diff options
Diffstat (limited to 'tools/perf/util/evsel.c')
| -rw-r--r-- | tools/perf/util/evsel.c | 862 |
1 files changed, 693 insertions, 169 deletions
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index bc144388f892..2ee87fd84d3e 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -34,6 +34,7 @@ #include "callchain.h" #include "cgroup.h" #include "counts.h" +#include "dwarf-regs.h" #include "event.h" #include "evsel.h" #include "time-utils.h" @@ -48,6 +49,7 @@ #include "record.h" #include "debug.h" #include "trace-event.h" +#include "session.h" #include "stat.h" #include "string2.h" #include "memswap.h" @@ -56,8 +58,10 @@ #include "off_cpu.h" #include "pmu.h" #include "pmus.h" +#include "drm_pmu.h" #include "hwmon_pmu.h" #include "tool_pmu.h" +#include "tp_pmu.h" #include "rlimit.h" #include "../perf-sys.h" #include "util/parse-branch-options.h" @@ -237,6 +241,16 @@ set_methods: return 0; } +const char *evsel__pmu_name(const struct evsel *evsel) +{ + struct perf_pmu *pmu = evsel__find_pmu(evsel); + + if (pmu) + return pmu->name; + + return event_type(evsel->core.attr.type); +} + #define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) int __evsel__sample_size(u64 sample_type) @@ -389,11 +403,11 @@ void evsel__init(struct evsel *evsel, evsel->sample_size = __evsel__sample_size(attr->sample_type); evsel__calc_id_pos(evsel); evsel->cmdline_group_boundary = false; - evsel->metric_events = NULL; evsel->per_pkg_mask = NULL; evsel->collect_stat = false; evsel->group_pmu_name = NULL; evsel->skippable = false; + evsel->supported = true; evsel->alternate_hw_config = PERF_COUNT_HW_MAX; evsel->script_output_type = -1; // FIXME: OUTPUT_TYPE_UNSET, see builtin-script.c } @@ -477,7 +491,7 @@ struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig) return NULL; evsel->core.cpus = perf_cpu_map__get(orig->core.cpus); - evsel->core.own_cpus = perf_cpu_map__get(orig->core.own_cpus); + evsel->core.pmu_cpus = perf_cpu_map__get(orig->core.pmu_cpus); evsel->core.threads = perf_thread_map__get(orig->core.threads); evsel->core.nr_members = orig->core.nr_members; evsel->core.system_wide = orig->core.system_wide; @@ -511,10 +525,21 @@ struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig) } evsel->cgrp = cgroup__get(orig->cgrp); #ifdef HAVE_LIBTRACEEVENT + if (orig->tp_sys) { + evsel->tp_sys = strdup(orig->tp_sys); + if (evsel->tp_sys == NULL) + goto out_err; + } + if (orig->tp_name) { + evsel->tp_name = strdup(orig->tp_name); + if (evsel->tp_name == NULL) + goto out_err; + } evsel->tp_format = orig->tp_format; #endif evsel->handler = orig->handler; evsel->core.leader = orig->core.leader; + evsel->metric_leader = orig->metric_leader; evsel->max_events = orig->max_events; zfree(&evsel->unit); @@ -532,11 +557,11 @@ struct evsel *evsel__clone(struct evsel *dest, struct evsel *orig) evsel->exclude_GH = orig->exclude_GH; evsel->sample_read = orig->sample_read; - evsel->auto_merge_stats = orig->auto_merge_stats; evsel->collect_stat = orig->collect_stat; evsel->weak_group = orig->weak_group; evsel->use_config_name = orig->use_config_name; evsel->pmu = orig->pmu; + evsel->first_wildcard_match = orig->first_wildcard_match; if (evsel__copy_config_terms(evsel, orig) < 0) goto out_err; @@ -550,24 +575,6 @@ out_err: return NULL; } -static int trace_event__id(const char *sys, const char *name) -{ - char *tp_dir = get_events_file(sys); - char path[PATH_MAX]; - int id, err; - - if (!tp_dir) - return -1; - - scnprintf(path, PATH_MAX, "%s/%s/id", tp_dir, name); - put_events_file(tp_dir); - err = filename__read_int(path, &id); - if (err) - return err; - - return id; -} - /* * Returns pointer with encoded error via <linux/err.h> interface. */ @@ -601,7 +608,7 @@ struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx, bool event_attr_init(&attr); if (format) { - id = trace_event__id(sys, name); + id = tp_pmu__id(sys, name); if (id < 0) { err = id; goto out_free; @@ -634,12 +641,17 @@ struct tep_event *evsel__tp_format(struct evsel *evsel) if (evsel->core.attr.type != PERF_TYPE_TRACEPOINT) return NULL; - tp_format = trace_event__tp_format(evsel->tp_sys, evsel->tp_name); + if (!evsel->tp_sys) + tp_format = trace_event__tp_format_id(evsel->core.attr.config); + else + tp_format = trace_event__tp_format(evsel->tp_sys, evsel->tp_name); + if (IS_ERR(tp_format)) { int err = -PTR_ERR(evsel->tp_format); - pr_err("Error getting tracepoint format '%s' '%s'(%d)\n", - evsel__name(evsel), strerror(err), err); + errno = err; + pr_err("Error getting tracepoint format '%s': %m\n", + evsel__name(evsel)); return NULL; } evsel->tp_format = tp_format; @@ -914,7 +926,8 @@ const char *evsel__name(struct evsel *evsel) break; case PERF_TYPE_TRACEPOINT: - scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint"); + scnprintf(bf, sizeof(bf), "unknown tracepoint id=%#"PRIx64, + evsel->core.attr.config); break; case PERF_TYPE_BREAKPOINT: @@ -926,8 +939,8 @@ const char *evsel__name(struct evsel *evsel) break; default: - scnprintf(bf, sizeof(bf), "unknown attr type: %d", - evsel->core.attr.type); + scnprintf(bf, sizeof(bf), "unknown event PMU=%d config=%#"PRIx64, + evsel->core.attr.type, evsel->core.attr.config); break; } @@ -996,12 +1009,24 @@ int evsel__group_desc(struct evsel *evsel, char *buf, size_t size) return ret; } -static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, - struct callchain_param *param) +uint16_t evsel__e_machine(struct evsel *evsel, uint32_t *e_flags) +{ + struct perf_session *session = evsel__session(evsel); + + return perf_session__e_machine(session, e_flags); +} + +static void __evsel__config_callchain(struct evsel *evsel, const struct record_opts *opts, + const struct callchain_param *param) { bool function = evsel__is_function_event(evsel); struct perf_event_attr *attr = &evsel->core.attr; + if (EM_HOST == EM_S390 && param->record_mode == CALLCHAIN_FP) { + pr_warning_once( + "Framepointer unwinding lacks kernel support. Use '--call-graph dwarf'\n"); + } + evsel__set_sample_bit(evsel, CALLCHAIN); attr->sample_max_stack = param->max_stack; @@ -1031,18 +1056,18 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o if (param->record_mode == CALLCHAIN_DWARF) { if (!function) { - const char *arch = perf_env__arch(evsel__env(evsel)); + uint16_t e_machine = evsel__e_machine(evsel, /*e_flags=*/NULL); evsel__set_sample_bit(evsel, REGS_USER); evsel__set_sample_bit(evsel, STACK_USER); if (opts->sample_user_regs && - DWARF_MINIMAL_REGS(arch) != arch__user_reg_mask()) { - attr->sample_regs_user |= DWARF_MINIMAL_REGS(arch); + DWARF_MINIMAL_REGS(e_machine) != perf_user_reg_mask(EM_HOST)) { + attr->sample_regs_user |= DWARF_MINIMAL_REGS(e_machine); pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, " "specifying a subset with --user-regs may render DWARF unwinding unreliable, " "so the minimal registers set (IP, SP) is explicitly forced.\n"); } else { - attr->sample_regs_user |= arch__user_reg_mask(); + attr->sample_regs_user |= perf_user_reg_mask(EM_HOST); } attr->sample_stack_user = param->dump_size; attr->exclude_callchain_user = 1; @@ -1056,16 +1081,19 @@ static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *o pr_info("Disabling user space callchains for function trace event.\n"); attr->exclude_callchain_user = 1; } + + if (param->defer && !attr->exclude_callchain_user) + attr->defer_callchain = 1; } -void evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, - struct callchain_param *param) +void evsel__config_callchain(struct evsel *evsel, const struct record_opts *opts, + const struct callchain_param *param) { if (param->enabled) return __evsel__config_callchain(evsel, opts, param); } -static void evsel__reset_callgraph(struct evsel *evsel, struct callchain_param *param) +static void evsel__reset_callgraph(struct evsel *evsel, const struct callchain_param *param) { struct perf_event_attr *attr = &evsel->core.attr; @@ -1082,8 +1110,73 @@ static void evsel__reset_callgraph(struct evsel *evsel, struct callchain_param * } } +static void evsel__apply_ratio_to_prev(struct evsel *evsel, + struct perf_event_attr *attr, + const struct record_opts *opts, + const char *buf) +{ + struct perf_event_attr *prev_attr = NULL; + struct evsel *evsel_prev = NULL; + u64 type = evsel->core.attr.sample_type; + u64 prev_type = 0; + double rtp; + + rtp = strtod(buf, NULL); + if (rtp <= 0) { + pr_err("Invalid ratio-to-prev value %lf\n", rtp); + return; + } + if (evsel == evsel__leader(evsel)) { + pr_err("Invalid use of ratio-to-prev term without preceding element in group\n"); + return; + } + if (!evsel->pmu->is_core) { + pr_err("Event using ratio-to-prev term must have a core PMU\n"); + return; + } + + evsel_prev = evsel__prev(evsel); + if (!evsel_prev) { + pr_err("Previous event does not exist.\n"); + return; + } + + if (evsel_prev->pmu->type != evsel->pmu->type) { + pr_err("Compared events (\"%s\", \"%s\") must have same PMU\n", + evsel->name, evsel_prev->name); + return; + } + + prev_attr = &evsel_prev->core.attr; + prev_type = evsel_prev->core.attr.sample_type; + + if (!(prev_type & PERF_SAMPLE_PERIOD)) { + attr->sample_period = prev_attr->sample_period * rtp; + attr->freq = 0; + evsel__reset_sample_bit(evsel, PERIOD); + } else if (!(type & PERF_SAMPLE_PERIOD)) { + prev_attr->sample_period = attr->sample_period / rtp; + prev_attr->freq = 0; + evsel__reset_sample_bit(evsel_prev, PERIOD); + } else { + if (opts->user_interval != ULLONG_MAX) { + prev_attr->sample_period = opts->user_interval; + attr->sample_period = prev_attr->sample_period * rtp; + prev_attr->freq = 0; + attr->freq = 0; + evsel__reset_sample_bit(evsel_prev, PERIOD); + evsel__reset_sample_bit(evsel, PERIOD); + } else { + pr_err("Event period term or count (-c) must be set when using ratio-to-prev term.\n"); + return; + } + } + + arch_evsel__apply_ratio_to_prev(evsel, attr); +} + static void evsel__apply_config_terms(struct evsel *evsel, - struct record_opts *opts, bool track) + const struct record_opts *opts, bool track) { struct evsel_config_term *term; struct list_head *config_terms = &evsel->config_terms; @@ -1095,6 +1188,7 @@ static void evsel__apply_config_terms(struct evsel *evsel, u32 dump_size = 0; int max_stack = 0; const char *callgraph_buf = NULL; + const char *rtp_buf = NULL; list_for_each_entry(term, config_terms, list) { switch (term->type) { @@ -1163,7 +1257,14 @@ static void evsel__apply_config_terms(struct evsel *evsel, case EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE: /* Already applied by auxtrace */ break; - case EVSEL__CONFIG_TERM_CFG_CHG: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG1: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG2: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG3: + case EVSEL__CONFIG_TERM_USR_CHG_CONFIG4: + break; + case EVSEL__CONFIG_TERM_RATIO_TO_PREV: + rtp_buf = term->val.str; break; default: break; @@ -1216,6 +1317,8 @@ static void evsel__apply_config_terms(struct evsel *evsel, evsel__config_callchain(evsel, opts, ¶m); } } + if (rtp_buf) + evsel__apply_ratio_to_prev(evsel, attr, opts, rtp_buf); } struct evsel_config_term *__evsel__get_config_term(struct evsel *evsel, enum evsel_term_type type) @@ -1230,6 +1333,109 @@ struct evsel_config_term *__evsel__get_config_term(struct evsel *evsel, enum evs return found_term; } +/* + * Set @config_name to @val as long as the user hasn't already set or cleared it + * by passing a config term on the command line. + * + * @val is the value to put into the bits specified by @config_name rather than + * the bit pattern. It is shifted into position by this function, so to set + * something to true, pass 1 for val rather than a pre shifted value. + */ +void evsel__set_config_if_unset(struct evsel *evsel, const char *config_name, + u64 val) +{ + u64 user_bits = 0; + struct evsel_config_term *term = evsel__get_config_term(evsel, + USR_CHG_CONFIG); + struct perf_pmu_format *format = pmu_find_format(&evsel->pmu->format, + config_name); + int fbit; + __u64 *vp; + + if (!format) + return; + + switch (format->value) { + case PERF_PMU_FORMAT_VALUE_CONFIG: + term = evsel__get_config_term(evsel, USR_CHG_CONFIG); + vp = &evsel->core.attr.config; + break; + case PERF_PMU_FORMAT_VALUE_CONFIG1: + term = evsel__get_config_term(evsel, USR_CHG_CONFIG1); + vp = &evsel->core.attr.config1; + break; + case PERF_PMU_FORMAT_VALUE_CONFIG2: + term = evsel__get_config_term(evsel, USR_CHG_CONFIG2); + vp = &evsel->core.attr.config2; + break; + case PERF_PMU_FORMAT_VALUE_CONFIG3: + term = evsel__get_config_term(evsel, USR_CHG_CONFIG3); + vp = &evsel->core.attr.config3; + break; + case PERF_PMU_FORMAT_VALUE_CONFIG4: + term = evsel__get_config_term(evsel, USR_CHG_CONFIG4); + vp = &evsel->core.attr.config4; + break; + default: + pr_err("Unknown format value: %d\n", format->value); + return; + } + + if (!format) + return; + + if (term) + user_bits = term->val.cfg_chg; + + /* Do nothing if the user changed the value */ + for_each_set_bit(fbit, format->bits, PERF_PMU_FORMAT_BITS) + if ((1ULL << fbit) & user_bits) + return; + + /* Otherwise replace it */ + perf_pmu__format_pack(format->bits, val, vp, /*zero=*/true); +} + + +int evsel__get_config_val(const struct evsel *evsel, const char *config_name, + u64 *val) +{ + struct perf_pmu_format *format = pmu_find_format(&evsel->pmu->format, config_name); + + if (!format || bitmap_empty(format->bits, PERF_PMU_FORMAT_BITS)) { + pr_err("Unknown/empty format name: %s\n", config_name); + *val = 0; + return -EINVAL; + } + + switch (format->value) { + case PERF_PMU_FORMAT_VALUE_CONFIG: + *val = perf_pmu__format_unpack(format->bits, + evsel->core.attr.config); + return 0; + case PERF_PMU_FORMAT_VALUE_CONFIG1: + *val = perf_pmu__format_unpack(format->bits, + evsel->core.attr.config1); + return 0; + case PERF_PMU_FORMAT_VALUE_CONFIG2: + *val = perf_pmu__format_unpack(format->bits, + evsel->core.attr.config2); + return 0; + case PERF_PMU_FORMAT_VALUE_CONFIG3: + *val = perf_pmu__format_unpack(format->bits, + evsel->core.attr.config3); + return 0; + case PERF_PMU_FORMAT_VALUE_CONFIG4: + *val = perf_pmu__format_unpack(format->bits, + evsel->core.attr.config4); + return 0; + default: + pr_err("Unknown format value: %d\n", format->value); + *val = 0; + return -EINVAL; + } +} + void __weak arch_evsel__set_sample_weight(struct evsel *evsel) { evsel__set_sample_bit(evsel, WEIGHT); @@ -1240,7 +1446,12 @@ void __weak arch__post_evsel_config(struct evsel *evsel __maybe_unused, { } -static void evsel__set_default_freq_period(struct record_opts *opts, +void __weak arch_evsel__apply_ratio_to_prev(struct evsel *evsel __maybe_unused, + struct perf_event_attr *attr __maybe_unused) +{ +} + +static void evsel__set_default_freq_period(const struct record_opts *opts, struct perf_event_attr *attr) { if (opts->freq) { @@ -1251,9 +1462,10 @@ static void evsel__set_default_freq_period(struct record_opts *opts, } } -static bool evsel__is_offcpu_event(struct evsel *evsel) +bool evsel__is_offcpu_event(struct evsel *evsel) { - return evsel__is_bpf_output(evsel) && evsel__name_is(evsel, OFFCPU_EVENT); + return evsel__is_bpf_output(evsel) && evsel__name_is(evsel, OFFCPU_EVENT) && + evsel->core.attr.sample_type & PERF_SAMPLE_RAW; } /* @@ -1284,8 +1496,8 @@ static bool evsel__is_offcpu_event(struct evsel *evsel) * enable/disable events specifically, as there's no * initial traced exec call. */ -void evsel__config(struct evsel *evsel, struct record_opts *opts, - struct callchain_param *callchain) +void evsel__config(struct evsel *evsel, const struct record_opts *opts, + const struct callchain_param *callchain) { struct evsel *leader = evsel__leader(evsel); struct perf_event_attr *attr = &evsel->core.attr; @@ -1355,10 +1567,11 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, attr->inherit_stat = 1; } - if (opts->sample_address) { + if (opts->sample_address) evsel__set_sample_bit(evsel, ADDR); + + if (opts->record_data_mmap) attr->mmap_data = track; - } /* * We don't allow user space callchains for function trace @@ -1401,7 +1614,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, evsel__set_sample_bit(evsel, CPU); } - if (opts->sample_address) + if (opts->sample_data_src) evsel__set_sample_bit(evsel, DATA_SRC); if (opts->sample_phys_addr) @@ -1416,14 +1629,16 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, attr->branch_sample_type = opts->branch_stack; } - if (opts->sample_weight) + if (opts->sample_weight || evsel->retire_lat) { arch_evsel__set_sample_weight(evsel); - + evsel->retire_lat = false; + } attr->task = track; attr->mmap = track; attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; attr->build_id = track && opts->build_id; + attr->defer_output = track && callchain && callchain->defer; /* * ksymbol is tracked separately with text poke because it needs to be @@ -1500,7 +1715,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, attr->exclude_user = 1; } - if (evsel->core.own_cpus || evsel->unit) + if (evsel->core.pmu_cpus || evsel->unit) evsel->core.attr.read_format |= PERF_FORMAT_ID; /* @@ -1530,8 +1745,10 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, if (evsel__is_dummy_event(evsel)) evsel__reset_sample_bit(evsel, BRANCH_STACK); - if (evsel__is_offcpu_event(evsel)) + if (evsel__is_offcpu_event(evsel)) { evsel->core.attr.sample_type &= OFFCPU_SAMPLE_TYPES; + attr->inherit = 0; + } arch__post_evsel_config(evsel, attr); } @@ -1628,10 +1845,21 @@ static void evsel__free_config_terms(struct evsel *evsel) free_config_terms(&evsel->config_terms); } +static void (*evsel__priv_destructor)(void *priv); + +void evsel__set_priv_destructor(void (*destructor)(void *priv)) +{ + assert(evsel__priv_destructor == NULL); + + evsel__priv_destructor = destructor; +} + void evsel__exit(struct evsel *evsel) { assert(list_empty(&evsel->core.node)); assert(evsel->evlist == NULL); + if (evsel__is_retire_lat(evsel)) + evsel__tpebs_close(evsel); bpf_counter__destroy(evsel); perf_bpf_filter__destroy(evsel); evsel__free_counts(evsel); @@ -1639,9 +1867,7 @@ void evsel__exit(struct evsel *evsel) perf_evsel__free_id(&evsel->core); evsel__free_config_terms(evsel); cgroup__put(evsel->cgrp); - perf_cpu_map__put(evsel->core.cpus); - perf_cpu_map__put(evsel->core.own_cpus); - perf_thread_map__put(evsel->core.threads); + perf_evsel__exit(&evsel->core); zfree(&evsel->group_name); zfree(&evsel->name); #ifdef HAVE_LIBTRACEEVENT @@ -1655,7 +1881,8 @@ void evsel__exit(struct evsel *evsel) evsel__zero_per_pkg(evsel); hashmap__free(evsel->per_pkg_mask); evsel->per_pkg_mask = NULL; - zfree(&evsel->metric_events); + if (evsel__priv_destructor) + evsel__priv_destructor(evsel->priv); perf_evsel__object.fini(evsel); if (evsel__tool_event(evsel) == TOOL_PMU__EVENT_SYSTEM_TIME || evsel__tool_event(evsel) == TOOL_PMU__EVENT_USER_TIME) @@ -1694,11 +1921,6 @@ static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread) return perf_evsel__read(&evsel->core, cpu_map_idx, thread, count); } -static int evsel__read_retire_lat(struct evsel *evsel, int cpu_map_idx, int thread) -{ - return tpebs_set_evsel(evsel, cpu_map_idx, thread); -} - static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread, u64 val, u64 ena, u64 run, u64 lost) { @@ -1706,8 +1928,8 @@ static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread, count = perf_counts(counter->counts, cpu_map_idx, thread); - if (counter->retire_lat) { - evsel__read_retire_lat(counter, cpu_map_idx, thread); + if (evsel__is_retire_lat(counter)) { + evsel__tpebs_read(counter, cpu_map_idx, thread); perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true); return; } @@ -1844,16 +2066,19 @@ bool __evsel__match(const struct evsel *evsel, u32 type, u64 config) u32 e_type = evsel->core.attr.type; u64 e_config = evsel->core.attr.config; - if (e_type != type) { - return type == PERF_TYPE_HARDWARE && evsel->pmu && evsel->pmu->is_core && - evsel->alternate_hw_config == config; - } - - if ((type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE) && - perf_pmus__supports_extended_type()) + if (e_type == type && e_config == config) + return true; + if (type != PERF_TYPE_HARDWARE && type != PERF_TYPE_HW_CACHE) + return false; + if ((e_type == PERF_TYPE_HARDWARE || e_type == PERF_TYPE_HW_CACHE) && + perf_pmus__supports_extended_type()) e_config &= PERF_HW_EVENT_MASK; - - return e_config == config; + if (e_type == type && e_config == config) + return true; + if (type == PERF_TYPE_HARDWARE && evsel->pmu && evsel->pmu->is_core && + evsel->alternate_hw_config == config) + return true; + return false; } int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread) @@ -1864,8 +2089,11 @@ int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread) if (evsel__is_hwmon(evsel)) return evsel__hwmon_pmu_read(evsel, cpu_map_idx, thread); + if (evsel__is_drm(evsel)) + return evsel__drm_pmu_read(evsel, cpu_map_idx, thread); + if (evsel__is_retire_lat(evsel)) - return evsel__read_retire_lat(evsel, cpu_map_idx, thread); + return evsel__tpebs_read(evsel, cpu_map_idx, thread); if (evsel->core.attr.read_format & PERF_FORMAT_GROUP) return evsel__read_group(evsel, cpu_map_idx, thread); @@ -1919,7 +2147,7 @@ static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) struct evsel *leader = evsel__leader(evsel); int fd; - if (evsel__is_group_leader(evsel)) + if (!evsel->supported || evsel__is_group_leader(evsel)) return -1; /* @@ -1933,7 +2161,7 @@ static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) return -1; fd = FD(leader, cpu_map_idx, thread); - BUG_ON(fd == -1 && !leader->skippable); + BUG_ON(fd == -1 && leader->supported); /* * When the leader has been skipped, return -2 to distinguish from no @@ -2099,6 +2327,10 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, static void evsel__disable_missing_features(struct evsel *evsel) { + if (perf_missing_features.defer_callchain && evsel->core.attr.defer_callchain) + evsel->core.attr.defer_callchain = 0; + if (perf_missing_features.defer_callchain && evsel->core.attr.defer_output) + evsel->core.attr.defer_output = 0; if (perf_missing_features.inherit_sample_read && evsel->core.attr.inherit && (evsel->core.attr.sample_type & PERF_SAMPLE_READ)) evsel->core.attr.inherit = 0; @@ -2373,8 +2605,15 @@ static bool evsel__detect_missing_features(struct evsel *evsel, struct perf_cpu /* Please add new feature detection here. */ + attr.defer_callchain = true; + if (has_attr_feature(&attr, /*flags=*/0)) + goto found; + perf_missing_features.defer_callchain = true; + pr_debug2("switching off deferred callchain support\n"); + attr.defer_callchain = false; + attr.inherit = true; - attr.sample_type = PERF_SAMPLE_READ; + attr.sample_type = PERF_SAMPLE_READ | PERF_SAMPLE_TID; if (has_attr_feature(&attr, /*flags=*/0)) goto found; perf_missing_features.inherit_sample_read = true; @@ -2484,6 +2723,10 @@ found: errno = old_errno; check: + if ((evsel->core.attr.defer_callchain || evsel->core.attr.defer_output) && + perf_missing_features.defer_callchain) + return true; + if (evsel->core.attr.inherit && (evsel->core.attr.sample_type & PERF_SAMPLE_READ) && perf_missing_features.inherit_sample_read) @@ -2542,25 +2785,6 @@ check: return false; } -static bool evsel__handle_error_quirks(struct evsel *evsel, int error) -{ - /* - * AMD core PMU tries to forward events with precise_ip to IBS PMU - * implicitly. But IBS PMU has more restrictions so it can fail with - * supported event attributes. Let's forward it back to the core PMU - * by clearing precise_ip only if it's from precise_max (:P). - */ - if ((error == -EINVAL || error == -ENOENT) && x86__is_amd_cpu() && - evsel->core.attr.precise_ip && evsel->precise_max) { - evsel->core.attr.precise_ip = 0; - pr_debug2_peo("removing precise_ip on AMD\n"); - display_attr(&evsel->core.attr); - return true; - } - - return false; -} - static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads, int start_cpu_map_idx, int end_cpu_map_idx) @@ -2570,12 +2794,14 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, enum rlimit_action set_rlimit = NO_CHANGE; struct perf_cpu cpu; - if (evsel__is_retire_lat(evsel)) - return tpebs_start(evsel->evlist); + if (evsel__is_retire_lat(evsel)) { + err = evsel__tpebs_open(evsel); + goto out; + } err = __evsel__prepare_open(evsel, cpus, threads); if (err) - return err; + goto out; if (cpus == NULL) cpus = empty_cpu_map; @@ -2595,14 +2821,22 @@ fallback_missing_features: display_attr(&evsel->core.attr); if (evsel__is_tool(evsel)) { - return evsel__tool_pmu_open(evsel, threads, + err = evsel__tool_pmu_open(evsel, threads, + start_cpu_map_idx, + end_cpu_map_idx); + goto out; + } + if (evsel__is_hwmon(evsel)) { + err = evsel__hwmon_pmu_open(evsel, threads, start_cpu_map_idx, end_cpu_map_idx); + goto out; } - if (evsel__is_hwmon(evsel)) { - return evsel__hwmon_pmu_open(evsel, threads, - start_cpu_map_idx, - end_cpu_map_idx); + if (evsel__is_drm(evsel)) { + err = evsel__drm_pmu_open(evsel, threads, + start_cpu_map_idx, + end_cpu_map_idx); + goto out; } for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) { @@ -2660,8 +2894,8 @@ retry_open: PERF_EVENT_IOC_SET_BPF, bpf_fd); if (err && errno != EEXIST) { - pr_err("failed to attach bpf fd %d: %s\n", - bpf_fd, strerror(errno)); + pr_err("failed to attach bpf fd %d: %m\n", + bpf_fd); err = -EINVAL; goto out_close; } @@ -2681,7 +2915,8 @@ retry_open: } } - return 0; + err = 0; + goto out; try_fallback: if (evsel__ignore_missing_thread(evsel, perf_cpu_map__nr(cpus), @@ -2706,9 +2941,6 @@ try_fallback: if (evsel__precise_ip_fallback(evsel)) goto retry_open; - if (evsel__handle_error_quirks(evsel, err)) - goto retry_open; - out_close: if (err) threads->err_thread = thread; @@ -2723,6 +2955,9 @@ out_close: thread = nthreads; } while (--idx >= 0); errno = old_errno; +out: + if (err) + evsel->supported = false; return err; } @@ -2735,22 +2970,37 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, void evsel__close(struct evsel *evsel) { if (evsel__is_retire_lat(evsel)) - tpebs_delete(); + evsel__tpebs_close(evsel); perf_evsel__close(&evsel->core); perf_evsel__free_id(&evsel->core); } -int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx) +int evsel__open_per_cpu_and_thread(struct evsel *evsel, + struct perf_cpu_map *cpus, int cpu_map_idx, + struct perf_thread_map *threads) { if (cpu_map_idx == -1) - return evsel__open_cpu(evsel, cpus, NULL, 0, perf_cpu_map__nr(cpus)); + return evsel__open_cpu(evsel, cpus, threads, 0, perf_cpu_map__nr(cpus)); + + return evsel__open_cpu(evsel, cpus, threads, cpu_map_idx, cpu_map_idx + 1); +} - return evsel__open_cpu(evsel, cpus, NULL, cpu_map_idx, cpu_map_idx + 1); +int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx) +{ + struct perf_thread_map *threads = thread_map__new_by_tid(-1); + int ret = evsel__open_per_cpu_and_thread(evsel, cpus, cpu_map_idx, threads); + + perf_thread_map__put(threads); + return ret; } int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads) { - return evsel__open(evsel, NULL, threads); + struct perf_cpu_map *cpus = perf_cpu_map__new_any_cpu(); + int ret = evsel__open_per_cpu_and_thread(evsel, cpus, -1, threads); + + perf_cpu_map__put(cpus); + return ret; } static int perf_evsel__parse_id_sample(const struct evsel *evsel, @@ -2823,7 +3073,7 @@ static inline bool overflow(const void *endp, u16 max_size, const void *offset, #define OVERFLOW_CHECK(offset, size, max_size) \ do { \ if (overflow(endp, (max_size), (offset), (size))) \ - return -EFAULT; \ + goto out_efault; \ } while (0) #define OVERFLOW_CHECK_u64(offset) \ @@ -2843,11 +3093,18 @@ perf_event__check_size(union perf_event *event, unsigned int sample_size) return 0; } -void __weak arch_perf_parse_sample_weight(struct perf_sample *data, - const __u64 *array, - u64 type __maybe_unused) +static void perf_parse_sample_weight(struct perf_sample *data, const __u64 *array, u64 type) { - data->weight = *array; + union perf_sample_weight weight; + + weight.full = *array; + if (type & PERF_SAMPLE_WEIGHT_STRUCT) { + data->weight = weight.var1_dw; + data->ins_lat = weight.var2_w; + data->weight3 = weight.var3_w; + } else { + data->weight = weight.full; + } } u64 evsel__bitfield_swap_branch_flags(u64 value) @@ -2921,6 +3178,37 @@ static inline bool evsel__has_branch_counters(const struct evsel *evsel) return false; } +static int __set_offcpu_sample(struct