diff options
Diffstat (limited to 'tools/perf/util/evsel.c')
| -rw-r--r-- | tools/perf/util/evsel.c | 654 |
1 files changed, 404 insertions, 250 deletions
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 8606175fe1e8..33e3fd8c2e68 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -15,6 +15,8 @@ #include <linux/perf_event.h> #include <sys/resource.h> #include "asm/bug.h" +#include "callchain.h" +#include "cgroup.h" #include "evsel.h" #include "evlist.h" #include "util.h" @@ -29,8 +31,55 @@ static struct { bool sample_id_all; bool exclude_guest; bool mmap2; + bool cloexec; + bool clockid; + bool clockid_wrong; } perf_missing_features; +static clockid_t clockid; + +static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused) +{ + return 0; +} + +static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused) +{ +} + +static struct { + size_t size; + int (*init)(struct perf_evsel *evsel); + void (*fini)(struct perf_evsel *evsel); +} perf_evsel__object = { + .size = sizeof(struct perf_evsel), + .init = perf_evsel__no_extra_init, + .fini = perf_evsel__no_extra_fini, +}; + +int perf_evsel__object_config(size_t object_size, + int (*init)(struct perf_evsel *evsel), + void (*fini)(struct perf_evsel *evsel)) +{ + + if (object_size == 0) + goto set_methods; + + if (perf_evsel__object.size > object_size) + return -EINVAL; + + perf_evsel__object.size = object_size; + +set_methods: + if (init != NULL) + perf_evsel__object.init = init; + + if (fini != NULL) + perf_evsel__object.fini = fini; + + return 0; +} + #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) int __perf_evsel__sample_size(u64 sample_type) @@ -115,16 +164,6 @@ void perf_evsel__calc_id_pos(struct perf_evsel *evsel) evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type); } -void hists__init(struct hists *hists) -{ - memset(hists, 0, sizeof(*hists)); - hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT; - hists->entries_in = &hists->entries_in_array[0]; - hists->entries_collapsed = RB_ROOT; - hists->entries = RB_ROOT; - pthread_mutex_init(&hists->lock, NULL); -} - void __perf_evsel__set_sample_bit(struct perf_evsel *evsel, enum perf_event_sample_format bit) { @@ -161,19 +200,20 @@ void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr, int idx) { evsel->idx = idx; + evsel->tracking = !idx; evsel->attr = *attr; evsel->leader = evsel; evsel->unit = ""; evsel->scale = 1.0; INIT_LIST_HEAD(&evsel->node); - hists__init(&evsel->hists); + perf_evsel__object.init(evsel); evsel->sample_size = __perf_evsel__sample_size(attr->sample_type); perf_evsel__calc_id_pos(evsel); } struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) { - struct perf_evsel *evsel = zalloc(sizeof(*evsel)); + struct perf_evsel *evsel = zalloc(perf_evsel__object.size); if (evsel != NULL) perf_evsel__init(evsel, attr, idx); @@ -183,7 +223,7 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx) { - struct perf_evsel *evsel = zalloc(sizeof(*evsel)); + struct perf_evsel *evsel = zalloc(perf_evsel__object.size); if (evsel != NULL) { struct perf_event_attr attr = { @@ -509,12 +549,28 @@ perf_evsel__config_callgraph(struct perf_evsel *evsel, perf_evsel__set_sample_bit(evsel, CALLCHAIN); - if (opts->call_graph == CALLCHAIN_DWARF) { + if (callchain_param.record_mode == CALLCHAIN_LBR) { + if (!opts->branch_stack) { + if (attr->exclude_user) { + pr_warning("LBR callstack option is only available " + "to get user callchain information. " + "Falling back to framepointers.\n"); + } else { + perf_evsel__set_sample_bit(evsel, BRANCH_STACK); + attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER | + PERF_SAMPLE_BRANCH_CALL_STACK; + } + } else + pr_warning("Cannot use LBR callstack with branch stack. " + "Falling back to framepointers.