsdes + dsdes, pos)) { diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c index cfcf8d534d76..08ec3c3ae0ee 100644 --- a/tools/perf/util/s390-sample-raw.c +++ b/tools/perf/util/s390-sample-raw.c @@ -160,11 +160,9 @@ static void s390_cpumcfdg_dump(struct perf_sample *sample) const char *color = PERF_COLOR_BLUE; struct cf_ctrset_entry *cep, ce; struct pmu_events_map *map; - struct perf_pmu pmu; u64 *p; - memset(&pmu, 0, sizeof(pmu)); - map = perf_pmu__find_map(&pmu); + map = pmu_events_map__find(); while (offset < len) { cep = (struct cf_ctrset_entry *)(buf + offset); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index c83c2c6564e0..4e4aa4c97ac5 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -1531,7 +1531,7 @@ static void set_table_handlers(struct tables *tables) * Attempt to use the call path root from the call return * processor, if the call return processor is in use. Otherwise, * we allocate a new call path root. This prevents exporting - * duplicate call path ids when both are in use simultaniously. + * duplicate call path ids when both are in use simultaneously. */ if (tables->dbe.crp) tables->dbe.cpr = tables->dbe.crp->cpr; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 859832a82496..a12cf4f0e97a 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -29,6 +29,7 @@ #include "thread-stack.h" #include "sample-raw.h" #include "stat.h" +#include "tsc.h" #include "ui/progress.h" #include "../perf.h" #include "arch/common.h" @@ -451,6 +452,16 @@ static int process_stat_round_stub(struct perf_session *perf_session __maybe_unu return 0; } +static int process_event_time_conv_stub(struct perf_session *perf_session __maybe_unused, + union perf_event *event) +{ + if (dump_trace) + perf_event__fprintf_time_conv(event, stdout); + + dump_printf(": unhandled!\n"); + return 0; +} + static int perf_session__process_compressed_event_stub(struct perf_session *session __maybe_unused, union perf_event *event __maybe_unused, u64 file_offset __maybe_unused) @@ -532,7 +543,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool) if (tool->stat_round == NULL) tool->stat_round = process_stat_round_stub; if (tool->time_conv == NULL) - tool->time_conv = process_event_op2_stub; + tool->time_conv = process_event_time_conv_stub; if (tool->feature == NULL) tool->feature = process_event_op2_stub; if (tool->compressed == NULL) @@ -949,6 +960,19 @@ static void perf_event__stat_round_swap(union perf_event *event, event->stat_round.time = bswap_64(event->stat_round.time); } +static void perf_event__time_conv_swap(union perf_event *event, + bool sample_id_all __maybe_unused) +{ + event->time_conv.time_shift = bswap_64(event->time_conv.time_shift); + event->time_conv.time_mult = bswap_64(event->time_conv.time_mult); + event->time_conv.time_zero = bswap_64(event->time_conv.time_zero); + + if (event_contains(event->time_conv, time_cycles)) { + event->time_conv.time_cycles = bswap_64(event->time_conv.time_cycles); + event->time_conv.time_mask = bswap_64(event->time_conv.time_mask); + } +} + typedef void (*perf_event__swap_op)(union perf_event *event, bool sample_id_all); @@ -985,7 +1009,7 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_STAT] = perf_event__stat_swap, [PERF_RECORD_STAT_ROUND] = perf_event__stat_round_swap, [PERF_RECORD_EVENT_UPDATE] = perf_event__event_update_swap, - [PERF_RECORD_TIME_CONV] = perf_event__all64_swap, + [PERF_RECORD_TIME_CONV] = perf_event__time_conv_swap, [PERF_RECORD_HEADER_MAX] = NULL, }; @@ -1069,7 +1093,7 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample) * in "to" register. * For example, there is a call stack * "A"->"B"->"C"->"D". - * The LBR registers will recorde like + * The LBR registers will be recorded like * "C"->"D", "B"->"C", "A"->"B". * So only the first "to" register and all "from" * registers are needed to construct the whole stack. @@ -1302,8 +1326,10 @@ static void dump_sample(struct evsel *evsel, union perf_event *event, if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) { printf("... weight: %" PRIu64 "", sample->weight); - if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) + if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) { printf(",0x%"PRIx16"", sample->ins_lat); + printf(",0x%"PRIx16"", sample->p_stage_cyc); + } printf("\n"); } @@ -1584,7 +1610,7 @@ static s64 perf_session__process_user_event(struct perf_session *session, return tool->event_update(tool, event, &session->evlist); case PERF_RECORD_HEADER_EVENT_TYPE: /* - * Depreceated, but we need to handle it for sake + * Deprecated, but we need to handle it for sake * of old data files create in pipe mode. */ return 0; @@ -2350,7 +2376,8 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp return machines__fprintf_dsos_buildid(&session->machines, fp, skip, parm); } -size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) +size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp, + bool skip_empty) { size_t ret; const char *msg = ""; @@ -2360,7 +2387,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) ret = fprintf(fp, "\nAggregated stats:%s\n", msg); - ret += events_stats__fprintf(&session->evlist->stats, fp); + ret += events_stats__fprintf(&session->evlist->stats, fp, skip_empty); return ret; } diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index f76480166d38..e31ba4c92a6c 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -113,7 +113,8 @@ size_t perf_session__fprintf_dsos(struct perf_session *session, FILE *fp); size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp, bool (fn)(struct dso *dso, int parm), int parm); -size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp); +size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp, + bool skip_empty); struct evsel *perf_session__find_first_evtype(struct perf_session *session, unsigned int type); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 552b590485bf..88ce47f2547e 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -25,6 +25,7 @@ #include <traceevent/event-parse.h> #include "mem-events.h" #include "annotate.h" +#include "event.h" #include "time-utils.h" #include "cgroup.h" #include "machine.h" @@ -36,7 +37,7 @@ const char default_parent_pattern[] = "^sys_|^do_page_fault"; const char *parent_pattern = default_parent_pattern; const char *default_sort_order = "comm,dso,symbol"; const char default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles"; -const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat"; +const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,p_stage_cyc"; const char default_top_sort_order[] = "dso,symbol"; const char default_diff_sort_order[] = "dso,symbol"; const char default_tracepoint_sort_order[] = "trace"; @@ -45,6 +46,8 @@ const char *field_order; regex_t ignore_callees_regex; int have_ignore_callees = 0; enum sort_mode sort__mode = SORT_MODE__NORMAL; +const char *dynamic_headers[] = {"local_ins_lat", "p_stage_cyc"}; +const char *arch_specific_sort_keys[] = {"p_stage_cyc"}; /* * Replaces all occurrences of a char used with the: @@ -1408,6 +1411,25 @@ struct sort_entry sort_global_ins_lat = { .se_width_idx = HISTC_GLOBAL_INS_LAT, }; +static int64_t +sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return left->stat.p_stage_cyc - right->stat.p_stage_cyc; +} + +static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%-*u", width, he->stat.p_stage_cyc); +} + +struct sort_entry sort_p_stage_cyc = { + .se_header = "Pipeline Stage Cycle", + .se_cmp = sort__global_p_stage_cyc_cmp, + .se_snprintf = hist_entry__p_stage_cyc_snprintf, + .se_width_idx = HISTC_P_STAGE_CYC, +}; + struct sort_entry sort_mem_daddr_sym = { .se_header = "Data Symbol", .se_cmp = sort__daddr_cmp, @@ -1816,6 +1838,21 @@ struct sort_dimension { int taken; }; +int __weak arch_support_sort_key(const char *sort_key __maybe_unused) +{ + return 0; +} + +const char * __weak arch_perf_header_entry(const char *se_header) +{ + return se_header; +} + +static void sort_dimension_add_dynamic_header(struct sort_dimension *sd) +{ + sd->entry->se_header = arch_perf_header_entry(sd->entry->se_header); +} + #define DIM(d, n, func) [d] = { .name = n, .entry = &(func) } static struct sort_dimension common_sort_dimensions[] = { @@ -1841,6 +1878,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size), DIM(SORT_LOCAL_INS_LAT, "local_ins_lat", sort_local_ins_lat), DIM(SORT_GLOBAL_INS_LAT, "ins_lat", sort_global_ins_lat), + DIM(SORT_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_p_stage_cyc), }; #undef