diff options
Diffstat (limited to 'tools/perf/util')
-rw-r--r-- | tools/perf/util/evlist.c | 12 | ||||
-rw-r--r-- | tools/perf/util/evsel.c | 3 | ||||
-rw-r--r-- | tools/perf/util/header.h | 1 | ||||
-rw-r--r-- | tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 38 | ||||
-rw-r--r-- | tools/perf/util/machine.c | 6 | ||||
-rw-r--r-- | tools/perf/util/parse-events.c | 8 | ||||
-rw-r--r-- | tools/perf/util/parse-events.h | 3 | ||||
-rw-r--r-- | tools/perf/util/pmu.c | 176 | ||||
-rw-r--r-- | tools/perf/util/pmu.h | 6 | ||||
-rw-r--r-- | tools/perf/util/probe-event.c | 2 | ||||
-rw-r--r-- | tools/perf/util/strbuf.h | 3 | ||||
-rw-r--r-- | tools/perf/util/thread.c | 9 |
12 files changed, 223 insertions, 44 deletions
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index ea34c5a32c11..d92e02006fb8 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -384,15 +384,14 @@ void perf_evlist__toggle_enable(struct perf_evlist *evlist) static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist, struct perf_evsel *evsel, int cpu) { - int thread, err; + int thread; int nr_threads = perf_evlist__nr_threads(evlist, evsel); if (!evsel->fd) return -EINVAL; for (thread = 0; thread < nr_threads; thread++) { - err = ioctl(FD(evsel, cpu, thread), - PERF_EVENT_IOC_ENABLE, 0); + int err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); if (err) return err; } @@ -403,14 +402,14 @@ static int perf_evlist__enable_event_thread(struct perf_evlist *evlist, struct perf_evsel *evsel, int thread) { - int cpu, err; + int cpu; int nr_cpus = cpu_map__nr(evlist->cpus); if (!evsel->fd) return -EINVAL; for (cpu = 0; cpu < nr_cpus; cpu++) { - err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); + int err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0); if (err) return err; } @@ -1606,10 +1605,9 @@ void perf_evlist__close(struct perf_evlist *evlist) struct perf_evsel *evsel; int ncpus = cpu_map__nr(evlist->cpus); int nthreads = thread_map__nr(evlist->threads); - int n; evlist__for_each_entry_reverse(evlist, evsel) { - n = evsel->cpus ? evsel->cpus->nr : ncpus; + int n = evsel->cpus ? evsel->cpus->nr : ncpus; perf_evsel__close(evsel, n, nthreads); } } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 380e84c3af3d..8bc271141d9d 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -985,14 +985,13 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { - int cpu, thread; - if (evsel->system_wide) nthreads = 1; evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); if (evsel->fd) { + int cpu, thread; for (cpu = 0; cpu < ncpus; cpu++) { for (thread = 0; thread < nthreads; thread++) { FD(evsel, cpu, thread) = -1; diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index d306ca118449..d30109b421ee 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -151,4 +151,5 @@ int write_padded(int fd, const void *bf, size_t count, size_t count_aligned); */ int get_cpuid(char *buffer, size_t sz); +char *get_cpuid_str(void); #endif /* __PERF_HEADER_H */ diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 7591a0c37473..16c06d3ae577 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -90,6 +90,7 @@ struct intel_pt_decoder { bool pge; bool have_tma; bool have_cyc; + bool fixup_last_mtc; uint64_t pos; uint64_t last_ip; uint64_t ip; @@ -586,10 +587,31 @@ struct intel_pt_calc_cyc_to_tsc_info { uint64_t tsc_timestamp; uint64_t timestamp; bool have_tma; + bool fixup_last_mtc; bool from_mtc; double cbr_cyc_to_tsc; }; +/* + * MTC provides a 8-bit slice of CTC but the TMA packet only provides the lower + * 16 bits of CTC. If mtc_shift > 8 then some of the MTC bits are not in the CTC + * provided