\n"); + } + + if (callchain_param.record_mode == CALLCHAIN_DWARF) { if (!function) { perf_evsel__set_sample_bit(evsel, REGS_USER); perf_evsel__set_sample_bit(evsel, STACK_USER); attr->sample_regs_user = PERF_REGS_MASK; - attr->sample_stack_user = opts->stack_dump_size; + attr->sample_stack_user = callchain_param.dump_size; attr->exclude_callchain_user = 1; } else { pr_info("Cannot use DWARF unwind for function trace event," @@ -560,7 +616,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) { struct perf_evsel *leader = evsel->leader; struct perf_event_attr *attr = &evsel->attr; - int track = !evsel->idx; /* only the first counter needs these */ + int track = evsel->tracking; bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread; attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1; @@ -623,21 +679,37 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->mmap_data = track; } - if (opts->call_graph_enabled) + /* + * We don't allow user space callchains for function trace + * event, due to issues with page faults while tracing page + * fault handler and its overall trickiness nature. + */ + if (perf_evsel__is_function_event(evsel)) + evsel->attr.exclude_callchain_user = 1; + + if (callchain_param.enabled && !evsel->no_aux_samples) perf_evsel__config_callgraph(evsel, opts); + if (opts->sample_intr_regs) { + attr->sample_regs_intr = PERF_REGS_MASK; + perf_evsel__set_sample_bit(evsel, REGS_INTR); + } + if (target__has_cpu(&opts->target)) perf_evsel__set_sample_bit(evsel, CPU); if (opts->period) perf_evsel__set_sample_bit(evsel, PERIOD); - if (!perf_missing_features.sample_id_all && - (opts->sample_time || !opts->no_inherit || - target__has_cpu(&opts->target) || per_cpu)) + /* + * When the user explicitely disabled time don't force it here. + */ + if (opts->sample_time && + (!perf_missing_features.sample_id_all && + (!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu))) perf_evsel__set_sample_bit(evsel, TIME); - if (opts->raw_samples) { + if (opts->raw_samples && !evsel->no_aux_samples) { perf_evsel__set_sample_bit(evsel, TIME); perf_evsel__set_sample_bit(evsel, RAW); perf_evsel__set_sample_bit(evsel, CPU); @@ -650,7 +722,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) attr->watermark = 0; attr->wakeup_events = 1; } - if (opts->branch_stack) { + if (opts->branch_stack && !evsel->no_aux_samples) { perf_evsel__set_sample_bit(evsel, BRANCH_STACK); attr->branch_sample_type = opts->branch_stack; } @@ -658,6 +730,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (opts->sample_weight) perf_evsel__set_sample_bit(evsel, WEIGHT); + attr->task = track; attr->mmap = track; attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; @@ -665,6 +738,12 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (opts->sample_transaction) perf_evsel__set_sample_bit(evsel, TRANSACTION); + if (opts->running_time) { + evsel->attr.read_format |= + PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING; + } + /* * XXX see the function comment above * @@ -681,11 +760,26 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) && !opts->initial_delay) attr->enable_on_exec = 1; + + if (evsel->immediate) { + attr->disabled = 0; + attr->enable_on_exec = 0; + } + + clockid = opts->clockid; + if (opts->use_clockid) { + attr->use_clockid = 1; + attr->clockid = opts->clockid; + } } -int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) +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) { @@ -704,6 +798,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea { int cpu, thread; + if (evsel->system_wide) + nthreads = 1; + for (cpu = 0; cpu < ncpus; cpu++) { for (thread = 0; thread < nthreads; thread++) { int fd = FD(evsel, cpu, thread), @@ -734,6 +831,12 @@ int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads) int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) { + if (ncpus == 0 || nthreads == 0) + return 0; + + if (evsel->system_wide) + nthreads = 1; + evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id)); if (evsel->sample_id == NULL) return -ENOMEM; @@ -761,13 +864,13 @@ int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus) return evsel->counts != NULL ? 