diff options
Diffstat (limited to 'tools/perf')
-rw-r--r-- | tools/perf/tests/cpumap.c | 19 | ||||
-rw-r--r-- | tools/perf/tests/sample-parsing.c | 14 | ||||
-rw-r--r-- | tools/perf/trace/beauty/include/linux/socket.h | 16 | ||||
-rw-r--r-- | tools/perf/util/cpumap.c | 80 | ||||
-rw-r--r-- | tools/perf/util/cpumap.h | 4 | ||||
-rw-r--r-- | tools/perf/util/event.h | 25 | ||||
-rw-r--r-- | tools/perf/util/evsel.c | 29 | ||||
-rw-r--r-- | tools/perf/util/scripting-engines/trace-event-python.c | 19 | ||||
-rw-r--r-- | tools/perf/util/session.c | 65 | ||||
-rw-r--r-- | tools/perf/util/synthetic-events.c | 99 | ||||
-rw-r--r-- | tools/perf/util/synthetic-events.h | 2 |
11 files changed, 240 insertions, 132 deletions
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index f94929ebb54b..7ea150cdc137 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -17,21 +17,23 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused, struct machine *machine __maybe_unused) { struct perf_record_cpu_map *map_event = &event->cpu_map; - struct perf_record_record_cpu_map *mask; struct perf_record_cpu_map_data *data; struct perf_cpu_map *map; int i; + unsigned int long_size; data = &map_event->data; TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__MASK); - mask = (struct perf_record_record_cpu_map *)data->data; + long_size = data->mask32_data.long_size; - TEST_ASSERT_VAL("wrong nr", mask->nr == 1); + TEST_ASSERT_VAL("wrong long_size", long_size == 4 || long_size == 8); + + TEST_ASSERT_VAL("wrong nr", data->mask32_data.nr == 1); for (i = 0; i < 20; i++) { - TEST_ASSERT_VAL("wrong cpu", test_bit(i, mask->mask)); + TEST_ASSERT_VAL("wrong cpu", perf_record_cpu_map_data__test_bit(i, data)); } map = cpu_map__new_data(data); @@ -51,7 +53,6 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, struct machine *machine __maybe_unused) { struct perf_record_cpu_map *map_event = &event->cpu_map; - struct cpu_map_entries *cpus; struct perf_record_cpu_map_data *data; struct perf_cpu_map *map; @@ -59,11 +60,9 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__CPUS); - cpus = (struct cpu_map_entries *)data->data; - - TEST_ASSERT_VAL("wrong nr", cpus->nr == 2); - TEST_ASSERT_VAL("wrong cpu", cpus->cpu[0] == 1); - TEST_ASSERT_VAL("wrong cpu", cpus->cpu[1] == 256); + TEST_ASSERT_VAL("wrong nr", data->cpus_data.nr == 2); + TEST_ASSERT_VAL("wrong cpu", data->cpus_data.cpu[0] == 1); + TEST_ASSERT_VAL("wrong cpu", data->cpus_data.cpu[1] == 256); map = cpu_map__new_data(data); TEST_ASSERT_VAL("wrong nr", perf_cpu_map__nr(map) == 2); diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 07f2411b0ad4..20930dd48ee0 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -86,10 +86,15 @@ static bool samples_same(const struct perf_sample *s1, COMP(read.time_running); /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ if (read_format & PERF_FORMAT_GROUP) { - for (i = 0; i < s1->read.group.nr; i++) - MCOMP(read.group.values[i]); + for (i = 0; i < s1->read.group.nr; i++) { + /* FIXME: check values without LOST */ + if (read_format & PERF_FORMAT_LOST) + MCOMP(read.group.values[i]); + } } else { COMP(read.one.id); + if (read_format & PERF_FORMAT_LOST) + COMP(read.one.lost); } } @@ -263,7 +268,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) .data = (void *)aux_data, }, }; - struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},}; + struct sample_read_value values[] = {{1, 5, 0}, {9, 3, 0}, {2, 7, 0}, {6, 4, 1},}; struct perf_sample sample_out, sample_out_endian; size_t i, sz, bufsz; int err, ret = -1; @@ -286,6 +291,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) } else { sample.read.one.value = 0x08789faeb786aa87ULL; sample.read.one.id = 99; + sample.read.one.lost = 1; } sz = perf_event__sample_event_size(&sample, sample_type, read_format); @@ -370,7 +376,7 @@ out_free: */ static int test__sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { - const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15}; + const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15, 20, 21, 22, 28, 29, 30, 31}; u64 sample_type; u64 sample_regs; size_t i; diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 17311ad9f9af..de3701a2a212 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -14,6 +14,8 @@ struct file; struct pid; struct