by the TMA packet. Fix-up the last_mtc calculated from the TMA + * packet by copying the missing bits from the current MTC assuming the least + * difference between the two, and that the current MTC comes after last_mtc. + */ +static void intel_pt_fixup_last_mtc(uint32_t mtc, int mtc_shift, + uint32_t *last_mtc) +{ + uint32_t first_missing_bit = 1U << (16 - mtc_shift); + uint32_t mask = ~(first_missing_bit - 1); + + *last_mtc |= mtc & mask; + if (*last_mtc >= mtc) { + *last_mtc -= first_missing_bit; + *last_mtc &= 0xff; + } +} + static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) { struct intel_pt_decoder *decoder = pkt_info->decoder; @@ -619,6 +641,11 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) return 0; mtc = pkt_info->packet.payload; + if (decoder->mtc_shift > 8 && data->fixup_last_mtc) { + data->fixup_last_mtc = false; + intel_pt_fixup_last_mtc(mtc, decoder->mtc_shift, + &data->last_mtc); + } if (mtc > data->last_mtc) mtc_delta = mtc - data->last_mtc; else @@ -687,6 +714,7 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info) data->ctc_delta = 0; data->have_tma = true; + data->fixup_last_mtc = true; return 0; @@ -753,6 +781,7 @@ static void intel_pt_calc_cyc_to_tsc(struct intel_pt_decoder *decoder, .tsc_timestamp = decoder->tsc_timestamp, .timestamp = decoder->timestamp, .have_tma = decoder->have_tma, + .fixup_last_mtc = decoder->fixup_last_mtc, .from_mtc = from_mtc, .cbr_cyc_to_tsc = 0, }; @@ -1271,6 +1300,7 @@ static void intel_pt_calc_tma(struct intel_pt_decoder *decoder) } decoder->ctc_delta = 0; decoder->have_tma = true; + decoder->fixup_last_mtc = true; intel_pt_log("CTC timestamp " x64_fmt " last MTC %#x CTC rem %#x\n", decoder->ctc_timestamp, decoder->last_mtc, ctc_rem); } @@ -1285,6 +1315,12 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder) mtc = decoder->packet.payload; + if (decoder->mtc_shift > 8 && decoder->fixup_last_mtc) { + decoder->fixup_last_mtc = false; + intel_pt_fixup_last_mtc(mtc, decoder->mtc_shift, + &decoder->last_mtc); + } + if (mtc > decoder->last_mtc) mtc_delta = mtc - decoder->last_mtc; else @@ -1353,6 +1389,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder) timestamp, decoder->timestamp); else decoder->timestamp = timestamp; + + decoder->timestamp_insn_cnt = 0; } /* Walk PSB+ packets when already in sync. */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 18e4519abef2..df85b9efd80f 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1745,9 +1745,8 @@ static int resolve_lbr_callchain_sample(struct thread *thread, int max_stack) { struct ip_callchain *chain = sample->callchain; - int chain_nr = min(max_stack, (int)chain->nr); + int chain_nr = min(max_stack, (int)chain->nr), i; u8 cpumode = PERF_RECORD_MISC_USER; - int i, j, err; u64 ip; for (i = 0; i < chain_nr; i++) { @@ -1758,7 +1757,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, /* LBR only affects the user callchain */ if (i != chain_nr) { struct branch_stack *lbr_stack = sample->branch_stack; - int lbr_nr = lbr_stack->nr; + int lbr_nr = lbr_stack->nr, j; /* * LBR callstack can only get user call chain. * The mix_chain_nr is kernel call chain @@ -1772,6 +1771,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, int mix_chain_nr = i + 1 + lbr_nr + 1; for (j = 0; j < mix_chain_nr; j++) { + int err; if (callchain_param.order == ORDER_CALLEE) { if (j < i + 1) ip = chain->ips[j]; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 33546c3ac1fe..4e778eae1510 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -924,6 +924,7 @@ config_term_avail(int term_type, struct parse_events_error *err) case PARSE_EVENTS__TERM_TYPE_CONFIG1: