From e989bc3d0f3f93aab7c5018affc3f87b74716b37 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 14 Jun 2022 07:33:48 -0700 Subject: perf cpumap: Const map for max() Allows max() to be used with 'const struct perf_cpu_maps *'. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Athira Jajeev Cc: Colin Ian King Cc: Dave Marchevsky Cc: German Gomez Cc: Gustavo A. R. Silva Cc: Ingo Molnar Cc: James Clark Cc: Kees Kook Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Song Liu Cc: Stephane Eranian Link: https://lore.kernel.org/r/20220614143353.1559597-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/cpumap.c | 2 +- tools/lib/perf/include/perf/cpumap.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index 384d5e076ee4..6cd0be7c1bb4 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -309,7 +309,7 @@ bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu) return perf_cpu_map__idx(cpus, cpu) != -1; } -struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map) +struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map) { struct perf_cpu result = { .cpu = -1 diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h index 24de795b09bb..03aceb72a783 100644 --- a/tools/lib/perf/include/perf/cpumap.h +++ b/tools/lib/perf/include/perf/cpumap.h @@ -23,7 +23,7 @@ LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map); LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus); LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map); -LIBPERF_API struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map); +LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map); LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); #define perf_cpu_map__for_each_cpu(cpu, idx, cpus) \ -- cgit v1.2.3 From b2f10cd4e805eb647773df273eb1a6ff9e6ea45d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 14 Jun 2022 07:33:51 -0700 Subject: perf cpumap: Fix alignment for masks in event encoding A mask encoding of a cpu map is laid out as: u16 nr u16 long_size unsigned long mask[]; However, the mask may be 8-byte aligned meaning there is a 4-byte pad after long_size. This means 32-bit and 64-bit builds see the mask as being at different offsets. On top of this the structure is in the byte data[] encoded as: u16 type char data[] This means the mask's struct isn't the required 4 or 8 byte aligned, but is offset by 2. Consequently the long reads and writes are causing undefined behavior as the alignment is broken. Fix the mask struct by creating explicit 32 and 64-bit variants, use a union to avoid data[] and casts; the struct must be packed so the layout matches the existing perf.data layout. Taking an address of a member of a packed struct breaks alignment so pass the packed perf_record_cpu_map_data to functions, so they can access variables with the right alignment. As the 64-bit version has 4 bytes of padding, optimizing writing to only write the 32-bit version. Committer notes: Disable warnings about 'packed' that break the build in some arches like riscv64, but just around that specific struct. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Athira Jajeev Cc: Colin Ian King Cc: Dave Marchevsky Cc: German Gomez Cc: Gustavo A. R. Silva Cc: Ingo Molnar Cc: James Clark Cc: Kees Kook Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Song Liu Cc: Stephane Eranian Link: https://lore.kernel.org/r/20220614143353.1559597-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/include/perf/event.h | 47 ++++++++++++++++++++-- tools/perf/tests/cpumap.c | 19 +++++---- tools/perf/util/cpumap.c | 80 +++++++++++++++++++++++++++++-------- tools/perf/util/cpumap.h | 4 +- tools/perf/util/session.c | 30 +++++++------- tools/perf/util/synthetic-events.c | 34 +++++++++------- 6 files changed, 154 insertions(+), 60 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index 556bb06798f2..57f54781f5ed 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -6,6 +6,7 @@ #include #include #include +#include #include /* pid_t */ #define event_contains(obj, mem) ((obj).header.size > offsetof(typeof(obj), mem)) @@ -153,22 +154,60 @@ enum { PERF_CPU_MAP__MASK = 1, }; +/* + * Array encoding of a perf_cpu_map where nr is the number of entries in cpu[] + * and each entry is a value for a CPU in the map. + */ struct cpu_map_entries { __u16 nr; __u16 cpu[]; }; -struct perf_record_record_cpu_map { +/* Bitmap encoding of a perf_cpu_map where bitmap entries are 32-bit. */ +struct perf_record_mask_cpu_map32 { + /* Number of mask values. */ __u16 nr; + /* Constant 4. */ __u16 