diff options
206 files changed, 5510 insertions, 1871 deletions
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 934e2777a2db..64df118376df 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -32,6 +32,7 @@ FEATURE_TESTS_BASIC := \ backtrace \ dwarf \ dwarf_getlocations \ + dwarf_getcfi \ eventfd \ fortify-source \ get_current_dir_name \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index dad79ede4e0a..37722e509eb9 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -7,6 +7,7 @@ FILES= \ test-bionic.bin \ test-dwarf.bin \ test-dwarf_getlocations.bin \ + test-dwarf_getcfi.bin \ test-eventfd.bin \ test-fortify-source.bin \ test-get_current_dir_name.bin \ @@ -154,6 +155,9 @@ $(OUTPUT)test-dwarf.bin: $(OUTPUT)test-dwarf_getlocations.bin: $(BUILD) $(DWARFLIBS) +$(OUTPUT)test-dwarf_getcfi.bin: + $(BUILD) $(DWARFLIBS) + $(OUTPUT)test-libelf-getphdrnum.bin: $(BUILD) -lelf diff --git a/tools/build/feature/test-dwarf_getcfi.c b/tools/build/feature/test-dwarf_getcfi.c new file mode 100644 index 000000000000..50e7d7cb7bdf --- /dev/null +++ b/tools/build/feature/test-dwarf_getcfi.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <elfutils/libdw.h> + +int main(void) +{ + Dwarf *dwarf = NULL; + return dwarf_getcfi(dwarf) == NULL; +} diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c index eb6303ff446e..4cfcef9da3e4 100644 --- a/tools/build/feature/test-libopencsd.c +++ b/tools/build/feature/test-libopencsd.c @@ -4,9 +4,9 @@ /* * Check OpenCSD library version is sufficient to provide required features */ -#define OCSD_MIN_VER ((1 << 16) | (1 << 8) | (1)) +#define OCSD_MIN_VER ((1 << 16) | (2 << 8) | (1)) #if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER) -#error "OpenCSD >= 1.1.1 is required" +#error "OpenCSD >= 1.2.1 is required" #endif int main(void) diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 39c6a250dd1b..3a64499b0f5d 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -204,6 +204,8 @@ enum perf_branch_sample_type_shift { PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT = 18, /* save privilege mode */ + PERF_SAMPLE_BRANCH_COUNTERS_SHIFT = 19, /* save occurrences of events on a branch */ + PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ }; @@ -235,6 +237,8 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_COUNTERS = 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; @@ -982,6 +986,12 @@ enum perf_event_type { * { u64 nr; * { u64 hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX * { u64 from, to, flags } lbr[nr]; + * # + * # The format of the counters is decided by the + * # "branch_counter_nr" and "branch_counter_width", + * # which are defined in the ABI. + * # + * { u64 counters; } cntr[nr] && PERF_SAMPLE_BRANCH_COUNTERS * } && PERF_SAMPLE_BRANCH_STACK * * { u64 abi; # enum perf_sample_regs_abi @@ -1427,6 +1437,9 @@ struct perf_branch_entry { reserved:31; }; +/* Size of used info bits in struct perf_branch_entry */ +#define PERF_BRANCH_ENTRY_INFO_BITS_MAX 33 + union perf_sample_weight { __u64 full; #if defined(__LITTLE_ENDIAN_BITFIELD) diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 5cb0eeec2c8a..337fde770e45 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -16,6 +16,7 @@ #include <sys/mount.h> #include "fs.h" +#include "../io.h" #include "debug-internal.h" #define _STR(x) #x @@ -344,53 +345,24 @@ int filename__read_ull(const char *filename, unsigned long long *value) return filename__read_ull_base(filename, value, 0); } -#define STRERR_BUFSIZE 128 /* For the buffer size of strerror_r */ - int