diff options
Diffstat (limited to 'tools/perf')
23 files changed, 334 insertions, 100 deletions
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 8806ed5f3802..f8d2167cf3e7 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -28,29 +28,46 @@ OPTIONS <command>...:: Any command you can specify in a shell. +-i:: +--input=<file>:: + Input file name. + -f:: --force:: Don't do ownership validation -t:: ---type=:: +--type=<type>:: Select the memory operation type: load or store (default: load,store) -D:: ---dump-raw-samples=:: +--dump-raw-samples:: Dump the raw decoded samples on the screen in a format that is easy to parse with one sample per line. -x:: ---field-separator:: +--field-separator=<separator>:: Specify the field separator used when dump raw samples (-D option). By default, The separator is the space character. -C:: ---cpu-list:: - Restrict dump of raw samples to those provided via this option. Note that the same - option can be passed in record mode. It will be interpreted the same way as perf - record. +--cpu=<cpu>:: + Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a + comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. Default + is to monitor all CPUS. +-U:: +--hide-unresolved:: + Only display entries resolved to a symbol. + +-p:: +--phys-data:: + Record/Report sample physical addresses + +RECORD OPTIONS +-------------- +-e:: +--event <event>:: + Event selector. Use 'perf mem record -e list' to list available events. -K:: --all-kernel:: @@ -60,12 +77,12 @@ OPTIONS --all-user:: Configure all used events to run in user space. ---ldload:: - Specify desired latency for loads event. +-v:: +--verbose:: + Be more verbose (show counter open errors, etc) --p:: ---phys-data:: - Record/Report sample physical addresses +--ldlat <n>:: + Specify desired latency for loads event. In addition, for report all perf report options are valid, and for record all perf record options. diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index d00f0d51cab8..dfb218feaad9 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -111,8 +111,8 @@ A perf_header_string with the CPU architecture (uname -m) A structure defining the number of CPUs. struct nr_cpus { - uint32_t nr_cpus_online; uint32_t nr_cpus_available; /* CPUs not yet onlined */ + uint32_t nr_cpus_online; }; HEADER_CPUDESC = 8, @@ -153,10 +153,18 @@ struct { HEADER_CPU_TOPOLOGY = 13, String lists defining the core and CPU threads topology. +The string lists are followed by a variable length array +which contains core_id and socket_id of each cpu. +The number of entries can be determined by the size of the +section minus the sizes of both string lists. struct { struct perf_header_string_list cores; /* Variable length */ struct perf_header_string_list threads; /* Variable length */ + struct { + uint32_t core_id; + uint32_t socket_id; + } cpus[nr]; /* Variable length records */ }; Example: diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c index 6cb48e4cffd9..3afe8256eff2 100644 --- a/tools/perf/arch/s390/util/auxtrace.c +++ b/tools/perf/arch/s390/util/auxtrace.c @@ -87,6 +87,7 @@ struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist, struct perf_evsel *pos; int diagnose = 0; + *err = 0; if (evlist->nr_entries == 0) return NULL; diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c index a4c30f1c70be..163b92f33998 100644 --- a/tools/perf/arch/s390/util/header.c +++ b/tools/perf/arch/s390/util/header.c @@ -146,21 +146,3 @@ char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused) zfree(&buf); return buf; } - -/* - * Compare the cpuid string returned by get_cpuid() function - * with the name generated by the jevents file read from - * pmu-events/arch/s390/mapfile.csv. - * - * Parameter mapcpuid is the cpuid as stored in the - * pmu-events/arch/s390/mapfile.csv. This is just the type number. - * Parameter cpuid is the cpuid returned by function get_cpuid(). - */ -int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) -{ - char *cp = strchr(cpuid, ','); - - if (cp == NULL) - return -1; - return strncmp(cp + 1, mapcpuid, strlen(mapcpuid)); -} diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 