perf_sample *data) +{ + u64 *array = data->raw_data; + u32 max_size = data->raw_size, *p32; + const void *endp = (void *)array + max_size; + + if (array == NULL) + return -EFAULT; + + OVERFLOW_CHECK_u64(array); + p32 = (void *)array++; + data->pid = p32[0]; + data->tid = p32[1]; + + OVERFLOW_CHECK_u64(array); + data->period = *array++; + + OVERFLOW_CHECK_u64(array); + data->callchain = (struct ip_callchain *)array++; + OVERFLOW_CHECK(array, data->callchain->nr * sizeof(u64), max_size); + data->ip = data->callchain->ips[1]; + array += data->callchain->nr; + + OVERFLOW_CHECK_u64(array); + data->cgroup = *array; + + return 0; +out_efault: + return -EFAULT; +} + int evsel__parse_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *data) { @@ -2937,7 +3225,8 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, */ union u64_swap u; - memset(data, 0, sizeof(*data)); + perf_sample__init(data, /*all=*/true); + data->evsel = evsel; data->cpu = data->pid = data->tid = -1; data->stream_id = data->id = data->time = -1ULL; data->period = evsel->core.attr.sample_period; @@ -2946,16 +3235,31 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, data->data_src = PERF_MEM_DATA_SRC_NONE; data->vcpu = -1; + if (event->header.type == PERF_RECORD_CALLCHAIN_DEFERRED) { + const u64 max_callchain_nr = UINT64_MAX / sizeof(u64); + + data->callchain = (struct ip_callchain *)&event->callchain_deferred.nr; + if (data->callchain->nr > max_callchain_nr) + goto out_efault; + + data->deferred_cookie = event->callchain_deferred.cookie; + + if (evsel->core.attr.sample_id_all) + perf_evsel__parse_id_sample(evsel, event, data); + + return 0; + } + if (event->header.type != PERF_RECORD_SAMPLE) { - if (!evsel->core.attr.sample_id_all) - return 0; - return perf_evsel__parse_id_sample(evsel, event, data); + if (evsel->core.attr.sample_id_all) + perf_evsel__parse_id_sample(evsel, event, data); + return 0; } array = event->sample.array; if (perf_event__check_size(event, evsel->sample_size)) - return -EFAULT; + goto out_efault; if (type & PERF_SAMPLE_IDENTIFIER) { data->id = *array; @@ -3048,7 +3352,7 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, sizeof(struct sample_read_value); if (data->read.group.nr > max_group_nr) - return -EFAULT; + goto out_efault; sz = data->read.group.nr * sample_read_value_size(read_format); OVERFLOW_CHECK(array, sz, max_size); @@ -3070,12 +3374,25 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, if (type & PERF_SAMPLE_CALLCHAIN) { const u64 max_callchain_nr = UINT64_MAX / sizeof(u64); + u64 callchain_nr; OVERFLOW_CHECK_u64(array); data->callchain = (struct ip_callchain *)array++; - if (data->callchain->nr > max_callchain_nr) - return -EFAULT; - sz = data->callchain->nr * sizeof(u64); + callchain_nr = data->callchain->nr; + if (callchain_nr > max_callchain_nr) + goto out_efault; + sz = callchain_nr * sizeof(u64); + /* + * Save the cookie for the deferred user callchain. The last 2 + * entries in the callchain should be the context marker and the + * cookie. The cookie will be used to match PERF_RECORD_ + * CALLCHAIN_DEFERRED later. + */ + if (evsel->core.attr.defer_callchain && callchain_nr >= 2 && + data->callchain->ips[callchain_nr - 2] == PERF_CONTEXT_USER_DEFERRED) { + data->deferred_cookie = data->callchain->ips[callchain_nr - 1]; + data->deferred_callchain = true; + } OVERFLOW_CHECK(array, sz, max_size); array = (void *)array + sz; } @@ -3121,7 +3438,7 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, data->branch_stack = (struct branch_stack *)array++; if (data->branch_stack->nr > max_branch_nr) - return -EFAULT; + goto out_efault; sz = data->branch_stack->nr * sizeof(struct branch_entry); if (evsel__has_branch_hw_idx(evsel)) { @@ -3164,17 +3481,19 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, } if (type & PERF_SAMPLE_REGS_USER) { + struct regs_dump *regs = perf_sample__user_regs(data); + OVERFLOW_CHECK_u64(array); - data->user_regs.abi = *array; + regs->abi = *array; array++; - if (data->user_regs.abi) { + if (regs->abi) { u64 mask = evsel->core.attr.sample_regs_user; sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); - data->user_regs.mask = mask; - data->user_regs.regs = (u64 *)array; + regs->mask = mask; + regs->regs = (u64 *)array; array = (void *)array + sz; } } @@ -3196,13 +3515,13 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, data->user_stack.size = *array++; if (WARN_ONCE(data->user_stack.size > sz, "user stack dump failure\n")) - return -EFAULT; + goto out_efault; } } if (type & PERF_SAMPLE_WEIGHT_TYPE) { OVERFLOW_CHECK_u64(array); - arch_perf_parse_sample_weight(data, array, type); + perf_parse_sample_weight(data, array, type); array++; } @@ -3218,19 +3537,20 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, array++; } - data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE; if (type & PERF_SAMPLE_REGS_INTR) { + struct regs_dump *regs = perf_sample__intr_regs(data); + OVERFLOW_CHECK_u64(array); - data->intr_regs.abi = *array; + regs->abi = *array; array++; - if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) { + if (regs->abi != PERF_SAMPLE_REGS_ABI_NONE) { u64 mask = evsel->core.attr.sample_regs_intr; sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); - data->intr_regs.mask = mask; - data->intr_regs.regs = (u64 *)array; + regs->mask = mask; + regs->regs = (u64 *)array; array = (void *)array + sz; } } @@ -3272,7 +3592,15 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, array = (void *)array + sz; } + if (evsel__is_offcpu_event(evsel)) { + if (__set_offcpu_sample(data)) + goto out_efault; + } + return 0; +out_efault: + perf_sample__exit(data); + return -EFAULT; } int evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event, @@ -3472,25 +3800,42 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, { int paranoid; - if ((err == ENOENT || err == ENXIO || err == ENODEV) && - evsel->core.attr.type == PERF_TYPE_HARDWARE && - evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES) { + if ((err == ENODEV || err == ENOENT || err == ENXIO) && + evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { /* - * If it's cycles then fall back to hrtimer based cpu-clock sw - * counter, which is always available even if no PMU support. - * - * PPC returns ENXIO until 2.6.37 (behavior changed with commit - * b0a873e). + * If it's the legacy hardware cycles event fails then fall back + * to hrtimer based cpu-clock sw counter, which is always + * available even if no PMU support. PPC returned ENXIO rather + * than ENODEV or ENOENT until 2.6.37. */ - evsel->core.attr.type = PERF_TYPE_SOFTWARE; + evsel->pmu = perf_pmus__find_by_type(PERF_TYPE_SOFTWARE); + assert(evsel->pmu); /* software is a "well-known" and can't fail PMU type. */ + + /* Configure the event. */ + evsel->core.attr.type = PERF_TYPE_SOFTWARE; evsel->core.attr.config = target__has_cpu(target) ? PERF_COUNT_SW_CPU_CLOCK : PERF_COUNT_SW_TASK_CLOCK; - scnprintf(msg, msgsize, - "The cycles event is not supported, trying to fall back to %s", - target__has_cpu(target) ? "cpu-clock" : "task-clock"); + evsel->core.is_pmu_core = false; + /* Remove excludes for new event. */ + if (evsel->fallenback_eacces) { + evsel->core.attr.exclude_kernel = 0; + evsel->core.attr.exclude_hv = 0; + evsel->fallenback_eacces = false; + } + if (evsel->fallenback_eopnotsupp) { + evsel->core.attr.exclude_guest = 0; + evsel->fallenback_eopnotsupp = false; + } + + /* Name is recomputed by evsel__name. */ zfree(&evsel->name); + + /* Log message. */ + scnprintf(msg, msgsize, + "The cycles event is not supported, trying to fall back to %s", + evsel__name(evsel)); return true; } else if (err == EACCES && !evsel->core.attr.exclude_kernel && (paranoid = perf_event_paranoid()) > 1) { @@ -3500,7 +3845,7 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, /* If event has exclude user then don't exclude kernel. */ if (evsel->core.attr.exclude_user) - return false; + goto no_fallback; /* Is there already the separator in the name. */ if (strchr(name, '/') || @@ -3508,7 +3853,7 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, sep = ""; if (asprintf(&new_name, "%s%su", name, sep) < 0) - return false; + goto no_fallback; free(evsel->name); evsel->name = new_name; @@ -3517,7 +3862,7 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, " samples", paranoid); evsel->core.attr.exclude_kernel = 1; evsel->core.attr.exclude_hv = 1; - + evsel->fallenback_eacces = true; return true; } else if (err == EOPNOTSUPP && !evsel->core.attr.exclude_guest && !evsel->exclude_GH) { @@ -3531,17 +3876,19 @@ bool evsel__fallback(struct evsel *evsel, struct target *target, int err, sep = ""; if (asprintf(&new_name, "%s%sH", name, sep) < 0) - return false; + goto no_fallback; free(evsel->name); evsel->name = new_name; /* Apple M1 requires exclude_guest */ - scnprintf(msg, msgsize, "trying to fall back to excluding guest samples"); + scnprintf(msg, msgsize, "Trying to fall back to excluding guest samples"); evsel->core.attr.exclude_guest = 1; - + evsel->fallenback_eopnotsupp = true; return true; } - +no_fallback: + scnprintf(msg, msgsize, "No fallback found for '%s' for error %d", + evsel__name(evsel), err); return false; } @@ -3654,6 +4001,7 @@ static int dump_perf_event_processes(char *msg, size_t size) } int __weak arch_evsel__open_strerror(struct evsel *evsel __maybe_unused, + int err __maybe_unused, char *msg __maybe_unused, size_t size __maybe_unused) { @@ -3663,7 +4011,7 @@ int __weak arch_evsel__open_strerror(struct evsel *evsel __maybe_unused, int evsel__open_strerror(struct evsel *evsel, struct target *target, int err, char *msg, size_t size) { - char sbuf[STRERR_BUFSIZE]; + struct perf_pmu *pmu; int printed = 0, enforced = 0; int ret; @@ -3747,6 +4095,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg, size, "%s", "No hardware sampling interrupt available.\n"); #endif + if (!target__has_cpu(target)) + return scnprintf(msg, size, + "Unsupported event (%s) in per-thread mode, enable system wide with '-a'.", + evsel__name(evsel)); break; case EBUSY: if (find_process("oprofiled")) @@ -3774,7 +4126,8 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg, size, "The 'aux_action' feature is not supported, update the kernel."); if (perf_missing_features.aux_output) return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel."); - if (!target__has_cpu(target)) + pmu = evsel__find_pmu(evsel); + if (!pmu->is_core && !target__has_cpu(target)) return scnprintf(msg, size, "Invalid event (%s) in per-thread mode, enable system wide with '-a'.", evsel__name(evsel)); @@ -3787,21 +4140,27 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, break; } - ret = arch_evsel__open_strerror(evsel, msg, size); + ret = arch_evsel__open_strerror(evsel, err, msg, size); if (ret) return ret; + errno = err; return scnprintf(msg, size, - "The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n" - "\"dmesg | grep -i perf\" may provide additional information.\n", - err, str_error_r(err, sbuf, sizeof(sbuf)), evsel__name(evsel)); + "The sys_perf_event_open() syscall failed for event (%s): %m\n" + "\"dmesg | grep -i perf\" may provide additional information.