filename__read_str(const char *filename, char **buf, size_t *sizep) { - size_t size = 0, alloc_size = 0; - void *bf = NULL, *nbf; - int fd, n, err = 0; - char sbuf[STRERR_BUFSIZE]; + struct io io; + char bf[128]; + int err; - fd = open(filename, O_RDONLY); - if (fd < 0) + io.fd = open(filename, O_RDONLY); + if (io.fd < 0) return -errno; - - do { - if (size == alloc_size) { - alloc_size += BUFSIZ; - nbf = realloc(bf, alloc_size); - if (!nbf) { - err = -ENOMEM; - break; - } - - bf = nbf; - } - - n = read(fd, bf + size, alloc_size - size); - if (n < 0) { - if (size) { - pr_warn("read failed %d: %s\n", errno, - strerror_r(errno, sbuf, sizeof(sbuf))); - err = 0; - } else - err = -errno; - - break; - } - - size += n; - } while (n > 0); - - if (!err) { - *sizep = size; - *buf = bf; + io__init(&io, io.fd, bf, sizeof(bf)); + *buf = NULL; + err = io__getdelim(&io, buf, sizep, /*delim=*/-1); + if (err < 0) { + free(*buf); + *buf = NULL; } else - free(bf); - - close(fd); + err = 0; + close(io.fd); return err; } @@ -475,15 +447,22 @@ int sysfs__read_str(const char *entry, char **buf, size_t *sizep) int sysfs__read_bool(const char *entry, bool *value) { - char *buf; - size_t size; - int ret; + struct io io; + char bf[16]; + int ret = 0; + char path[PATH_MAX]; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return -1; - ret = sysfs__read_str(entry, &buf, &size); - if (ret < 0) - return ret; + snprintf(path, sizeof(path), "%s/%s", sysfs, entry); + io.fd = open(path, O_RDONLY); + if (io.fd < 0) + return -errno; - switch (buf[0]) { + io__init(&io, io.fd, bf, sizeof(bf)); + switch (io__get_char(&io)) { case '1': case 'y': case 'Y': @@ -497,8 +476,7 @@ int sysfs__read_bool(const char *entry, bool *value) default: ret = -1; } - - free(buf); + close(io.fd); return ret; } diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h index a77b74c5fb65..84adf8102018 100644 --- a/tools/lib/api/io.h +++ b/tools/lib/api/io.h @@ -12,6 +12,7 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> +#include <linux/types.h> struct io { /* File descriptor being read/ */ @@ -140,8 +141,8 @@ static inline int io__get_dec(struct io *io, __u64 *dec) } } -/* Read up to and including the first newline following the pattern of getline. */ -static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_len_out) +/* Read up to and including the first delim. */ +static inline ssize_t io__getdelim(struct io *io, char **line_out, size_t *line_len_out, int delim) { char buf[128]; int buf_pos = 0; @@ -151,7 +152,7 @@ static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_l /* TODO: reuse previously allocated memory. */ free(*line_out); - while (ch != '\n') { + while (ch != delim) { ch = io__get_char(io); if (ch < 0) @@ -184,4 +185,9 @@ err_out: return -ENOMEM; } +static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_len_out) +{ + return io__getdelim(io, line_out, line_len_out, /*delim=*/'\n'); +} + #endif /* __API_IO__ */ diff --git a/tools/lib/perf/Documentation/examples/sampling.c b/tools/lib/perf/Documentation/examples/sampling.c index 8e1a926a9cfe..bc142f0664b5 100644 --- a/tools/lib/perf/Documentation/examples/sampling.c +++ b/tools/lib/perf/Documentation/examples/sampling.c @@ -39,7 +39,7 @@ int main(int argc, char **argv) libperf_init(libperf_print); - cpus = perf_cpu_map__new(NULL); + cpus = perf_cpu_map__new_online_cpus(); if (!cpus) { fprintf(stderr, "failed to create cpus\n"); return -1; diff --git a/tools/lib/perf/Documentation/libperf-sampling.txt b/tools/lib/perf/Documentation/libperf-sampling.txt index