cred; struct socket; +struct sock; +struct sk_buff; #define __sockaddr_check_size(size) \ BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage))) @@ -69,6 +71,9 @@ struct msghdr { unsigned int msg_flags; /* flags on received message */ __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ + struct ubuf_info *msg_ubuf; + int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb, + struct iov_iter *from, size_t length); }; struct user_msghdr { @@ -416,10 +421,9 @@ extern int recvmsg_copy_msghdr(struct msghdr *msg, struct user_msghdr __user *umsg, unsigned flags, struct sockaddr __user **uaddr, struct iovec **iov); -extern int __copy_msghdr_from_user(struct msghdr *kmsg, - struct user_msghdr __user *umsg, - struct sockaddr __user **save_addr, - struct iovec __user **uiov, size_t *nsegs); +extern int __copy_msghdr(struct msghdr *kmsg, + struct user_msghdr *umsg, + struct sockaddr __user **save_addr); /* helpers which do the actual work for syscalls */ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, @@ -428,10 +432,6 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); -extern int __sys_accept4_file(struct file *file, unsigned file_flags, - struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags, - unsigned long nofile); extern struct file *do_accept(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 12b2243222b0..ae43fb88f444 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -22,54 +22,102 @@ static int max_node_num; */ static int *cpunode_map; -static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus) +bool perf_record_cpu_map_data__test_bit(int i, + const struct perf_record_cpu_map_data *data) +{ + int bit_word32 = i / 32; + __u32 bit_mask32 = 1U << (i & 31); + int bit_word64 = i / 64; + __u64 bit_mask64 = ((__u64)1) << (i & 63); + + return (data->mask32_data.long_size == 4) + ? (bit_word32 < data->mask32_data.nr) && + (data->mask32_data.mask[bit_word32] & bit_mask32) != 0 + : (bit_word64 < data->mask64_data.nr) && + (data->mask64_data.mask[bit_word64] & bit_mask64) != 0; +} + +/* Read ith mask value from data into the given 64-bit sized bitmap */ +static void perf_record_cpu_map_data__read_one_mask(const struct perf_record_cpu_map_data *data, + int i, unsigned long *bitmap) +{ +#if __SIZEOF_LONG__ == 8 + if (data->mask32_data.long_size == 4) + bitmap[0] = data->mask32_data.mask[i]; + else + bitmap[0] = data->mask64_data.mask[i]; +#else + if (data->mask32_data.long_size == 4) { + bitmap[0] = data->mask32_data.mask[i]; + bitmap[1] = 0; + } else { +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + bitmap[0] = (unsigned long)(data->mask64_data.mask[i] >> 32); + bitmap[1] = (unsigned long)data->mask64_data.mask[i]; +#else + bitmap[0] = (unsigned long)data->mask64_data.mask[i]; + bitmap[1] = (unsigned long)(data->mask64_data.mask[i] >> 32); +#endif + } +#endif +} +static struct perf_cpu_map *cpu_map__from_entries(const struct perf_record_cpu_map_data *data) { struct perf_cpu_map *map; - map = perf_cpu_map__empty_new(cpus->nr); + map = perf_cpu_map__empty_new(data->cpus_data.nr); if (map) { unsigned i; - for (i = 0; i < cpus->nr; i++) { + for (i = 0; i < data->cpus_data.nr; i++) { /* * Special treatment for -1, which is not real cpu number, * and we need to use (int) -1 to initialize map[i], * otherwise it would become 65535. */ - if (cpus->cpu[i] == (u16) -1) + if (data->cpus_data.cpu[i] == (u16) -1) map->map[i].cpu = -1; else - map->map[i].cpu = (int) cpus->cpu[i]; + map->map[i].cpu = (int) data->cpus_data.cpu[i]; } } return map; } -static struct perf_cpu_map *cpu_map__from_mask(struct perf_record_record_cpu_map *mask) +static struct perf_cpu_map *cpu_map__from_mask(const struct perf_record_cpu_map_data *data) { + DECLARE_BITMAP(local_copy, 64); + int weight = 0, mask_nr = data->mask32_data.nr; struct perf_cpu_map *map; - int nr, nbits = mask->nr * mask->long_size * BITS_PER_BYTE; - nr = bitmap_weight(mask->mask, nbits); + for (int i = 0; i < mask_nr; i++) { + perf_record_cpu_map_data__read_one_mask(data, i, local_copy); + weight += bitmap_weight(local_copy, 64); + } + + map = perf_cpu_map__empty_new(weight); + if (!map) + return NULL; - map = perf_cpu_map__empty_new(nr); - if (map) { - int cpu, i = 0; + for (int i = 0, j = 0; i < mask_nr; i++) { + int cpus_per_i = (i * data->mask32_data.long_size * BITS_PER_BYTE); + int cpu; - for_each_set_bit(cpu, mask->mask, nbits) - map->map[i++].cpu = cpu; + perf_record_cpu_map_data__read_one_mask(data, i, local_copy); + for_each_set_bit(cpu, local_copy, 64) + map->map[j++].cpu = cpu + cpus_per_i; } return map; } -struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data) +struct perf_cpu_map *cpu_map__new_data(const struct perf_record_cpu_map_data *data) { if (data->type == PERF_CPU_MAP__CPUS) - return cpu_map__from_entries((struct cpu_map_entries *)data->data); + return cpu_map__from_entries(data); else - return cpu_map__from_mask((struct perf_record_record_cpu_map *)data->data); + return cpu_map__from_mask(data); } size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp) diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 703ae6d3386e..fa8a5acdcae1 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -37,9 +37,11 @@ struct cpu_aggr_map { struct perf_record_cpu_map_data; +bool perf_record_cpu_map_data__test_bit(int i, const struct perf_record_cpu_map_data *data); + struct perf_cpu_map *perf_cpu_map__empty_new(int nr); -struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data); +struct perf_cpu_map *cpu_map__new_data(const struct perf_record_cpu_map_data *data); size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size); size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size); size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp); diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index a7b0931d5137..12eae6917022 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -65,7 +65,8 @@ struct stack_dump { struct sample_read_value { u64 value; - u64 id; + u64 id; /* only if PERF_FORMAT_ID */ + u64 lost; /* only if PERF_FORMAT_LOST */ }; struct sample_read { @@ -80,6 +81,24 @@ struct sample_read { }; }; +static inline size_t sample_read_value_size(u64 read_format) +{ + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + if (read_format & PERF_FORMAT_LOST) + return sizeof(struct sample_read_value); + else + return offsetof(struct sample_read_value, lost); +} + +static inline struct sample_read_value * +next_sample_read_value(struct sample_read_value *v, u64 read_format) +{ + return (void *)v + sample_read_value_size(read_format); +} + +#define sample_read_group__for_each(v, nr, rf) \ + for (int __i = 0; __i < (int)nr; v = next_sample_read_value(v, rf), __i++) + struct ip_callchain { u64 nr; u64 ips[]; @@ -463,10 +482,6 @@ size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FIL int kallsyms__get_function_start(const char *kallsyms_filename, const char *symbol_name, u64 *addr); -void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max); -void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map, - u16 type, int max); - void event_attr_init(struct perf_event_attr *attr); int perf_event_paranoid(void); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 4852089e1d79..18c3eb864d55 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1541,7 +1541,7 @@ static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread) } static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread, - u64 val, u64 ena, u64 run) + u64 val, u64 ena, u64 run, u64 lost) { struct perf_counts_values *count; @@ -1550,6 +1550,7 @@ static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread, count->val = val; count->ena = ena; count->run = run; + count->lost = lost; perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true); } @@ -1558,7 +1559,7 @@ static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int { u64 read_format = leader->core.attr.read_format; struct sample_read_value *v; - u64 nr, ena = 0, run = 0, i; + u64 nr, ena = 0, run = 0, lost = 0; nr = *data++; @@ -1571,18 +1572,18 @@ static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) run = *data++; - v = (struct sample_read_value *) data; - - evsel__set_count(leader, cpu_map_idx, thread, v[0].value, ena, run); - - for (i = 1; i < nr; i++) { + v = (void *)data; + sample_read_group__for_each(v, nr, read_format) { struct evsel *counter; - counter = evlist__id2evsel(leader->evlist, v[i].id); + counter = evlist__id2evsel(leader->evlist, v->id); if (!counter) return -EINVAL; - evsel__set_count(counter, cpu_map_idx, thread, v[i].value, ena, run); + if (read_format & PERF_FORMAT_LOST) + lost = v->lost; + + evsel__set_count(counter, cpu_map_idx, thread, v->value, ena, run, lost); } return 0; @@ -2475,8 +2476,8 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, if (data->read.group.nr > max_group_nr) return -EFAULT; - sz = data->read.group.nr * - sizeof(struct sample_read_value); + + sz = data->read.group.nr * sample_read_value_size(read_format); OVERFLOW_CHECK(array, sz, max_size); data->read.group.values = (struct sample_read_value *)array; @@ -2485,6 +2486,12 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, OVERFLOW_CHECK_u64(array); data->read.one.id = *array; array++; + + if (read_format & PERF_FORMAT_LOST) { + OVERFLOW_CHECK_u64(array); + data->read.one.lost = *array; + array++; + } } } diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 9ef2406e0ede..1f2040f36d4e 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -642,15 +642,19 @@ exit: return pylist; } -static PyObject *get_sample_value_as_tuple(struct sample_read_value *value) +static PyObject *get_sample_value_as_tuple(struct sample_read_value *value, + u64 read_format) { PyObject *t; - t = PyTuple_New(2); + t = PyTuple_New(3); if (!t) Py_FatalError("couldn't create Python tuple"); PyTuple_SetItem(t, 0, PyLong_FromUnsignedLongLong(value->id)); PyTuple_SetItem(t, 1, PyLong_FromUnsignedLongLong(value->value)); + if (read_format & PERF_FORMAT_LOST) + PyTuple_SetItem(t, 2, PyLong_FromUnsignedLongLong(value->lost)); + return t; } @@ -681,12 +685,17 @@ static void set_sample_read_in_dict(PyObject *dict_sample, Py_FatalError("couldn't create Python list"); if (read_format & PERF_FORMAT_GROUP) { - for (i = 0; i < sample->read.group.nr; i++) { - PyObject *t = get_sample_value_as_tuple(&sample->read.group.values[i]); + struct sample_read_value *v = sample->read.group.values; + + i = 0; + sample_read_group__for_each(v, sample->read.group.nr, read_format) { + PyObject *t = get_sample_value_as_tuple(v, read_format); PyList_SET_ITEM(values, i, t); + i++; } } else { - PyObject *t = get_sample_value_as_tuple(&sample->read.one); + PyObject *t = get_sample_value_as_tuple(&sample->read.one, + read_format); PyList_SET_ITEM(values, 0, t); } pydict_set_item_string_decref(dict_sample, "values", values); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 98e16659a149..192c9274f7ad 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -916,30 +916,30 @@ static void perf_event__cpu_map_swap(union perf_event *event, bool sample_id_all __maybe_unused) { struct perf_record_cpu_map_data *data = &event->cpu_map.data; - struct cpu_map_entries *cpus; - struct perf_record_record_cpu_map *mask; - unsigned i; data->type = bswap_16(data->type); switch (data->type) { case PERF_CPU_MAP__CPUS: - cpus = (struct cpu_map_entries *)data->data; - - cpus->nr = bswap_16(cpus->nr); + data->cpus_data.nr = bswap_16(data->cpus_data.nr); - for (i = 0; i < cpus->nr; i++) - cpus->cpu[i] = bswap_16(cpus->cpu[i]); + for (unsigned i = 0; i < data->cpus_data.nr; i++) + data->cpus_data.cpu[i] = bswap_16(data->cpus_data.cpu[i]); break; case PERF_CPU_MAP__MASK: - mask = (struct perf_record_record_cpu_map *)data->data; - - mask->nr = bswap_16(mask->nr); - mask->long_size = bswap_16(mask->long_size); + data->mask32_data.long_size = bswap_16(data->mask32_data.long_size); - switch (mask->long_size) { - case 4: mem_bswap_32(&mask->mask, mask->nr); break; - case 8: mem_bswap_64(&mask->mask, mask->nr); break; + switch (data->mask32_data.long_size) { + case 4: + data->mask32_data.nr = bswap_16(data->mask32_data.nr); + for (unsigned i = 0; i < data->mask32_data.nr; i++) + data->mask32_data.mask[i] = bswap_32(data->mask32_data.mask[i]); + break; + case 8: + data->mask64_data.nr = bswap_16(data->mask64_data.nr); + for (unsigned i = 0; i < data->mask64_data.nr; i++) + data->mask64_data.mask[i] = bswap_64(data->mask64_data.mask[i]); + break; default: pr_err("cpu_map swap: unsupported long size\n"); } @@ -1283,21 +1283,25 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format) sample->read.time_running); if (read_format & PERF_FORMAT_GROUP) { - u64 i; + struct sample_read_value *value = sample->read.group.values; printf(".... group nr %" PRIu64 "\n", sample->read.group.nr); - for (i = 0; i < sample->read.group.nr; i++) { - struct