944070e98a2c..63eb49082774 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -175,7 +175,7 @@ static const struct option options[] = { OPT_UINTEGER('s', "nr_secs" , &p0.nr_secs, "max number of seconds to run (default: 5 secs)"), OPT_UINTEGER('u', "usleep" , &p0.sleep_usecs, "usecs to sleep per loop iteration"), - OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via writes (can be mixed with -W)"), + OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via reads (can be mixed with -W)"), OPT_BOOLEAN('W', "data_writes" , &p0.data_writes, "access the data via writes (can be mixed with -R)"), OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards, "access the data backwards as well"), OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"), diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 147a27e8c937..f17dc601b0f3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -172,6 +172,7 @@ static bool interval_count; static const char *output_name; static int output_fd; static int print_free_counters_hint; +static int print_mixed_hw_group_error; struct perf_stat { bool record; @@ -1126,6 +1127,30 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); } +static bool is_mixed_hw_group(struct perf_evsel *counter) +{ + struct perf_evlist *evlist = counter->evlist; + u32 pmu_type = counter->attr.type; + struct perf_evsel *pos; + + if (counter->nr_members < 2) + return false; + + evlist__for_each_entry(evlist, pos) { + /* software events can be part of any hardware group */ + if (pos->attr.type == PERF_TYPE_SOFTWARE) + continue; + if (pmu_type == PERF_TYPE_SOFTWARE) { + pmu_type = pos->attr.type; + continue; + } + if (pmu_type != pos->attr.type) + return true; + } + + return false; +} + static void printout(int id, int nr, struct perf_evsel *counter, double uval, char *prefix, u64 run, u64 ena, double noise, struct runtime_stat *st) @@ -1178,8 +1203,11 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep); - if (counter->supported) + if (counter->supported) { print_free_counters_hint = 1; + if (is_mixed_hw_group(counter)) + print_mixed_hw_group_error = 1; + } fprintf(stat_config.output, "%-*s%s", csv_output ? 0 : unit_width, @@ -1256,7 +1284,8 @@ static void uniquify_event_name(struct perf_evsel *counter) char *new_name; char *config; - if (!counter->pmu_name || !strncmp(counter->name, counter->pmu_name, + if (counter->uniquified_name || + !counter->pmu_name || !strncmp(counter->name, counter->pmu_name, strlen(counter->pmu_name))) return; @@ -1274,6 +1303,8 @@ static void uniquify_event_name(struct perf_evsel *counter) counter->name = new_name; } } + + counter->uniquified_name = true; } static void collect_all_aliases(struct perf_evsel *counter, @@ -1757,6 +1788,11 @@ static void print_footer(void) " echo 0 > /proc/sys/kernel/nmi_watchdog\n" " perf stat ...\n" " echo 1 > /proc/sys/kernel/nmi_watchdog\n"); + + if (print_mixed_hw_group_error) + fprintf(output, + "The events in group usually have to be from " + "the same PMU. Try reorganizing the group.\n"); } static void print_counters(struct timespec *ts, int argc, const char **argv) diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv index ca7682748a4b..78bcf7f8e206 100644 --- a/tools/perf/pmu-events/arch/s390/mapfile.csv +++ b/tools/perf/pmu-events/arch/s390/mapfile.csv @@ -1,6 +1,6 @@ Family-model,Version,Filename,EventType -209[78],1,cf_z10,core -281[78],1,cf_z196,core -282[78],1,cf_zec12,core -296[45],1,cf_z13,core -3906,3,cf_z14,core +^IBM.209[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z10,core +^IBM.281[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z196,core +^IBM.282[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_zec12,core +^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core +^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 93656f2fd53a..7e3cce3bcf3b 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -29,7 +29,6 @@ GenuineIntel-6-4D,v13,silvermont,core GenuineIntel-6-4C,v13,silvermont,core GenuineIntel-6-2A,v15,sandybridge,core GenuineIntel-6-2C,v2,westmereep-dp,core -GenuineIntel-6-2C,v2,westmereep-dp,core