DIM @@ -2739,7 +2777,20 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok, struct evlist *evlist, int level) { - unsigned int i; + unsigned int i, j; + + /* + * Check to see if there are any arch specific + * sort dimensions not applicable for the current + * architecture. If so, Skip that sort key since + * we don't want to display it in the output fields. + */ + for (j = 0; j < ARRAY_SIZE(arch_specific_sort_keys); j++) { + if (!strcmp(arch_specific_sort_keys[j], tok) && + !arch_support_sort_key(tok)) { + return 0; + } + } for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) { struct sort_dimension *sd = &common_sort_dimensions[i]; @@ -2747,6 +2798,11 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok, if (strncasecmp(tok, sd->name, strlen(tok))) continue; + for (j = 0; j < ARRAY_SIZE(dynamic_headers); j++) { + if (!strcmp(dynamic_headers[j], sd->name)) + sort_dimension_add_dynamic_header(sd); + } + if (sd->entry == &sort_parent) { int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED); if (ret) { diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 63f67a3f3630..87a092645aa7 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -51,6 +51,7 @@ struct he_stat { u64 period_guest_us; u64 weight; u64 ins_lat; + u64 p_stage_cyc; u32 nr_events; }; @@ -234,6 +235,7 @@ enum sort_type { SORT_CODE_PAGE_SIZE, SORT_LOCAL_INS_LAT, SORT_GLOBAL_INS_LAT, + SORT_PIPELINE_STAGE_CYC, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 7f09cdaf5b60..a76fff5e7d83 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -17,6 +17,8 @@ #include "cgroup.h" #include <api/fs/fs.h> #include "util.h" +#include "iostat.h" +#include "pmu-hybrid.h" #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" @@ -310,6 +312,11 @@ static void print_metric_header(struct perf_stat_config *config, struct outstate *os = ctx; char tbuf[1024]; + /* In case of iostat, print metric header for first root port only */ + if (config->iostat_run && + os->evsel->priv != os->evsel->evlist->selected->priv) + return; + if (!valid_only_metric(unit)) return; unit = fixunit(tbuf, os->evsel, unit); @@ -439,6 +446,12 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int if (counter->cgrp) os.nfields++; } + + if (!config->no_csv_summary && config->csv_output && + config->summary && !config->interval) { + fprintf(config->output, "%16s%s", "summary", config->csv_sep); + } + if (run == 0 || ena == 0 || counter->counts->scaled == -1) { if (config->metric_only) { pm(config, &os, NULL, "", "", 0); @@ -526,6 +539,7 @@ static void uniquify_event_name(struct evsel *counter) { char *new_name; char *config; + int ret = 0; if (counter->uniquified_name || !counter->pmu_name || !strncmp(counter->name, counter->pmu_name, @@ -540,8 +554,17 @@ static void uniquify_event_name(struct evsel *counter) counter->name = new_name; } } else { - if (asprintf(&new_name, - "%s [%s]", counter->name, counter->pmu_name) > 0) { + if (perf_pmu__has_hybrid()) { + if (!counter->use_config_name) { + ret = asprintf(&new_name, "%s/%s/", + counter->pmu_name, counter->name); + } + } else { + ret = asprintf(&new_name, "%s [%s]", + counter->name, counter->pmu_name); + } + + if (ret) { free(counter->name); counter->name = new_name; } @@ -644,6 +667,9 @@ static void print_counter_aggrdata(struct perf_stat_config *config, if (!collect_data(config, counter, aggr_cb, &ad)) return; + if (perf_pmu__has_hybrid() && ad.ena == 0) + return; + nr = ad.nr; ena = ad.ena; run = ad.run; @@ -952,8 +978,11 @@ static void print_metric_headers(struct perf_stat_config *config, if (config->csv_output) { if (config->interval) fputs("time,", config->output); - fputs(aggr_header_csv[config->aggr_mode], config->output); + if (!config->iostat_run) + fputs(aggr_header_csv[config->aggr_mode], config->output); } + if (config->iostat_run) + iostat_print_header_prefix(config); /* Print metrics headers only */ evlist__for_each_entry(evlist, counter) { @@ -983,7 +1012,8 @@ static void print_interval(struct perf_stat_config *config, if (config->interval_clear) puts(CONSOLE_CLEAR); - sprintf(prefix, "%6lu.%09lu%s", (unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep); + if (!config->iostat_run) + sprintf(prefix, "%6lu.