0 : -ENOMEM; } -void perf_evsel__free_fd(struct perf_evsel *evsel) +static void perf_evsel__free_fd(struct perf_evsel *evsel) { xyarray__delete(evsel->fd); evsel->fd = NULL; } -void perf_evsel__free_id(struct perf_evsel *evsel) +static void perf_evsel__free_id(struct perf_evsel *evsel) { xyarray__delete(evsel->sample_id); evsel->sample_id = NULL; @@ -778,6 +881,9 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { int cpu, thread; + if (evsel->system_wide) + nthreads = 1; + for (cpu = 0; cpu < ncpus; cpu++) for (thread = 0; thread < nthreads; ++thread) { close(FD(evsel, cpu, thread)); @@ -795,22 +901,20 @@ void perf_evsel__exit(struct perf_evsel *evsel) assert(list_empty(&evsel->node)); perf_evsel__free_fd(evsel); perf_evsel__free_id(evsel); + close_cgroup(evsel->cgrp); + zfree(&evsel->group_name); + zfree(&evsel->name); + perf_evsel__object.fini(evsel); } void perf_evsel__delete(struct perf_evsel *evsel) { perf_evsel__exit(evsel); - close_cgroup(evsel->cgrp); - zfree(&evsel->group_name); - if (evsel->tp_format) - pevent_free_format(evsel->tp_format); - zfree(&evsel->name); free(evsel); } -static inline void compute_deltas(struct perf_evsel *evsel, - int cpu, - struct perf_counts_values *count) +void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, + struct perf_counts_values *count) { struct perf_counts_values tmp; @@ -830,78 +934,60 @@ static inline void compute_deltas(struct perf_evsel *evsel, count->run = count->run - tmp.run; } -int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, - int cpu, int thread, bool scale) +void perf_counts_values__scale(struct perf_counts_values *count, + bool scale, s8 *pscaled) { - struct perf_counts_values count; - size_t nv = scale ? 3 : 1; - - if (FD(evsel, cpu, thread) < 0) - return -EINVAL; - - if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0) - return -ENOMEM; - - if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0) - return -errno; - - compute_deltas(evsel, cpu, &count); + s8 scaled = 0; if (scale) { - if (count.run == 0) - count.val = 0; - else if (count.run < count.ena) - count.val = (u64)((double)count.val * count.ena / count.run + 0.5); + if (count->run == 0) { + scaled = -1; + count->val = 0; + } else if (count->run < count->ena) { + scaled = 1; + count->val = (u64)((double) count->val * count->ena / count->run + 0.5); + } } else - count.ena = count.run = 0; + count->ena = count->run = 0; - evsel->counts->cpu[cpu] = count; - return 0; + if (pscaled) + *pscaled = scaled; } -int __perf_evsel__read(struct perf_evsel *evsel, - int ncpus, int nthreads, bool scale) +int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread, + perf_evsel__read_cb_t cb) { - size_t nv = scale ? 3 : 1; - int cpu, thread; - struct perf_counts_values *aggr = &evsel->counts->aggr, count; + struct perf_counts_values count; - aggr->val = aggr->ena = aggr->run = 0; + memset(&count, 0, sizeof(count)); - for (cpu = 0; cpu < ncpus; cpu++) { - for (thread = 0; thread < nthreads; thread++) { - if (FD(evsel, cpu, thread) < 0) - continue; + if (FD(evsel, cpu, thread) < 0) + return -EINVAL; - if (readn(FD(evsel, cpu, thread), - &count, nv * sizeof(u64)) < 0) - return -errno; + if (readn(FD(evsel, cpu, thread), &count, sizeof(count)) < 0) + return -errno; - aggr->val += count.val; - if (scale) { - aggr->ena += count.ena; - aggr->run += count.run; - } - } - } + return cb(evsel, cpu, thread, &count); +} + +int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, + int cpu, int thread, bool scale) +{ + struct perf_counts_values count; + size_t nv = scale ? 3 : 1; - compute_deltas(evsel, -1, aggr); + if (FD(evsel, cpu, thread) < 0) + return -EINVAL; - evsel->counts->scaled = 0; - if (scale) { - if (aggr->run == 0) { - evsel->counts->scaled = -1; - aggr->val = 0; - return 0; - } + if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0) + return -ENOMEM; - if (aggr->run < aggr->ena) { - evsel->counts->scaled = 1; - aggr->val = (u64)((double)aggr->val * aggr->ena / aggr->run + 0.5); - } - } else - aggr->ena = aggr->run = 0; + if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0) + return -errno; + perf_evsel__compute_deltas(evsel, cpu, &count); + perf_counts_values__scale(&count, scale, NULL); + evsel->counts->cpu[cpu] = count; return 0; } @@ -925,84 +1011,157 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread) return fd; } -#define __PRINT_ATTR(fmt, cast, field) \ - fprintf(fp, " %-19s "fmt"\n", #field, cast attr->field) - -#define PRINT_ATTR_U32(field) __PRINT_ATTR("%u" , , field) -#define PRINT_ATTR_X32(field) __PRINT_ATTR("%#x", , field) -#define PRINT_ATTR_U64(field) __PRINT_ATTR("%" PRIu64, (uint64_t), field) -#define PRINT_ATTR_X64(field) __PRINT_ATTR("%#"PRIx64, (uint64_t), field) - -#define PRINT_ATTR2N(name1, field1, name2, field2) \ - fprintf(fp, " %-19s %u %-19s %u\n", \ - name1, attr->field1, name2, attr->field2) - -#define PRINT_ATTR2(field1, field2) \ - PRINT_ATTR2N(#field1, field1, #field2, field2) - -static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp) -{ - size_t ret = 0; - - ret += fprintf(fp, "%.60s\n", graph_dotted_line); - ret += fprintf(fp, "perf_event_attr:\n"); - - ret += PRINT_ATTR_U32(type); - ret += PRINT_ATTR_U32(size); - ret += PRINT_ATTR_X64(config); - ret += PRINT_ATTR_U64(sample_period); - ret += PRINT_ATTR_U64(sample_freq); - ret += PRINT_ATTR_X64(sample_type); - ret += PRINT_ATTR_X64(read_format); - - ret += PRINT_ATTR2(disabled, inherit); - ret += PRINT_ATTR2(pinned, exclusive); - ret += PRINT_ATTR2(exclude_user, exclude_kernel); - ret += PRINT_ATTR2(exclude_hv, exclude_idle); - ret += PRINT_ATTR2(mmap, comm); - ret += PRINT_ATTR2(freq, inherit_stat); - ret += PRINT_ATTR2(enable_on_exec, task); - ret += PRINT_ATTR2(watermark, precise_ip); - ret += PRINT_ATTR2(mmap_data, sample_id_all); - ret += PRINT_ATTR2(exclude_host, exclude_guest); - ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel, - "excl.callchain_user", exclude_callchain_user); - ret += PRINT_ATTR_U32(mmap2); - - ret += PRINT_ATTR_U32(wakeup_events); - ret += PRINT_ATTR_U32(wakeup_watermark); - ret += PRINT_ATTR_X32(bp_type); - ret += PRINT_ATTR_X64(bp_addr); - ret += PRINT_ATTR_X64(config1); - ret += PRINT_ATTR_U64(bp_len); - ret += PRINT_ATTR_X64(config2); - ret += PRINT_ATTR_X64(branch_sample_type); - ret += PRINT_ATTR_X64(sample_regs_user); - ret += PRINT_ATTR_U32(sample_stack_user); - - ret += fprintf(fp, "%.60s\n", graph_dotted_line); +struct bit_names { + int bit; + const char *name; +}; + +static void __p_bits(char *buf, size_t size, u64 value, struct bit_names *bits) +{ + bool first_bit = true; + int i = 0; + + do { + if (value & bits[i].bit) { + buf += scnprintf(buf, size, "%s%s", first_bit ? "" : "|", bits[i].name); + first_bit = false; + } + } while (bits[++i].name != NULL); +} + +static void __p_sample_type(char *buf, size_t size, u64 value) +{ +#define bit_name(n) { PERF_SAMPLE_##n, #n } + struct bit_names bits[] = { + bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR), + bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU), + bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), + bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), + bit_name(IDENTIFIER), bit_name(REGS_INTR), + { .name = NULL, } + }; +#undef bit_name + __p_bits(buf, size, value, bits); +} + +static void __p_read_format(char *buf, size_t size, u64 value) +{ +#define bit_name(n) { PERF_FORMAT_##n, #n } + struct bit_names bits[] = { + bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING), + bit_name(ID), bit_name(GROUP), + { .name = NULL, } + }; +#undef bit_name + __p_bits(buf, size, value, bits); +} + +#define BUF_SIZE 1024 + +#define p_hex(val) snprintf(buf, BUF_SIZE, "%"PRIx64, (uint64_t)(val)) +#define p_unsigned(val) snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val)) +#define p_signed(val) snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val)) +#define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val) +#define p_read_format(val) __p_read_format(buf, BUF_SIZE, val) + +#define PRINT_ATTRn(_n, _f, _p) \ +do { \ + if (attr->_f) { \ + _p(attr->_f); \ + ret += attr__fprintf(fp, _n, buf, priv);\ + } \ +} while (0) + +#define PRINT_ATTRf(_f, _p) PRINT_ATTRn(#_f, _f, _p) + +int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, + attr__fprintf_f attr__fprintf, void *priv) +{ + char buf[BUF_SIZE]; + int ret = 0; + + PRINT_ATTRf(type, p_unsigned); + PRINT_ATTRf(size, p_unsigned); + PRINT_ATTRf(config, p_hex); + PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned); + PRINT_ATTRf(sample_type, p_sample_type); + PRINT_ATTRf(read_format, p_read_format); + + PRINT_ATTRf(disabled, p_unsigned); + PRINT_ATTRf(inherit, p_unsigned); + PRINT_ATTRf(pinned, p_unsigned); + PRINT_ATTRf(exclusive, p_unsigned); + PRINT_ATTRf(exclude_user, p_unsigned); + PRINT_ATTRf(exclude_kernel, p_unsigned); + PRINT_ATTRf(exclude_hv, p_unsigned); + PRINT_ATTRf(exclude_idle, p_unsigned); + PRINT_ATTRf(mmap, p_unsigned); + PRINT_ATTRf(comm, p_unsigned); + PRINT_ATTRf(freq, p_unsigned); + PRINT_ATTRf(inherit_stat, p_unsigned); + PRINT_ATTRf(enable_on_exec, p_unsigned); + PRINT_ATTRf(task, p_unsigned); + PRINT_ATTRf(watermark, p_unsigned); + PRINT_ATTRf(precise_ip, p_unsigned); + PRINT_ATTRf(mmap_data, p_unsigned); + PRINT_ATTRf(sample_id_all, p_unsigned); + PRINT_ATTRf(exclude_host, p_unsigned); + PRINT_ATTRf(exclude_guest, p_unsigned); + PRINT_ATTRf(exclude_callchain_kernel, p_unsigned); + PRINT_ATTRf(exclude_callchain_user, p_unsigned); + PRINT_ATTRf(mmap2, p_unsigned); + PRINT_ATTRf(comm_exec, p_unsigned); + PRINT_ATTRf(use_clockid, p_unsigned); + + PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned); + PRINT_ATTRf(bp_type, p_unsigned); + PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex); + PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex); + PRINT_ATTRf(sample_regs_user, p_hex); + PRINT_ATTRf(sample_stack_user, p_unsigned); + PRINT_ATTRf(clockid, p_signed); + PRINT_ATTRf(sample_regs_intr, p_hex); return ret; } +static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, + void *priv __attribute__((unused))) +{ + return fprintf(fp, " %-32s %s\n", name, val); +} + static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { - int cpu, thread; - unsigned long flags = 0; + int cpu, thread, nthreads; + unsigned long flags = PERF_FLAG_FD_CLOEXEC; int pid = -1, err; enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE; + if (evsel->system_wide) + nthreads = 1; + else + nthreads = threads->nr; + if (evsel->fd == NULL && - perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0) + perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0) return -ENOMEM; if (evsel->cgrp) { - flags = PERF_FLAG_PID_CGROUP; + flags |= PERF_FLAG_PID_CGROUP; pid = evsel->cgrp->fd; } fallback_missing_features: + if (perf_missing_features.clockid_wrong) + evsel->attr.clockid = CLOCK_MONOTONIC; /* should always work */ + if (perf_missing_features.clockid) { + evsel->attr.use_clockid = 0; + evsel->attr.clockid = 0; + } + if (perf_missing_features.cloexec) + flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC; if (perf_missing_features.mmap2) evsel->attr.mmap2 = 0; if (perf_missing_features.exclude_guest) @@ -1011,15 +1170,19 @@ retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; - if (verbose >= 2) - perf_event_attr__fprintf(&evsel->attr, stderr); + if (verbose >= 