GenuineIntel-6-25,v2,westmereep-sp,core GenuineIntel-6-2F,v2,westmereex,core GenuineIntel-6-55,v1,skylakex,core diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling index f906b793196f..8a33ca4f9e1f 100644 --- a/tools/perf/tests/attr/test-record-group-sampling +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -35,3 +35,6 @@ inherit=0 # sampling disabled sample_freq=0 sample_period=0 +freq=0 +write_backward=0 +sample_id_all=0 diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 1ecc1f0ff84a..ee86473643be 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -16,15 +16,13 @@ nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254 trace_libc_inet_pton_backtrace() { idx=0 expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" - expected[1]=".*inet_pton[[:space:]]\($libc\)$" + expected[1]=".*inet_pton[[:space:]]\($libc|inlined\)$" case "$(uname -m)" in s390x) - eventattr='call-graph=dwarf' + eventattr='call-graph=dwarf,max-stack=4' expected[2]="gaih_inet.*[[:space:]]\($libc|inlined\)$" - expected[3]="__GI_getaddrinfo[[:space:]]\($libc|inlined\)$" + expected[3]="(__GI_)?getaddrinfo[[:space:]]\($libc|inlined\)$" expected[4]="main[[:space:]]\(.*/bin/ping.*\)$" - expected[5]="__libc_start_main[[:space:]]\($libc\)$" - expected[6]="_start[[:space:]]\(.*/bin/ping.*\)$" ;; *) eventattr='max-stack=3' diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index 17cb1bb3448c..40e30a26b23c 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -70,6 +70,27 @@ static int check_cpu_topology(char *path, struct cpu_map *map) session = perf_session__new(&data, false, NULL); TEST_ASSERT_VAL("can't get session", session); + /* On platforms with large numbers of CPUs process_cpu_topology() + * might issue an error while reading the perf.data file section + * HEADER_CPU_TOPOLOGY and the cpu_topology_map pointed to by member + * cpu is a NULL pointer. + * Example: On s390 + * CPU 0 is on core_id 0 and physical_package_id 6 + * CPU 1 is on core_id 1 and physical_package_id 3 + * + * Core_id and physical_package_id are platform and architecture + * dependend and might have higher numbers than the CPU id. + * This actually depends on the configuration. + * + * In this case process_cpu_topology() prints error message: + * "socket_id number is too big. You may need to upgrade the + * perf tool." + * + * This is the reason why this test might be skipped. + */ + if (!session->header.env.cpu) + return TEST_SKIP; + for (i = 0; i < session->header.env.nr_cpus_avail; i++) { if (!cpu_map__has(map, i)) continue; @@ -95,7 +116,7 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe { char path[PATH_MAX]; struct cpu_map *map; - int ret = -1; + int ret = TEST_FAIL; TEST_ASSERT_VAL("can't get templ file", !get_temp(path)); @@ -110,12 +131,9 @@ int test__session_topology(struct test *test __maybe_unused, int subtest __maybe goto free_path; } - if (check_cpu_topology(path, map)) - goto free_map; - ret = 0; - -free_map: + ret = check_cpu_topology(path, map); cpu_map__put(map); + free_path: unlink(path); return ret; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 536ee148bff8..5d74a30fe00f 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1263,6 +1263,9 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start max_percent = sample->percent; } + if (al->samples_nr > nr_percent) + nr_percent = al->samples_nr; + if (max_percent < min_pcnt) return -1; diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index af7ad814b2c3..cee658733e2c 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -66,7 +66,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name) } obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name); - if (IS_ERR(obj)) { + if (IS_ERR_OR_NULL(obj)) { pr_debug("bpf: failed to load buffer\n"); return ERR_PTR(-EINVAL); } @@ -102,14 +102,14 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source) pr_debug("bpf: successfull builtin compilation\n"); obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename); - if (!IS_ERR(obj) && llvm_param.dump_obj) + if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj) llvm__dump_obj(filename, obj_buf, obj_buf_sz); free(obj_buf); } else