%09lu%s", (unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep); if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) { switch (config->aggr_mode) { @@ -1019,9 +1049,11 @@ static void print_interval(struct perf_stat_config *config, break; case AGGR_GLOBAL: default: - fprintf(output, "# time"); - if (!metric_only) - fprintf(output, " counts %*s events\n", unit_width, "unit"); + if (!config->iostat_run) { + fprintf(output, "# time"); + if (!metric_only) + fprintf(output, " counts %*s events\n", unit_width, "unit"); + } case AGGR_UNSET: break; } @@ -1214,6 +1246,9 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf struct evsel *counter; char buf[64], *prefix = NULL; + if (config->iostat_run) + evlist->selected = evlist__first(evlist); + if (interval) print_interval(config, evlist, prefix = buf, ts); else @@ -1226,7 +1261,7 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf print_metric_headers(config, evlist, prefix, false); if (num_print_iv++ == 25) num_print_iv = 0; - if (config->aggr_mode == AGGR_GLOBAL && prefix) + if (config->aggr_mode == AGGR_GLOBAL && prefix && !config->iostat_run) fprintf(config->output, "%s", prefix); } @@ -1243,11 +1278,16 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf } break; case AGGR_GLOBAL: - evlist__for_each_entry(evlist, counter) { - print_counter_aggr(config, counter, prefix); + if (config->iostat_run) + iostat_print_counters(evlist, config, ts, prefix = buf, + print_counter_aggr); + else { + evlist__for_each_entry(evlist, counter) { + print_counter_aggr(config, counter, prefix); + } + if (metric_only) + fputc('\n', config->output); } - if (metric_only) - fputc('\n', config->output); break; case AGGR_NONE: if (metric_only) diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 6ccf21a72f06..39967a45f55b 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -9,7 +9,9 @@ #include "expr.h" #include "metricgroup.h" #include "cgroup.h" +#include "units.h" #include <linux/zalloc.h> +#include "iostat.h" /* * AGGR_GLOBAL: Use CPU 0 @@ -961,7 +963,9 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct metric_event *me; int num = 1; - if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { + if (config->iostat_run) { + iostat_print_metric(config, evsel, out); + } else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd); if (total) { @@ -1270,18 +1274,15 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL, evsel->name, evsel->metric_name, NULL, 1, cpu, out, st); } else if (runtime_stat_n(st, STAT_NSECS, cpu, &rsd) != 0) { - char unit = 'M'; - char unit_buf[10]; + char unit = ' '; + char unit_buf[10] = "/sec"; total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd); - if (total) - ratio = 1000.0 * avg / total; - if (ratio < 0.001) { - ratio *= 1000; - unit = 'K'; - } - snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); + ratio = convert_unit_double(1000000000.0 * avg / total, &unit); + + if (unit != ' ') + snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio); } else if (perf_stat_evsel__is(evsel, SMI_NUM)) { print_smi_cost(config, cpu, out, st, &rsd); diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index c400f8dde017..2db46b9bebd0 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -76,8 +76,7 @@ double rel_stddev_stats(double stddev, double avg) return pct; } -bool __perf_evsel_stat__is(struct evsel *evsel, - enum perf_stat_evsel_id id) +bool __perf_stat_evsel__is(struct evsel *evsel, enum perf_stat_evsel_id id) { struct perf_stat_evsel *ps = evsel->stats; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index d85c292148bb..32c8527de347 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -128,10 +128,12 @@ struct perf_stat_config { bool all_user; bool percore_show_thread; bool summary; + bool no_csv_summary; bool metric_no_group; bool metric_no_merge; bool stop_read_counter; bool quiet; + bool iostat_run; FILE *output; unsigned int interval; unsigned int timeout; @@ -160,6 +162,7 @@ struct perf_stat_config { }; void perf_stat__set_big_num(int set); +void perf_stat__set_no_csv_summary(int set); void update_stats(struct stats *stats, u64 val); double avg_stats(struct stats *stats); @@ -187,11 +190,10 @@ struct perf_aggr_thread_value { u64 ena; }; -bool __perf_evsel_stat__is(struct evsel *evsel, - enum perf_stat_evsel_id id); +bool __perf_stat_evsel__is(struct evsel *evsel, enum perf_stat_evsel_id id); #define perf_stat_evsel__is(evsel, id) \ - __perf_evsel_stat__is(evsel, PERF_STAT_EVSEL_ID__ ## id) + __perf_stat_evsel__is(evsel, PERF_STAT_EVSEL_ID__ ## id) extern struct runtime_stat rt_stat; extern struct stats walltime_nsecs_stats; diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h index ea94d8628980..be94d7046fa0 100644 --- a/tools/perf/util/strbuf.h +++ b/tools/perf/util/strbuf.h @@ -12,7 +12,7 @@ * build complex strings/buffers whose final size isn't easily known. * * It is NOT legal to copy the ->buf pointer away. - * `strbuf_detach' is the operation that detachs a buffer from its shell + * `strbuf_detach' is the operation that detaches a buffer from its shell * while keeping the shell valid wrt its invariants. * * 2. the ->buf member is a byte array that has at least ->len + 1 bytes diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h index e0c25a40f796..c05aca9ca582 100644 --- a/tools/perf/util/strfilter.h +++ b/tools/perf/util/strfilter.h @@ -8,8 +8,8 @@ /* A node of string filter */ struct strfilter_node { - struct strfilter_node *l; /* Tree left branche (for &,|) */ - struct strfilter_node *r; /* Tree right branche (for !,&,|) */ + struct strfilter_node *l; /* Tree left branch (for &,|) */ + struct strfilter_node *r; /* Tree right branch (for !,&,|) */ const char *p; /* Operator or rule */ }; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 6dff843fd883..4c56aa837434 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1058,7 +1058,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, curr_dso->symtab_type = dso->symtab_type; maps__insert(kmaps, curr_map); /* - * Add it before we drop the referece to curr_map, i.e. while + * Add it before we drop the reference to curr_map, i.e. while * we still are sure to have a reference to this DSO via * *curr_map->dso. */ diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c index 35c936ce33ef..2664fb65e47a 100644 --- a/tools/perf/util/symbol_fprintf.c +++ b/tools/perf/util/symbol_fprintf.c @@ -68,7 +68,7 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso, for (nd = rb_first_cached(&dso->symbol_names); nd; nd = rb_next(nd)) { pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); - fprintf(fp, "%s\n", pos->sym.name); + ret += fprintf(fp, "%s\n", pos->sym.name); } return ret; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index dff178103ce5..35aa0c0f7cd9 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -1211,7 +1211,7 @@ static size_t mask_size(struct perf_cpu_map *map, int *max) *max = 0; for (i = 0; i < map->nr; i++) { - /* bit possition of the cpu is + 1 */ + /* bit position of the cpu is + 1 */ int bit = map->map[i] + 1; if (bit > *max) @@ -1237,7 +1237,7 @@ void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int * mask = size of 'struct perf_record_record_cpu_map' + * maximum cpu bit converted to size of longs * - * and finaly + the size of 'struct perf_record_cpu_map_data'. + * and finally + the size of 'struct perf_record_cpu_map_data'. */ size_cpus = cpus_size(map); size_mask = mask_size(map, max); diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 03bd99d3be16..a2e906858891 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -34,6 +34,10 @@ static const char **syscalltbl_native = syscalltbl_powerpc_32; #include <asm/syscalls.c> const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID; static const char **syscalltbl_native = syscalltbl_arm64; +#elif defined(__mips__) +#include <asm/syscalls_n64.c> +const int syscalltbl_native_max_id = SYSCALLTBL_MIPS_N64_MAX_ID; +static const char **syscalltbl_native = syscalltbl_mips_n64; #endif struct syscall { diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h index f132c6c2eef8..4ff56217f2a6 100644 --- a/tools/perf/util/target.h +++ b/tools/perf/util/target.h @@ -16,6 +16,8 @@ struct target { bool uses_mmap; bool default_per_cpu; bool per_thread; + bool use_bpf; + const char *attr_map; }; enum target_errno { @@ -64,11 +66,6 @@ static inline bool target__has_cpu(struct target *target) return target->system_wide || target->cpu_list; } -static inline bool target__has_bpf(struct target *target) -{ - return target->bpf_str; -} - static inline bool target__none(struct target *target) { return !target__has_task(target) && !target__has_cpu(target); diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h index 3bc47a42af8e..b3cd09beb62f 100644 --- a/tools/perf/util/thread-stack.h +++ b/tools/perf/util/thread-stack.h @@ -16,7 +16,6 @@ struct comm; struct ip_callchain; struct symbol; struct dso; -struct comm; struct perf_sample; struct addr_location; struct call_path; diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c index 62b4c75c966c..f19791d46e99 100644 --- a/tools/perf/util/tsc.c +++ b/tools/perf/util/tsc.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> +#include <inttypes.h> +#include <string.h> #include <linux/compiler.h> #include <linux/perf_event.h> @@ -110,3 +112,31 @@ u64 __weak rdtsc(void) { return 0; } + +size_t perf_event__fprintf_time_conv(union perf_event *event, FILE *fp) +{ + struct perf_record_time_conv *tc = (struct perf_record_time_conv *)event; + size_t ret; + + ret = fprintf(fp, "\n... Time Shift %" PRI_lu64 "\n", tc->time_shift); + ret += fprintf(fp, "... Time Muliplier %" PRI_lu64 "\n", tc->time_mult); + ret += fprintf(fp, "... Time Zero %" PRI_lu64 "\n", tc->time_zero); + + /* + * The event TIME_CONV was extended for the fields from "time_cycles" + * when supported cap_user_time_short, for backward compatibility, + * prints the extended fields only if they are contained in the event. + */ + if (event_contains(*tc, time_cycles)) { + ret += fprintf(fp, "... Time Cycles %" PRI_lu64 "\n", + tc->time_cycles); + ret += fprintf(fp, "... Time Mask %#" PRI_lx64 "\n", + tc->time_mask); + ret += fprintf(fp, "... Cap Time Zero %" PRId32 "\n", + tc->cap_user_time_zero); + ret += fprintf(fp, "... Cap Time Short %" PRId32 "\n", + tc->cap_user_time_short); + } + + return ret; +} diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h index 72a15419f3b3..7d83a31732a7 100644 --- a/tools/perf/util/tsc.h +++ b/tools/perf/util/tsc.h @@ -4,6 +4,8 @@ #include <linux/types.h> +#include "event.h" + struct perf_tsc_conversion { u16 time_shift; u32 time_mult; @@ -24,4 +26,6 @@ u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc); u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc); u64 rdtsc(void); +size_t perf_event__fprintf_time_conv(union perf_event *event, FILE *fp); + #endif // __PERF_TSC_H diff --git a/tools/perf/util/units.c b/tools/perf/util/units.c index a46762aec4c9..32c39cfe209b 100644 --- a/tools/perf/util/units.c +++ b/tools/perf/util/units.c @@ -33,28 +33,35 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags) return (unsigned long) -1; } -unsigned long convert_unit(unsigned long value, char *unit) +double convert_unit_double(double value, char *unit) { *unit = ' '; - if (value > 1000) { - value /= 1000; + if (value > 1000.0) { + value /= 1000.0; *unit = 'K'; } - if (value > 1000) { - value /= 1000; + if (value > 1000.0) { + value /= 1000.0; *unit = 'M'; } - if (value > 1000) { - value /= 1000; + if (value > 1000.0) { + value /= 1000.0; *unit = 'G'; } return value; } +unsigned long convert_unit(unsigned long value, char *unit) +{ + double v = convert_unit_double((double)value, unit); + + return (unsigned long)v; +} + int unit_number__scnprintf(char *buf, size_t size, u64 n) { char unit[4] = "BKMG"; diff --git a/tools/perf/util/units.h b/tools/perf/util/units.h index 99263b6a23f7..ea43e74e3240 100644 --- a/tools/perf/util/units.h +++ b/tools/perf/util/units.h @@ -12,6 +12,7 @@ struct parse_tag { unsigned long parse_tag_value(const char *str, struct parse_tag *tags); +double convert_unit_double(double value, char *unit); unsigned long convert_unit(unsigned long value, char *unit); int unit_number__scnprintf(char *buf, size_t size, u64 n); diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 9aededc0bc06..71a353349181 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -82,7 +82,7 @@ UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug, #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: +/* Flags intentionally 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 |