case PARSE_EVENTS__TERM_TYPE_CONFIG2: case PARSE_EVENTS__TERM_TYPE_NAME: + case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: return true; default: if (!err) @@ -1458,7 +1459,7 @@ comp_pmu(const void *p1, const void *p2) struct perf_pmu_event_symbol *pmu1 = (struct perf_pmu_event_symbol *) p1; struct perf_pmu_event_symbol *pmu2 = (struct perf_pmu_event_symbol *) p2; - return strcmp(pmu1->symbol, pmu2->symbol); + return strcasecmp(pmu1->symbol, pmu2->symbol); } static void perf_pmu__parse_cleanup(void) @@ -2263,7 +2264,8 @@ out_enomem: /* * Print the help text for the event symbols: */ -void print_events(const char *event_glob, bool name_only) +void print_events(const char *event_glob, bool name_only, bool quiet_flag, + bool long_desc) { print_symbol_events(event_glob, PERF_TYPE_HARDWARE, event_symbols_hw, PERF_COUNT_HW_MAX, name_only); @@ -2273,7 +2275,7 @@ void print_events(const char *event_glob, bool name_only) print_hwcache_events(event_glob, name_only); - print_pmu_events(event_glob, name_only); + print_pmu_events(event_glob, name_only, quiet_flag, long_desc); if (event_glob != NULL) return; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 8d09a976fca8..da246a3ddb69 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -172,7 +172,8 @@ void parse_events_update_lists(struct list_head *list_event, void parse_events_evlist_error(struct parse_events_evlist *data, int idx, const char *str); -void print_events(const char *event_glob, bool name_only); +void print_events(const char *event_glob, bool name_only, bool quiet, + bool long_desc); struct event_symbol { const char *symbol; diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 2babcdf62839..b1474dcadfa2 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -12,6 +12,9 @@ #include "pmu.h" #include "parse-events.h" #include "cpumap.h" +#include "header.h" +#include "pmu-events/pmu-events.h" +#include "cache.h" struct perf_pmu_format { char *name; @@ -220,7 +223,8 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias, } static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, - char *desc __maybe_unused, char *val) + char *desc, char *val, char *long_desc, + char *topic) { struct perf_pmu_alias *alias; int ret; @@ -253,6 +257,11 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, perf_pmu__parse_snapshot(alias, dir, name); } + alias->desc = desc ? strdup(desc) : NULL; + alias->long_desc = long_desc ? strdup(long_desc) : + desc ? strdup(desc) : NULL; + alias->topic = topic ? strdup(topic) : NULL; + list_add_tail(&alias->list, list); return 0; @@ -269,7 +278,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI buf[ret] = 0; - return __perf_pmu__new_alias(list, dir, name, NULL, buf); + return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL); } static inline bool pmu_alias_info_file(char *name) @@ -473,6 +482,68 @@ static struct cpu_map *pmu_cpumask(const char *name) return cpus; } +/* + * Return the CPU id as a raw string. + * + * Each architecture should provide a more precise id string that + * can be use to match the architecture's "mapfile". + */ +char * __weak get_cpuid_str(void) +{ + return NULL; +} + +/* + * From the pmu_events_map, find the table of PMU events that corresponds + * to the current running CPU. Then, add all PMU events from that table + * as aliases. + */ +static void pmu_add_cpu_aliases(struct list_head *head) +{ + int i; + struct pmu_events_map *map; + struct pmu_event *pe; + char *cpuid; + + cpuid = getenv("PERF_CPUID"); + if (cpuid) + cpuid = strdup(cpuid); + if (!cpuid) + cpuid = get_cpuid_str(); + if (!cpuid) + return; + + pr_debug("Using CPUID %s\n", cpuid); + + i = 0; + while (1) { + map = &pmu_events_map[i++]; + if (!map->table) + goto out; + + if (!strcmp(map->cpuid, cpuid)) + break; + } + + /* + * Found a matching PMU events table. Create aliases + */ + i = 0; + while (1) { + pe = &map->table[i++]; + if (!pe->name) + break; + + /* 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); + } + +out: + free(cpuid); +} + struct perf_event_attr * __weak perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) { @@ -497,6 +568,9 @@ static struct perf_pmu *pmu_lookup(const char *name) if (pmu_aliases(name, &aliases)) return NULL; + if (!strcmp(name, "cpu")) + pmu_add_cpu_aliases(&aliases); + if (pmu_type(name, &type)) return NULL; @@ -983,21 +1057,63 @@ static char *format_alias_or(char *buf, int len, struct perf_pmu *pmu, return buf; } -static int cmp_string(const void *a, const void *b) +struct sevent { + char *name; + char *desc; + char *topic; +}; + +static int cmp_sevent(const void *a, const void *b) { - const char * const *as = a; - const char * const *bs = b; - return strcmp(*as, *bs); + const struct sevent *as = a; + const struct sevent *bs = b; + + /* Put extra events last */ + if (!!as->desc != !!bs->desc) + return !!as->desc - !!bs->desc; + if (as->topic && bs->topic) { + int n = strcmp(as->topic, bs->topic); + + if (n) + return n; + } + return strcmp(as->name, bs->name); } -void print_pmu_events(const char *event_glob, bool name_only) +static void wordwrap(char *s, int start, int max, int corr) +{ + int column = start; + int n; + + while (*s) { + int wlen = strcspn(s, " \t"); + + if (column + wlen >= max && column > start) { + printf("\n%*s", start, ""); + column = start + corr; + } + n = printf("%s%.*s", column > start ? " " : "", wlen, s); + if (n <= 0) + break; + s += wlen; + column += n; + while (isspace(*s)) + s++; + } +} + +void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, + bool long_desc) { struct perf_pmu *pmu; struct perf_pmu_alias *alias; char buf[1024]; int printed = 0; int len, j; - char **aliases; + struct sevent *aliases; + int numdesc = 0; + int columns = pager_get_columns(); + char *topic = NULL; pmu = NULL; len = 0; @@ -1007,14 +1123,15 @@ void print_pmu_events(const char *event_glob, bool name_only) if (pmu->selectable) len++; } - aliases = zalloc(sizeof(char *) * len); + aliases = zalloc(sizeof(struct sevent) * len); if (!aliases) goto out_enomem; pmu = NULL; j = 0; while ((pmu = perf_pmu__scan(pmu)) != NULL) { list_for_each_entry(alias, &pmu->aliases, list) { - char *name = format_alias(buf, sizeof(buf), pmu, alias); + char *name = alias->desc ? alias->name : + format_alias(buf, sizeof(buf), pmu, alias); bool is_cpu = !strcmp(pmu->name, "cpu"); if (event_glob != NULL && @@ -1023,12 +1140,21 @@ void print_pmu_events(const char *event_glob, bool name_only) event_glob)))) continue; - if (is_cpu && !name_only) + if (is_cpu && !name_only && !alias->desc) name = format_alias_or(buf, sizeof(buf), pmu, alias); - aliases[j] = strdup(name); - if (aliases[j] == NULL) + aliases[j].name = name; + if (is_cpu && !name_only && !alias->desc) + aliases[j].name = format_alias_or(buf, + sizeof(buf), + pmu, alias); + aliases[j].name = strdup(aliases[j].name); + if (!aliases[j].name) goto out_enomem; + + aliases[j].desc = long_desc ? alias->long_desc : + alias->desc; + aliases[j].topic = alias->topic; j++; } if (pmu->selectable && @@ -1036,25 +1162,39 @@ void print_pmu_events(const char *event_glob, bool name_only) char *s; if (asprintf(&s, "%s//", pmu->name) < 0) goto out_enomem; - aliases[j] = s; + aliases[j].name = s; j++; } } len = j; - qsort(aliases, len, sizeof(char *), cmp_string); + qsort(aliases, len, sizeof(struct sevent), cmp_sevent); for (j = 0; j < len; j++) { if (name_only) { - printf("%s ", aliases[j]); + printf("%s ", aliases[j].name); continue; } - printf(" %-50s [Kernel PMU event]\n", aliases[j]); + if (aliases[j].desc && !quiet_flag) { + if (numdesc++ == 0) + printf("\n"); + if (aliases[j].topic && (!topic || + strcmp(topic, aliases[j].topic))) { + printf("%s%s:\n", topic ? "\n" : "", + aliases[j].topic); + topic = aliases[j].topic; + } + printf(" %-50s\n", aliases[j].name); + printf("%*s", 8, "["); + wordwrap(aliases[j].desc, 8, columns, 0); + printf("]\n"); + } else + printf(" %-50s [Kernel PMU event]\n", aliases[j].name); printed++; } if (printed && pager_in_use()) printf("\n"); out_free: for (j = 0; j < len; j++) - zfree(&aliases[j]); + zfree(&aliases[j].name); zfree(&aliases); return; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 743422ad900b..25712034c815 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -40,6 +40,9 @@ struct perf_pmu_info { struct perf_pmu_alias { char *name; + char *desc; + char *long_desc; + char *topic; struct list_head terms; /* HEAD struct parse_events_term -> list */ struct list_head list; /* ELEM */ char unit[UNIT_MAX_LEN+1]; @@ -71,7 +74,8 @@ int perf_pmu__format_parse(char *dir, struct list_head *head); struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); -void print_pmu_events(const char *event_glob, bool name_only); +void print_pmu_events(const char *event_glob, bool name_only, bool quiet, + bool long_desc); bool pmu_have_event(const char *pname, const char *name); int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index fcfbef07b92d..d281ae2b54e8 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -213,7 +213,7 @@ static int convert_exec_to_group(const char *exec, char **result) goto out; } - for (ptr2 = ptr1; ptr2 != '\0'; ptr2++) { + for (ptr2 = ptr1; *ptr2 != '\0'; ptr2++) { if (!isalnum(*ptr2) && *ptr2 != '_') { *ptr2 = '\0'; break; diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h index b268a6648a5d..318424ea561d 100644 --- a/tools/perf/util/strbuf.h +++ b/tools/perf/util/strbuf.h @@ -66,9 +66,8 @@ static inline ssize_t strbuf_avail(const struct strbuf *sb) { int strbuf_grow(struct strbuf *buf, size_t); static inline int strbuf_setlen(struct strbuf *sb, size_t len) { - int ret; if (!sb->alloc) { - ret = strbuf_grow(sb, 0); + int ret = strbuf_grow(sb, 0); if (ret) return ret; } diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 8b10a55410a2..f5af87f66663 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -14,13 +14,12 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine) { - struct thread *leader; pid_t pid = thread->pid_; if (pid == thread->tid || pid == -1) { thread->mg = map_groups__new(machine); } else { - leader = __machine__findnew_thread(machine, pid, pid); + struct thread *leader = __machine__findnew_thread(machine, pid, pid); if (leader) { thread->mg = map_groups__get(leader->mg); thread__put(leader); @@ -130,11 +129,10 @@ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp, bool exec) { struct comm *new, *curr = thread__comm(thread); - int err; /* Override the default :tid entry */ if (!thread->comm_set) { - err = comm__override(curr, str, timestamp, exec); + int err = comm__override(curr, str, timestamp, exec); if (err) return err; } else { @@ -270,10 +268,9 @@ static int thread__clone_map_groups(struct thread *thread, int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp) { - int err; - if (parent->comm_set) { const char *comm = thread__comm_str(parent); + int err; if (!comm) return -ENOMEM; err = thread__set_comm(thread, comm, timestamp); |