2) { + fprintf(stderr, "%.60s\n", graph_dotted_line); + fprintf(stderr, "perf_event_attr:\n"); + perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL); + fprintf(stderr, "%.60s\n", graph_dotted_line); + } for (cpu = 0; cpu < cpus->nr; cpu++) { - for (thread = 0; thread < threads->nr; thread++) { + for (thread = 0; thread < nthreads; thread++) { int group_fd; - if (!evsel->cgrp) + if (!evsel->cgrp && !evsel->system_wide) pid = threads->map[thread]; group_fd = get_group_fd(evsel, cpu, thread); @@ -1038,6 +1201,17 @@ retry_open: goto try_fallback; } set_rlimit = NO_CHANGE; + + /* + * If we succeeded but had to kill clockid, fail and + * have perf_evsel__open_strerror() print us a nice + * error. + */ + if (perf_missing_features.clockid || + perf_missing_features.clockid_wrong) { + err = -EINVAL; + goto out_close; + } } } @@ -1071,7 +1245,20 @@ try_fallback: if (err != -EINVAL || cpu > 0 || thread > 0) goto out_close; - if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { + /* + * Must probe features in the order they were added to the + * perf_event_attr interface. + */ + if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) { + perf_missing_features.clockid_wrong = true; + goto fallback_missing_features; + } else if (!perf_missing_features.clockid && evsel->attr.use_clockid) { + perf_missing_features.clockid = true; + goto fallback_missing_features; + } else if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) { + perf_missing_features.cloexec = true; + goto fallback_missing_features; + } else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) { perf_missing_features.mmap2 = true; goto fallback_missing_features; } else if (!perf_missing_features.exclude_guest && @@ -1089,7 +1276,7 @@ out_close: close(FD(evsel, cpu, thread)); FD(evsel, cpu, thread) = -1; } - thread = threads->nr; + thread = nthreads; } while (--cpu >= 0); return err; } @@ -1468,6 +1655,23 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, array++; } + data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE; + if (type & PERF_SAMPLE_REGS_INTR) { + OVERFLOW_CHECK_u64(array); + data->intr_regs.abi = *array; + array++; + + if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) { + u64 mask = evsel->attr.sample_regs_intr; + + sz = hweight_long(mask) * sizeof(u64); + OVERFLOW_CHECK(array, sz, max_size); + data->intr_regs.mask = mask; + data->intr_regs.regs = (u64 *)array; + array = (void *)array + sz; + } + } + return 0; } @@ -1563,6 +1767,16 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_TRANSACTION) result += sizeof(u64); + if (type & PERF_SAMPLE_REGS_INTR) { + if (sample->intr_regs.abi) { + result += sizeof(u64); + sz = hweight_long(sample->intr_regs.mask) * sizeof(u64); + result += sz; + } else { + result += sizeof(u64); + } + } + return result; } @@ -1741,6 +1955,17 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, array++; } + if (type & PERF_SAMPLE_REGS_INTR) { + if (sample->intr_regs.abi) { + *array++ = sample->intr_regs.abi; + sz = hweight_long(sample->intr_regs.mask) * sizeof(u64); + memcpy(array, sample->intr_regs.regs, sz); + array = (void *)array + sz; + } else { + *array++ = 0; + } + } + return 0; } @@ -1790,7 +2015,7 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, value = *(u32 *)ptr; break; case 8: - value = *(u64 *)ptr; + memcpy(&value, ptr, sizeof(u64)); break; default: return 0; @@ -1831,62 +2056,9 @@ static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) return ret; } -static int __if_fprintf(FILE *fp, bool *first, const char *field, u64 value) -{ - if (value == 0) - return 0; - - return comma_fprintf(fp, first, " %s: %" PRIu64, field, value); -} - -#define if_print(field) printed += __if_fprintf(fp, &first, #field, evsel->attr.field) - -struct bit_names { - int bit; - const char *name; -}; - -static int bits__fprintf(FILE *fp, const char *field, u64 value, - struct bit_names *bits, bool *first) -{ - int i = 0, printed = comma_fprintf(fp, first, " %s: ", field); - bool first_bit = true; - - do { - if (value & bits[i].bit) { - printed += fprintf(fp, "%s%s", first_bit ? "" : "|", bits[i].name); - first_bit = false; - } - } while (bits[++i].name != NULL); - - return printed; -} - -static int sample_type__fprintf(FILE *fp, bool *first, u64 value) +static int __print_attr__fprintf(FILE *fp, const char *name, const char *val, void *priv) { -#define bit_name(n) { PERF_SAMPLE_##n, #n } - struct bit_names bits[] = { - bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR), - bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU), - bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), - bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), - bit_name(IDENTIFIER), - { .name = NULL, } - }; -#undef bit_name - return bits__fprintf(fp, "sample_type", value, bits, first); -} - -static int read_format__fprintf(FILE *fp, bool *first, u64 value) -{ -#define bit_name(n) { PERF_FORMAT_##n, #n } - struct bit_names bits[] = { - bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING), - bit_name(ID), bit_name(GROUP), - { .name = NULL, } - }; -#undef bit_name - return bits__fprintf(fp, "read_format", value, bits, first); + return comma_fprintf(fp, (bool *)priv, " %s: %s", name, val); } int perf_evsel__fprintf(struct perf_evsel *evsel, @@ -1915,46 +2087,13 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, printed += fprintf(fp, "%s", perf_evsel__name(evsel)); - if (details->verbose || details->freq) { + if (details->verbose) { + printed += perf_event_attr__fprintf(fp, &evsel->attr, + __print_attr__fprintf, &first); + } else if (details->freq) { printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64, (u64)evsel->attr.sample_freq); } - - if (details->verbose) { - if_print(type); - if_print(config); - if_print(config1); - if_print(config2); - if_print(size); - printed += sample_type__fprintf(fp, &first, evsel->attr.sample_type); - if (evsel->attr.read_format) - printed += read_format__fprintf(fp, &first, evsel->attr.read_format); - if_print(disabled); - if_print(inherit); - if_print(pinned); - if_print(exclusive); - if_print(exclude_user); - if_print(exclude_kernel); - if_print(exclude_hv); - if_print(exclude_idle); - if_print(mmap); - if_print(mmap2); - if_print(comm); - if_print(freq); - if_print(inherit_stat); - if_print(enable_on_exec); - if_print(task); - if_print(watermark); - if_print(precise_ip); - if_print(mmap_data); - if_print(sample_id_all); - if_print(exclude_host); - if_print(exclude_guest); - if_print(__reserved_1); - if_print(wakeup_events); - if_print(bp_type); - if_print(branch_sample_type); - } out: fputc('\n', fp); return ++printed; @@ -1990,6 +2129,8 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, int err, char *msg, size_t size) { + char sbuf[STRERR_BUFSIZE]; + switch (err) { case EPERM: case EACCES: @@ -2024,13 +2165,26 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, "No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it."); #endif break; + case EBUSY: + if (find_process("oprofiled")) + return scnprintf(msg, size, + "The PMU counters are busy/taken by another profiler.\n" + "We found oprofile daemon running, please stop it and try again."); + break; + case EINVAL: + if (perf_missing_features.clockid) + return scnprintf(msg, size, "clockid feature not supported."); + if (perf_missing_features.clockid_wrong) + return scnprintf(msg, size, "wrong clockid (%d).", clockid); + break; default: break; } return scnprintf(msg, size, - "The sys_perf_event_open() syscall returned with %d (%s) for event (%s). \n" + "The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n" "/bin/dmesg may provide additional information.\n" "No CONFIG_PERF_EVENTS=y kernel support configured?\n", - err, strerror(err), perf_evsel__name(evsel)); + err, strerror_r(err, sbuf, sizeof(sbuf)), + perf_evsel__name(evsel)); } |