sample_read_value *value; - - value = &sample->read.group.values[i]; + sample_read_group__for_each(value, sample->read.group.nr, read_format) { printf("..... id %016" PRIx64 - ", value %016" PRIx64 "\n", + ", value %016" PRIx64, value->id, value->value); + if (read_format & PERF_FORMAT_LOST) + printf(", lost %" PRIu64, value->lost); + printf("\n"); } - } else - printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n", + } else { + printf("..... id %016" PRIx64 ", value %016" PRIx64, sample->read.one.id, sample->read.one.value); + if (read_format & PERF_FORMAT_LOST) + printf(", lost %" PRIu64, sample->read.one.lost); + printf("\n"); + } } static void dump_event(struct evlist *evlist, union perf_event *event, @@ -1411,6 +1415,9 @@ static void dump_read(struct evsel *evsel, union perf_event *event) if (read_format & PERF_FORMAT_ID) printf("... id : %" PRI_lu64 "\n", read_event->id); + + if (read_format & PERF_FORMAT_LOST) + printf("... lost : %" PRI_lu64 "\n", read_event->lost); } static struct machine *machines__find_for_cpumode(struct machines *machines, @@ -1479,14 +1486,14 @@ static int deliver_sample_group(struct evlist *evlist, struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, - struct machine *machine) + struct machine *machine, + u64 read_format) { int ret = -EINVAL; - u64 i; + struct sample_read_value *v = sample->read.group.values; - for (i = 0; i < sample->read.group.nr; i++) { - ret = deliver_sample_value(evlist, tool, event, sample, - &sample->read.group.values[i], + sample_read_group__for_each(v, sample->read.group.nr, read_format) { + ret = deliver_sample_value(evlist, tool, event, sample, v, machine); if (ret) break; @@ -1510,7 +1517,7 @@ static int evlist__deliver_sample(struct evlist *evlist, struct perf_tool *tool, /* For PERF_SAMPLE_READ we have either single or group mode. */ if (read_format & PERF_FORMAT_GROUP) return deliver_sample_group(evlist, tool, event, sample, - machine); + machine, read_format); else return deliver_sample_value(evlist, tool, event, sample, &sample->read.one, machine); diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 2ae59c03ae77..812424dbf2d5 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -1184,52 +1184,48 @@ int perf_event__synthesize_thread_map2(struct perf_tool *tool, return err; } -static void synthesize_cpus(struct cpu_map_entries *cpus, - struct perf_cpu_map *map) +static void synthesize_cpus(struct perf_record_cpu_map_data *data, + const struct perf_cpu_map *map) { int i, map_nr = perf_cpu_map__nr(map); - cpus->nr = map_nr; + data->cpus_data.nr = map_nr; for (i = 0; i < map_nr; i++) - cpus->cpu[i] = perf_cpu_map__cpu(map, i).cpu; + data->cpus_data.cpu[i] = perf_cpu_map__cpu(map, i).cpu; } -static void synthesize_mask(struct perf_record_record_cpu_map *mask, - struct perf_cpu_map *map, int max) +static void synthesize_mask(struct perf_record_cpu_map_data *data, + const struct perf_cpu_map *map, int max) { - int i; + int idx; + struct perf_cpu cpu; + + /* Due to padding, the 4bytes per entry mask variant is always smaller. */ + data->mask32_data.nr = BITS_TO_U32(max); + data->mask32_data.long_size = 4; - mask->nr = BITS_TO_LONGS(max); - mask->long_size = sizeof(long); + perf_cpu_map__for_each_cpu(cpu, idx, map) { + int bit_word = cpu.cpu / 32; + __u32 bit_mask = 1U << (cpu.cpu & 31); - for (i = 0; i < perf_cpu_map__nr(map); i++) - set_bit(perf_cpu_map__cpu(map, i).cpu, mask->mask); + data->mask32_data.mask[bit_word] |= bit_mask; + } } -static size_t cpus_size(struct perf_cpu_map *map) +static size_t cpus_size(const struct perf_cpu_map *map) { return sizeof(struct cpu_map_entries) + perf_cpu_map__nr(map) * sizeof(u16); } -static size_t mask_size(struct perf_cpu_map *map, int *max) +static size_t mask_size(const struct perf_cpu_map *map, int *max) { - int i; - - *max = 0; - - for (i = 0; i < perf_cpu_map__nr(map); i++) { - /* bit position of the cpu is + 1 */ - int bit = perf_cpu_map__cpu(map, i).cpu + 1; - - if (bit > *max) - *max = bit; - } - - return sizeof(struct perf_record_record_cpu_map) + BITS_TO_LONGS(*max) * sizeof(long); + *max = perf_cpu_map__max(map).cpu; + return sizeof(struct perf_record_mask_cpu_map32) + BITS_TO_U32(*max) * sizeof(__u32); } -void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *max) +static