obj = bpf_object__open(filename); - if (IS_ERR(obj)) { + if (IS_ERR_OR_NULL(obj)) { pr_debug("bpf: failed to load %s\n", filename); return obj; } 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 c8b98fa22997..4d5fc374e730 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -96,11 +96,19 @@ int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder, /* Nothing to do, might as well just return */ if (decoder->packet_count == 0) return 0; + /* + * The queueing process in function cs_etm_decoder__buffer_packet() + * increments the tail *before* using it. This is somewhat counter + * intuitive but it has the advantage of centralizing tail management + * at a single location. Because of that we need to follow the same + * heuristic with the head, i.e we increment it before using its + * value. Otherwise the first element of the packet queue is not + * used. + */ + decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1); *packet = decoder->packet_buffer[decoder->head]; - decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1); - decoder->packet_count--; return 1; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 40020b1ca54f..bf16dc9ee507 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -239,6 +239,7 @@ static void cs_etm__free(struct perf_session *session) for (i = 0; i < aux->num_cpu; i++) zfree(&aux->metadata[i]); + thread__zput(aux->unknown_thread); zfree(&aux->metadata); zfree(&aux); } @@ -612,8 +613,8 @@ cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq) return buff->len; } -static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm, - struct auxtrace_queue *queue) +static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm, + struct auxtrace_queue *queue) { struct cs_etm_queue *etmq = queue->priv; @@ -1357,6 +1358,23 @@ int cs_etm__process_auxtrace_info(union perf_event *event, etm->auxtrace.free = cs_etm__free; session->auxtrace = &etm->auxtrace; + etm->unknown_thread = thread__new(999999999, 999999999); + if (!etm->unknown_thread) + goto err_free_queues; + + /* + * Initialize list node so that at thread__zput() we can avoid + * segmentation fault at list_del_init(). + */ + INIT_LIST_HEAD(&etm->unknown_thread->node); + + err = thread__set_comm(etm->unknown_thread, "unknown", 0); + if (err) + goto err_delete_thread; + + if (thread__init_map_groups(etm->unknown_thread, etm->machine)) + goto err_delete_thread; + if (dump_trace) { cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu); return 0; @@ -1371,16 +1389,18 @@ int cs_etm__process_auxtrace_info(union perf_event *event, err = cs_etm__synth_events(etm, session); if (err) - goto err_free_queues; + goto err_delete_thread; err = auxtrace_queues__process_index(&etm->queues, session); if (err) - goto err_free_queues; + goto err_delete_thread; etm->data_queued = etm->queues.populated; return 0; +err_delete_thread: + thread__zput(etm->unknown_thread); err_free_queues: auxtrace_queues__free(&etm->queues); session->auxtrace = NULL; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 3e87486c28fe..4cd2cf93f726 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -930,8 +930,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, * than leader in case leader 'leads' the sampling. */ if ((leader != evsel) && leader->sample_read) { - attr->sample_freq = 0; - attr->sample_period = 0; + attr->freq = 0; + attr->sample_freq = 0; + attr->sample_period = 0; + attr->write_backward = 0; + attr->sample_id_all = 0; } if (opts->no_samples) @@ -1922,7 +1925,8 @@ try_fallback: goto fallback_missing_features; } else if (!perf_missing_features.group_read && evsel->attr.inherit && - (evsel->attr.read_format & PERF_FORMAT_GROUP)) { + (evsel->attr.read_format & PERF_FORMAT_GROUP) && + perf_evsel__is_group_leader(evsel)) { perf_missing_features.group_read = true; pr_debug2("switching off group read\n"); goto fallback_missing_features; @@ -2754,8 +2758,14 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, (paranoid = perf_event_paranoid()) > 1) { const char *name = perf_evsel__name(evsel); char *new_name; + const char *sep = ":"; - if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0) + /* Is there already the separator in the name. */ + if (strchr(name, '/') || + strchr(name, ':')) + sep = ""; + + if (asprintf(&new_name, "%s%su", name, sep) < 0) return false; if (evsel->name) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d3ee3af618ef..b13f5f234c8f 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -115,6 +115,7 @@ struct perf_evsel { unsigned int sample_size; int id_pos; int is_pos; + bool uniquified_name; bool snapshot; bool supported; bool needs_swap; @@ -126,6 +127,7 @@ struct perf_evsel { bool precise_max; bool ignore_missing_thread; bool forced_leader; + bool use_uncore_alias; /* parse modifier helper */ int exclude_GH; int nr_members; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 2eca8478e24f..32d50492505d 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1019,13 +1019,6 @@ int machine__load_vmlinux_path(struct machine *machine, enum map_type type) return ret; } -static void map_groups__fixup_end(struct map_groups *mg) -{ - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) - __map_groups__fixup_end(mg, i); -} - static char *get_kernel_version(const char *root_dir) { char version[PATH_MAX]; @@ -1233,6 +1226,7 @@ int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); const char *name = NULL; + struct map *map; u64 addr = 0; int ret; @@ -1259,13 +1253,25 @@ int machine__create_kernel_maps(struct machine *machine) machine__destroy_kernel_maps(machine); return -1; } - machine__set_kernel_mmap(machine, addr, 0); + + /* we have a real start address now, so re-order the kmaps */ + map = machine__kernel_map(machine); + + map__get(map); + map_groups__remove(&machine->kmaps, map); + + /* assume it's the last in the kmaps */ + machine__set_kernel_mmap(machine, addr, ~0ULL); + + map_groups__insert(&machine->kmaps, map); + map__put(map); } - /* - * Now that we have all the maps created, just set the ->end of them: - */ - map_groups__fixup_end(&machine->kmaps); + /* update end address of the kernel map using adjacent module address */ + map = map__next(machine__kernel_map(machine)); + if (map) + machine__set_kernel_mmap(machine, addr, map->start); + return 0; } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 2fb0272146d8..2fc4ee8b86c1 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1219,13 +1219,16 @@ int parse_events_add_numeric(struct parse_events_state *parse_state, int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, - struct list_head *head_config, bool auto_merge_stats) + struct list_head *head_config, + bool auto_merge_stats, + bool use_alias) { struct perf_event_attr attr; struct perf_pmu_info info; struct perf_pmu *pmu; struct perf_evsel *evsel; struct parse_events_error *err = parse_state->error; + bool use_uncore_alias; LIST_HEAD(config_terms); pmu = perf_pmu__find(name); @@ -1244,11 +1247,14 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, memset(&attr, 0, sizeof(attr)); } + use_uncore_alias = (pmu->is_uncore && use_alias); + if (!head_config) { attr.type = pmu->type; evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats); if (evsel) { evsel->pmu_name = name; + evsel->use_uncore_alias = use_uncore_alias; return 0; } else { return -ENOMEM; @@ -1282,6 +1288,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel->metric_expr = info.metric_expr; evsel->metric_name = info.metric_name; evsel->pmu_name = name; + evsel->use_uncore_alias = use_uncore_alias; } return evsel ? 0 : -ENOMEM; @@ -1317,7 +1324,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, list_add_tail(&term->list, head); if (!parse_events_add_pmu(parse_state, list, - pmu->name, head, true)) { + pmu->name, head, + true, true)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; @@ -1339,7 +1347,120 @@ int parse_events__modifier_group(struct list_head *list, return parse_events__modifier_event(list, event_mod, true); } -void parse_events__set_leader(char *name, struct list_head *list) +/* + * Check if the two uncore PMUs are from the same uncore block + * The format of the uncore PMU name is uncore_#blockname_#pmuidx + */ +static