long_size; - unsigned long mask[]; + /* Bitmap data. */ + __u32 mask[]; }; -struct perf_record_cpu_map_data { +/* Bitmap encoding of a perf_cpu_map where bitmap entries are 64-bit. */ +struct perf_record_mask_cpu_map64 { + /* Number of mask values. */ + __u16 nr; + /* Constant 8. */ + __u16 long_size; + /* Legacy padding. */ + char __pad[4]; + /* Bitmap data. */ + __u64 mask[]; +}; + +/* + * 'struct perf_record_cpu_map_data' is packed as unfortunately an earlier + * version had unaligned data and we wish to retain file format compatibility. + * -irogers + */ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wpacked" +#pragma GCC diagnostic ignored "-Wattributes" + +struct __packed perf_record_cpu_map_data { __u16 type; - char data[]; + union { + /* Used when type == PERF_CPU_MAP__CPUS. */ + struct cpu_map_entries cpus_data; + /* Used when type == PERF_CPU_MAP__MASK and long_size == 4. */ + struct perf_record_mask_cpu_map32 mask32_data; + /* Used when type == PERF_CPU_MAP__MASK and long_size == 8. */ + struct perf_record_mask_cpu_map64 mask64_data; + }; }; +#pragma GCC diagnostic pop + struct perf_record_cpu_map { struct perf_event_header header; struct perf_record_cpu_map_data data; 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/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/session.c b/tools/perf/util/session.c index 98e16659a149..61bb9675e044 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"); } diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 3ae7c0f54157..59747c440bd5 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -1184,27 +1184,33 @@ int perf_event__synthesize_thread_map2(struct perf_tool *tool, return err; } -static void synthesize_cpus(struct cpu_map_entries *cpus, +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, +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(const struct perf_cpu_map *map) @@ -1215,7 +1221,7 @@ static size_t cpus_size(const struct perf_cpu_map *map) static size_t mask_size(const struct perf_cpu_map *map, int *max) { *max = perf_cpu_map__max(map).cpu; - return sizeof(struct perf_record_record_cpu_map) + BITS_TO_LONGS(*max) * sizeof(long); + return sizeof(struct perf_record_mask_cpu_map32) + BITS_TO_U32(*max) * sizeof(__u32); } static void *cpu_map_data__alloc(const struct perf_cpu_map *map, size_t *size, @@ -1248,7 +1254,7 @@ static void *cpu_map_data__alloc(const struct perf_cpu_map *map, size_t *size, *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); } @@ -1261,10 +1267,10 @@ static void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, 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; } @@ -1272,7 +1278,7 @@ static void cpu_map_data__synthesize(struct perf_record_cpu_map_data *data, 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; -- cgit v1.2.3 From 89e3106fa25fb1b626a7123dba870159d453e785 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 18 Aug 2022 17:36:42 -0700 Subject: libperf: Handle read format in perf_evsel__read() The perf_counts_values should be increased to read the new lost data. Also adjust values after read according the read format. This supports PERF_FORMAT_GROUP which has a different data format but it's only available for leader events. Currently it doesn't have an API to read sibling (member) events in the group. But users may read the sibling event directly. Also reading from mmap would be disabled when the read format has ID or LOST bit as it's not exposed via mmap. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Ian Rogers Cc: Ingo Molnar Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20220819003644.508916-3-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/evsel.c | 79 ++++++++++++++++++++++++++++++++++++- tools/lib/perf/include/perf/event.h | 3 +- tools/lib/perf/include/perf/evsel.h | 4 +- 3 files changed, 83 insertions(+), 3 deletions(-) (limited to 'tools/lib') diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index 952f3520d5c2..8ce5bbd09666 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -305,6 +305,9 @@ int perf_evsel__read_size(struct perf_evsel *evsel) if (read_format & PERF_FORMAT_ID) entry += sizeof(u64); + if (read_format & PERF_FORMAT_LOST) + entry += sizeof(u64); + if (read_format & PERF_FORMAT_GROUP) { nr = evsel->nr_members; size += sizeof(u64); @@ -314,24 +317,98 @@ int perf_evsel__read_size(struct perf_evsel *evsel) return size; } +/* This only reads values for the leader */ +static int perf_evsel__read_group(struct perf_evsel *evsel, int cpu_map_idx, + int thread, struct