\n", + evsel__name(evsel)); +} + +struct perf_session *evsel__session(struct evsel *evsel) +{ + return evsel && evsel->evlist ? evsel->evlist->session : NULL; } struct perf_env *evsel__env(struct evsel *evsel) { - if (evsel && evsel->evlist && evsel->evlist->env) - return evsel->evlist->env; - return &perf_env; + struct perf_session *session = evsel__session(evsel); + + return session ? perf_session__env(session) : NULL; } static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist) @@ -3811,6 +4170,9 @@ static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist) if (evsel__is_retire_lat(evsel)) return 0; + if (perf_pmu__kind(evsel->pmu) != PERF_PMU_KIND_PE) + return 0; + for (cpu_map_idx = 0; cpu_map_idx < xyarray__max_x(evsel->core.fd); cpu_map_idx++) { for (thread = 0; thread < xyarray__max_y(evsel->core.fd); thread++) { @@ -3856,14 +4218,16 @@ void evsel__zero_per_pkg(struct evsel *evsel) */ bool evsel__is_hybrid(const struct evsel *evsel) { - if (perf_pmus__num_core_pmus() == 1) + if (!evsel->core.is_pmu_core) return false; - return evsel->core.is_pmu_core; + return perf_pmus__num_core_pmus() > 1; } struct evsel *evsel__leader(const struct evsel *evsel) { + if (evsel->core.leader == NULL) + return NULL; return container_of(evsel->core.leader, struct evsel, core); } @@ -3882,6 +4246,17 @@ void evsel__set_leader(struct evsel *evsel, struct evsel *leader) evsel->core.leader = &leader->core; } +bool evsel__is_aux_event(const struct evsel *evsel) +{ + struct perf_pmu *pmu; + + if (evsel->needs_auxtrace_mmap) + return true; + + pmu = evsel__find_pmu(evsel); + return pmu && pmu->auxtrace; +} + int evsel__source_count(const struct evsel *evsel) { struct evsel *pos; @@ -3912,3 +4287,152 @@ void evsel__remove_from_group(struct evsel *evsel, struct evsel *leader) leader->core.nr_members--; } } + +bool evsel__set_needs_uniquify(struct evsel *counter, const struct perf_stat_config *config) +{ + struct evsel *evsel; + + if (counter->needs_uniquify) { + /* Already set. */ + return true; + } + + if (counter->use_config_name || counter->is_libpfm_event) { + /* Original name will be used. */ + return false; + } + + if (!config->hybrid_merge && evsel__is_hybrid(counter)) { + /* Unique hybrid counters necessary. */ + counter->needs_uniquify = true; + return true; + } + + if (counter->core.attr.type < PERF_TYPE_MAX && counter->core.attr.type != PERF_TYPE_RAW) { + /* Legacy event, don't uniquify. */ + return false; + } + + if (counter->pmu && counter->pmu->is_core && + counter->alternate_hw_config != PERF_COUNT_HW_MAX) { + /* A sysfs or json event replacing a legacy event, don't uniquify. */ + return false; + } + + if (config->aggr_mode == AGGR_NONE) { + /* Always unique with no aggregation. */ + counter->needs_uniquify = true; + return true; + } + + if (counter->first_wildcard_match != NULL) { + /* + * If stats are merged then only the first_wildcard_match is + * displayed, there is no need to uniquify this evsel as the + * name won't be shown. + */ + return false; + } + + /* + * Do other non-merged events in the evlist have the same name? If so + * uniquify is necessary. + */ + evlist__for_each_entry(counter->evlist, evsel) { + if (evsel == counter || evsel->first_wildcard_match || evsel->pmu == counter->pmu) + continue; + + if (evsel__name_is(counter, evsel__name(evsel))) { + counter->needs_uniquify = true; + return true; + } + } + return false; +} + +void evsel__uniquify_counter(struct evsel *counter) +{ + const char *name, *pmu_name, *config; + char *new_name; + int len, ret; + + /* No uniquification necessary. */ + if (!counter->needs_uniquify) + return; + + /* The evsel was already uniquified. */ + if (counter->uniquified_name) + return; + + /* Avoid checking to uniquify twice. */ + counter->uniquified_name = true; + + name = evsel__name(counter); + config = strchr(name, '/'); + pmu_name = counter->pmu->name; + + /* Already prefixed by the PMU name? */ + len = pmu_name_len_no_suffix(pmu_name); + + if (!strncmp(name, pmu_name, len)) { + /* + * If the PMU name is there, then there is no sense in not + * having a slash. Do this for robustness. + */ + if (config == NULL) + config = name - 1; + + ret = asprintf(&new_name, "%s/%s", pmu_name, config + 1); + } else if (config) { + len = config - name; + if (config[1] == '/') { + /* case: event// */ + ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 2); + } else { + /* case: event/.../ */ + ret = asprintf(&new_name, "%s/%.*s,%s", pmu_name, len, name, config + 1); + } + } else { + config = strchr(name, ':'); + if (config) { + /* case: event:.. */ + len = config - name; + + ret = asprintf(&new_name, "%s/%.*s/%s", pmu_name, len, name, config + 1); + } else { + /* case: event */ + ret = asprintf(&new_name, "%s/%s/", pmu_name, name); + } + } + if (ret > 0) { + free(counter->name); + counter->name = new_name; + } else { + /* ENOMEM from asprintf. */ + counter->uniquified_name = false; + } +} + +void evsel__warn_user_requested_cpus(struct evsel *evsel, struct perf_cpu_map *user_requested_cpus) +{ + struct perf_cpu_map *intersect, *online = NULL; + const struct perf_pmu *pmu = evsel__find_pmu(evsel); + + if (pmu && pmu->is_core) { + intersect = perf_cpu_map__intersect(pmu->cpus, user_requested_cpus); + } else { + online = cpu_map__online(); + intersect = perf_cpu_map__intersect(online, user_requested_cpus); + } + if (!perf_cpu_map__equal(intersect, user_requested_cpus)) { + char buf1[128]; + char buf2[128]; + + cpu_map__snprint(user_requested_cpus, buf1, sizeof(buf1)); + cpu_map__snprint(online ?: pmu->cpus, buf2, sizeof(buf2)); + pr_warning("WARNING: A requested CPU in '%s' is not supported by PMU '%s' (CPUs %s) for event '%s'\n", + buf1, pmu ? pmu->name : "cpu", buf2, evsel__name(evsel)); + } + perf_cpu_map__put(intersect); + perf_cpu_map__put(online); +} |