bool is_same_uncore_block(const char *pmu_name_a, const char *pmu_name_b) +{ + char *end_a, *end_b; + + end_a = strrchr(pmu_name_a, '_'); + end_b = strrchr(pmu_name_b, '_'); + + if (!end_a || !end_b) + return false; + + if ((end_a - pmu_name_a) != (end_b - pmu_name_b)) + return false; + + return (strncmp(pmu_name_a, pmu_name_b, end_a - pmu_name_a) == 0); +} + +static int +parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list, + struct parse_events_state *parse_state) +{ + struct perf_evsel *evsel, *leader; + uintptr_t *leaders; + bool is_leader = true; + int i, nr_pmu = 0, total_members, ret = 0; + + leader = list_first_entry(list, struct perf_evsel, node); + evsel = list_last_entry(list, struct perf_evsel, node); + total_members = evsel->idx - leader->idx + 1; + + leaders = calloc(total_members, sizeof(uintptr_t)); + if (WARN_ON(!leaders)) + return 0; + + /* + * Going through the whole group and doing sanity check. + * All members must use alias, and be from the same uncore block. + * Also, storing the leader events in an array. + */ + __evlist__for_each_entry(list, evsel) { + + /* Only split the uncore group which members use alias */ + if (!evsel->use_uncore_alias) + goto out; + + /* The events must be from the same uncore block */ + if (!is_same_uncore_block(leader->pmu_name, evsel->pmu_name)) + goto out; + + if (!is_leader) + continue; + /* + * If the event's PMU name starts to repeat, it must be a new + * event. That can be used to distinguish the leader from + * other members, even they have the same event name. + */ + if ((leader != evsel) && (leader->pmu_name == evsel->pmu_name)) { + is_leader = false; + continue; + } + /* The name is always alias name */ + WARN_ON(strcmp(leader->name, evsel->name)); + + /* Store the leader event for each PMU */ + leaders[nr_pmu++] = (uintptr_t) evsel; + } + + /* only one event alias */ + if (nr_pmu == total_members) { + parse_state->nr_groups--; + goto handled; + } + + /* + * An uncore event alias is a joint name which means the same event + * runs on all PMUs of a block. + * Perf doesn't support mixed events from different PMUs in the same + * group. The big group has to be split into multiple small groups + * which only include the events from the same PMU. + * + * Here the uncore event aliases must be from the same uncore block. + * The number of PMUs must be same for each alias. The number of new + * small groups equals to the number of PMUs. + * Setting the leader event for corresponding members in each group. + */ + i = 0; + __evlist__for_each_entry(list, evsel) { + if (i >= nr_pmu) + i = 0; + evsel->leader = (struct perf_evsel *) leaders[i++]; + } + + /* The number of members and group name are same for each group */ + for (i = 0; i < nr_pmu; i++) { + evsel = (struct perf_evsel *) leaders[i]; + evsel->nr_members = total_members / nr_pmu; + evsel->group_name = name ? strdup(name) : NULL; + } + + /* Take the new small groups into account */ + parse_state->nr_groups += nr_pmu - 1; + +handled: + ret = 1; +out: + free(leaders); + return ret; +} + +void parse_events__set_leader(char *name, struct list_head *list, + struct parse_events_state *parse_state) { struct perf_evsel *leader; @@ -1348,6 +1469,9 @@ void parse_events__set_leader(char *name, struct list_head *list) return; } + if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state)) + return; + __perf_evlist__set_leader(list); leader = list_entry(list->next, struct perf_evsel, node); leader->group_name = name ? strdup(name) : NULL; @@ -1715,7 +1839,7 @@ int parse_events(struct perf_evlist *evlist, const char *str, struct perf_evsel *last; if (list_empty(&parse_state.list)) { - WARN_ONCE(true, "WARNING: event parser found nothing"); + WARN_ONCE(true, "WARNING: event parser found nothing\n"); return -1; } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 5015cfd58277..4473dac27aee 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -167,7 +167,9 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, void *ptr, char *type, u64 len); int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, - struct list_head *head_config, bool