perf_counts_values *count) +{ + size_t size = perf_evsel__read_size(evsel); + int *fd = FD(evsel, cpu_map_idx, thread); + u64 read_format = evsel->attr.read_format; + u64 *data; + int idx = 1; + + if (fd == NULL || *fd < 0) + return -EINVAL; + + data = calloc(1, size); + if (data == NULL) + return -ENOMEM; + + if (readn(*fd, data, size) <= 0) { + free(data); + return -errno; + } + + /* + * This reads only the leader event intentionally since we don't have + * perf counts values for sibling events. + */ + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + count->ena = data[idx++]; + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + count->run = data[idx++]; + + /* value is always available */ + count->val = data[idx++]; + if (read_format & PERF_FORMAT_ID) + count->id = data[idx++]; + if (read_format & PERF_FORMAT_LOST) + count->lost = data[idx++]; + + free(data); + return 0; +} + +/* + * The perf read format is very flexible. It needs to set the proper + * values according to the read format. + */ +static void perf_evsel__adjust_values(struct perf_evsel *evsel, u64 *buf, + struct perf_counts_values *count) +{ + u64 read_format = evsel->attr.read_format; + int n = 0; + + count->val = buf[n++]; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + count->ena = buf[n++]; + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + count->run = buf[n++]; + + if (read_format & PERF_FORMAT_ID) + count->id = buf[n++]; + + if (read_format & PERF_FORMAT_LOST) + count->lost = buf[n++]; +} + int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread, struct perf_counts_values *count) { size_t size = perf_evsel__read_size(evsel); int *fd = FD(evsel, cpu_map_idx, thread); + u64 read_format = evsel->attr.read_format; + struct perf_counts_values buf; memset(count, 0, sizeof(*count)); if (fd == NULL || *fd < 0) return -EINVAL; + if (read_format & PERF_FORMAT_GROUP) + return perf_evsel__read_group(evsel, cpu_map_idx, thread, count); + if (MMAP(evsel, cpu_map_idx, thread) && + !(read_format & (PERF_FORMAT_ID | PERF_FORMAT_LOST)) && !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count)) return 0; - if (readn(*fd, count->values, size) <= 0) + if (readn(*fd, buf.values, size) <= 0) return -errno; + perf_evsel__adjust_values(evsel, buf.values, count); return 0; } diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index 57f54781f5ed..93bf93a59c99 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -77,7 +77,7 @@ struct perf_record_lost_samples { }; /* - * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID + * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID | PERF_FORMAT_LOST */ struct perf_record_read { struct perf_event_header header; @@ -86,6 +86,7 @@ struct perf_record_read { __u64 time_enabled; __u64 time_running; __u64 id; + __u64 lost; }; struct perf_record_throttle { diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h index 699c0ed97d34..6f92204075c2 100644 --- a/tools/lib/perf/include/perf/evsel.h +++ b/tools/lib/perf/include/perf/evsel.h @@ -18,8 +18,10 @@ struct perf_counts_values { uint64_t val; uint64_t ena; uint64_t run; + uint64_t id; + uint64_t lost; }; - uint64_t values[3]; + uint64_t values[5]; }; }; -- cgit v1.2.3 From 6d395a513556e61dc22c6abdf9b419deb46f1908 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 18 Aug 2022 17:36:43 -0700 Subject: libperf: Add a test case for read formats It checks a various combination of the read format settings and verify it return the value in a proper position. The test uses task-clock software events to guarantee it's always active and sets enabled/running time. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Ian Rogers Cc: Ingo Molnar Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20220819003644.508916-4-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/tests/test-evsel.c | 161 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 161 insertions(+) (limited to 'tools/lib') diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c index 89be89afb24d..a11fc51bfb68 100644 --- a/tools/lib/perf/tests/test-evsel.c +++ b/tools/lib/perf/tests/test-evsel.c @@ -1,10 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include +#include #include #include #include +#include #include #include "tests.h" @@ -189,6 +192,163 @@ static int test_stat_user_read(int event) return 0; } +static int test_stat_read_format_single(struct perf_event_attr *attr, struct perf_thread_map *threads) +{ + struct perf_evsel *evsel; + struct perf_counts_values counts; + volatile int count = 0x100000; + int err; + + evsel = perf_evsel__new(attr); + __T("failed to create evsel", evsel); + + /* skip old kernels that don't support the format */ + err = perf_evsel__open(evsel, NULL, threads); + if (err < 0) + return 0; + + while (count--) ; + + memset(&counts, -1, sizeof(counts)); + perf_evsel__read(evsel, 0, 0, &counts); + + __T("failed to read value", counts.val); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + __T("failed to read TOTAL_TIME_ENABLED", counts.ena); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + __T("failed to read TOTAL_TIME_RUNNING", counts.run); + if (attr->read_format & PERF_FORMAT_ID) + __T("failed to read ID", counts.id); + if (attr->read_format & PERF_FORMAT_LOST) + __T("failed to read LOST", counts.lost == 0); + + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + return 0; +} + +static int test_stat_read_format_group(struct perf_event_attr *attr, struct perf_thread_map *threads) +{ + struct perf_evsel *leader, *member; + struct perf_counts_values counts; + volatile int count = 0x100000; + int err; + + attr->read_format |= PERF_FORMAT_GROUP; + leader = perf_evsel__new(attr); + __T("failed to create leader", leader); + + attr->read_format &= ~PERF_FORMAT_GROUP; + member = perf_evsel__new(attr); + __T("failed to create member", member); + + member->leader = leader; + leader->nr_members = 2; + + /* skip old kernels that don't support the format */ + err = perf_evsel__open(leader, NULL, threads); + if (err < 0) + return 0; + err = perf_evsel__open(member, NULL, threads); + if (err < 0) + return 0; + + while (count--) ; + + memset(&counts, -1, sizeof(counts)); + perf_evsel__read(leader, 0, 0, &counts); + + __T("failed to read leader value", counts.val); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + __T("failed to read leader TOTAL_TIME_ENABLED", counts.ena); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + __T("failed to read leader TOTAL_TIME_RUNNING", counts.run); + if (attr->read_format & PERF_FORMAT_ID) + __T("failed to read leader ID", counts.id); + if (attr->read_format & PERF_FORMAT_LOST) + __T("failed to read leader LOST", counts.lost == 0); + + memset(&counts, -1, sizeof(counts)); + perf_evsel__read(member, 0, 0, &counts); + + __T("failed to read member value", counts.val); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + __T("failed to read member TOTAL_TIME_ENABLED", counts.ena); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + __T("failed to read member TOTAL_TIME_RUNNING", counts.run); + if (attr->read_format & PERF_FORMAT_ID) + __T("failed to read member ID", counts.id); + if (attr->read_format & PERF_FORMAT_LOST) + __T("failed to read member LOST", counts.lost == 0); + + perf_evsel__close(member); + perf_evsel__close(leader); + perf_evsel__delete(member); + perf_evsel__delete(leader); + return 0; +} + +static int test_stat_read_format(void) +{ + struct perf_thread_map *threads; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + }; + int err, i; + +#define FMT(_fmt) PERF_FORMAT_ ## _fmt +#define FMT_TIME (FMT(TOTAL_TIME_ENABLED) | FMT(TOTAL_TIME_RUNNING)) + + uint64_t test_formats [] = { + 0, + FMT_TIME, + FMT(ID), + FMT(LOST), + FMT_TIME | FMT(ID), + FMT_TIME | FMT(LOST), + FMT_TIME | FMT(ID) | FMT(LOST), + FMT(ID) | FMT(LOST), + }; + +#undef FMT +#undef FMT_TIME + + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + for (i = 0; i < (int)ARRAY_SIZE(test_formats); i++) { + attr.read_format = test_formats[i]; + __T_VERBOSE("testing single read with read_format: %lx\n", + (unsigned long)test_formats[i]); + + err = test_stat_read_format_single(&attr, threads); + __T("failed to read single format", err == 0); + } + + perf_thread_map__put(threads); + + threads = perf_thread_map__new_array(2, NULL); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + perf_thread_map__set_pid(threads, 1, 0); + + for (i = 0; i < (int)ARRAY_SIZE(test_formats); i++) { + attr.read_format = test_formats[i]; + __T_VERBOSE("testing group read with read_format: %lx\n", + (unsigned long)test_formats[i]); + + err = test_stat_read_format_group(&attr, threads); + __T("failed to read group format", err == 0); + } + + perf_thread_map__put(threads); + return 0; +} + int test_evsel(int argc, char **argv) { __T_START; @@ -200,6 +360,7 @@ int test_evsel(int argc, char **argv) test_stat_thread_enable(); test_stat_user_read(PERF_COUNT_HW_INSTRUCTIONS); test_stat_user_read(PERF_COUNT_HW_CPU_CYCLES); + test_stat_read_format(); __T_END; return tests_failed == 0 ? 0 : -1; -- cgit v1.2.3