void *cpu_map_data__alloc(const struct perf_cpu_map *map, size_t *size, + u16 *type, int *max) { size_t size_cpus, size_mask; bool is_dummy = perf_cpu_map__empty(map); @@ -1258,30 +1254,31 @@ void *cpu_map_data__alloc(struct perf_cpu_map *map, size_t *size, u16 *type, int *type = PERF_CPU_MAP__MASK; } - *size += sizeof(struct perf_record_cpu_map_data); + *size += sizeof(__u16); /* For perf_record_cpu_map_data.type. */ *size = PERF_ALIGN(*size, sizeof(u64)); return zalloc(*size); } -void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, struct perf_cpu_map *map, - u16 type, int max) +static void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, + const struct perf_cpu_map *map, + u16 type, int max) { data->type = type; switch (type) { case PERF_CPU_MAP__CPUS: - synthesize_cpus((struct cpu_map_entries *) data->data, map); + synthesize_cpus(data, map); break; case PERF_CPU_MAP__MASK: - synthesize_mask((struct perf_record_record_cpu_map *)data->data, map, max); + synthesize_mask(data, map, max); default: break; } } -static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map) +static struct perf_record_cpu_map *cpu_map_event__new(const struct perf_cpu_map *map) { - size_t size = sizeof(struct perf_record_cpu_map); + size_t size = sizeof(struct perf_event_header); struct perf_record_cpu_map *event; int max; u16 type; @@ -1299,7 +1296,7 @@ static struct perf_record_cpu_map *cpu_map_event__new(struct perf_cpu_map *map) } int perf_event__synthesize_cpu_map(struct perf_tool *tool, - struct perf_cpu_map *map, + const struct perf_cpu_map *map, perf_event__handler_t process, struct machine *machine) { @@ -1432,11 +1429,12 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, result += sizeof(u64); /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ if (read_format & PERF_FORMAT_GROUP) { - sz = sample->read.group.nr * - sizeof(struct sample_read_value); - result += sz; + sz = sample_read_value_size(read_format); + result += sz * sample->read.group.nr; } else { result += sizeof(u64); + if (read_format & PERF_FORMAT_LOST) + result += sizeof(u64); } } @@ -1521,6 +1519,20 @@ void __weak arch_perf_synthesize_sample_weight(const struct perf_sample *data, *array = data->weight; } +static __u64 *copy_read_group_values(__u64 *array, __u64 read_format, + const struct perf_sample *sample) +{ + size_t sz = sample_read_value_size(read_format); + struct sample_read_value *v = sample->read.group.values; + + sample_read_group__for_each(v, sample->read.group.nr, read_format) { + /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ + memcpy(array, v, sz); + array = (void *)array + sz; + } + return array; +} + int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format, const struct perf_sample *sample) { @@ -1602,13 +1614,16 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ if (read_format & PERF_FORMAT_GROUP) { - sz = sample->read.group.nr * - sizeof(struct sample_read_value); - memcpy(array, sample->read.group.values, sz); - array = (void *)array + sz; + array = copy_read_group_values(array, read_format, + sample); } else { *array = sample->read.one.id; array++; + + if (read_format & PERF_FORMAT_LOST) { + *array = sample->read.one.lost; + array++; + } } } diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h index 81cb3d6af0b9..53737d1619a4 100644 --- a/tools/perf/util/synthetic-events.h +++ b/tools/perf/util/synthetic-events.h @@ -46,7 +46,7 @@ typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *e int perf_event__synthesize_attrs(struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process); int perf_event__synthesize_attr(struct perf_tool *tool, struct perf_event_attr *attr, u32 ids, u64 *id, perf_event__handler_t process); int perf_event__synthesize_build_id(struct perf_tool *tool, struct dso *pos, u16 misc, perf_event__handler_t process, struct machine *machine); -int perf_event__synthesize_cpu_map(struct perf_tool *tool, struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_cpu_map(struct perf_tool *tool, const struct perf_cpu_map *cpus, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process); int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process); int perf_event__synthesize_event_update_scale(struct perf_tool *tool, struct evsel *evsel, perf_event__handler_t process); |