auto_merge_stats); + struct list_head *head_config, + bool auto_merge_stats, + bool use_alias); int parse_events_multi_pmu_add(struct parse_events_state *parse_state, char *str, @@ -178,7 +180,8 @@ int parse_events_copy_term_list(struct list_head *old, enum perf_pmu_event_symbol_type perf_pmu__parse_check(const char *name); -void parse_events__set_leader(char *name, struct list_head *list); +void parse_events__set_leader(char *name, struct list_head *list, + struct parse_events_state *parse_state); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); void parse_events_evlist_error(struct parse_events_state *parse_state, diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 7afeb80cc39e..e37608a87dba 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -161,7 +161,7 @@ PE_NAME '{' events '}' struct list_head *list = $3; inc_group_count(list, _parse_state); - parse_events__set_leader($1, list); + parse_events__set_leader($1, list, _parse_state); $$ = list; } | @@ -170,7 +170,7 @@ PE_NAME '{' events '}' struct list_head *list = $2; inc_group_count(list, _parse_state); - parse_events__set_leader(NULL, list); + parse_events__set_leader(NULL, list, _parse_state); $$ = list; } @@ -232,7 +232,7 @@ PE_NAME opt_event_config YYABORT; ALLOC_LIST(list); - if (parse_events_add_pmu(_parse_state, list, $1, $2, false)) { + if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) { struct perf_pmu *pmu = NULL; int ok = 0; char *pattern; @@ -251,7 +251,7 @@ PE_NAME opt_event_config free(pattern); YYABORT; } - if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true)) + if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true, false)) ok++; parse_events_terms__delete(terms); } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 61a5e5027338..d2fb597c9a8c 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -539,9 +539,10 @@ static bool pmu_is_uncore(const char *name) /* * PMU CORE devices have different name other than cpu in sysfs on some - * platforms. looking for possible sysfs files to identify as core device. + * platforms. + * Looking for possible sysfs files to identify the arm core device. */ -static int is_pmu_core(const char *name) +static int is_arm_pmu_core(const char *name) { struct stat st; char path[PATH_MAX]; @@ -550,12 +551,6 @@ static int is_pmu_core(const char *name) if (!sysfs) return 0; - /* Look for cpu sysfs (x86 and others) */ - scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu", sysfs); - if ((stat(path, &st) == 0) && - (strncmp(name, "cpu", strlen("cpu")) == 0)) - return 1; - /* Look for cpu sysfs (specific to arm) */ scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus", sysfs, name); @@ -586,7 +581,7 @@ char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused) * cpuid string generated on this platform. * Otherwise return non-zero. */ -int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) +int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) { regex_t re; regmatch_t pmatch[1]; @@ -668,6 +663,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) struct pmu_events_map *map; struct pmu_event *pe; const char *name = pmu->name; + const char *pname; map = perf_pmu__find_map(pmu); if (!map) @@ -686,11 +682,9 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) break; } - if (!is_pmu_core(name)) { - /* check for uncore devices */ - if (pe->pmu == NULL) - continue; - if (strncmp(pe->pmu, name, strlen(pe->pmu))) + if (!is_arm_pmu_core(name)) { + pname = pe->pmu ? pe->pmu : "cpu"; + if (strncmp(pname, name, strlen(pname))) continue; } diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 10dd5fce082b..7f8afacd08ee 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -531,6 +531,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, PyLong_FromUnsignedLongLong(sample->period)); pydict_set_item_string_decref(dict_sample, "phys_addr", PyLong_FromUnsignedLongLong(sample->phys_addr)); + pydict_set_item_string_decref(dict_sample, "addr", + PyLong_FromUnsignedLongLong(sample->addr)); set_sample_read_in_dict(dict_sample, sample, evsel); pydict_set_item_string_decref(dict, "sample", dict_sample); |