d6ca24f6ef78..2378980fab8a 100644 --- a/tools/lib/perf/Documentation/libperf-sampling.txt +++ b/tools/lib/perf/Documentation/libperf-sampling.txt @@ -97,7 +97,7 @@ In this case we will monitor all the available CPUs: [source,c] -- - 42 cpus = perf_cpu_map__new(NULL); + 42 cpus = perf_cpu_map__new_online_cpus(); 43 if (!cpus) { 44 fprintf(stderr, "failed to create cpus\n"); 45 return -1; diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt index a8f1a237931b..fcfb9499ef9c 100644 --- a/tools/lib/perf/Documentation/libperf.txt +++ b/tools/lib/perf/Documentation/libperf.txt @@ -37,7 +37,7 @@ SYNOPSIS struct perf_cpu_map; - struct perf_cpu_map *perf_cpu_map__dummy_new(void); + struct perf_cpu_map *perf_cpu_map__new_any_cpu(void); struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); struct perf_cpu_map *perf_cpu_map__read(FILE *file); struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); @@ -46,7 +46,7 @@ SYNOPSIS void perf_cpu_map__put(struct perf_cpu_map *map); int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); int perf_cpu_map__nr(const struct perf_cpu_map *cpus); - bool perf_cpu_map__empty(const struct perf_cpu_map *map); + bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map); int perf_cpu_map__max(struct perf_cpu_map *map); bool perf_cpu_map__has(const struct perf_cpu_map *map, int cpu); diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index 2a5a29217374..4adcd7920d03 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -9,6 +9,7 @@ #include <unistd.h> #include <ctype.h> #include <limits.h> +#include "internal.h" void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus) { @@ -27,7 +28,7 @@ struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus) return result; } -struct perf_cpu_map *perf_cpu_map__dummy_new(void) +struct perf_cpu_map *perf_cpu_map__new_any_cpu(void) { struct perf_cpu_map *cpus = perf_cpu_map__alloc(1); @@ -66,15 +67,21 @@ void perf_cpu_map__put(struct perf_cpu_map *map) } } -static struct perf_cpu_map *cpu_map__default_new(void) +static struct perf_cpu_map *cpu_map__new_sysconf(void) { struct perf_cpu_map *cpus; - int nr_cpus; + int nr_cpus, nr_cpus_conf; nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); if (nr_cpus < 0) return NULL; + nr_cpus_conf = sysconf(_SC_NPROCESSORS_CONF); + if (nr_cpus != nr_cpus_conf) { + pr_warning("Number of online CPUs (%d) differs from the number configured (%d) the CPU map will only cover the first %d CPUs.", + nr_cpus, nr_cpus_conf, nr_cpus); + } + cpus = perf_cpu_map__alloc(nr_cpus); if (cpus != NULL) { int i; @@ -86,9 +93,27 @@ static struct perf_cpu_map *cpu_map__default_new(void) return cpus; } -struct perf_cpu_map *perf_cpu_map__default_new(void) +static struct perf_cpu_map *cpu_map__new_sysfs_online(void) { - return cpu_map__default_new(); + struct perf_cpu_map *cpus = NULL; + FILE *onlnf; + + onlnf = fopen("/sys/devices/system/cpu/online", "r"); + if (onlnf) { + cpus = perf_cpu_map__read(onlnf); + fclose(onlnf); + } + return cpus; +} + +struct perf_cpu_map *perf_cpu_map__new_online_cpus(void) +{ + struct perf_cpu_map *cpus = cpu_map__new_sysfs_online(); + + if (cpus) + return cpus; + + return cpu_map__new_sysconf(); } @@ -180,27 +205,11 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file) if (nr_cpus > 0) cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); - else - cpus = cpu_map__default_new(); out_free_tmp: free(tmp_cpus); return cpus; } -static struct perf_cpu_map *cpu_map__read_all_cpu_map(void) -{ - struct perf_cpu_map *cpus = NULL; - FILE *onlnf; - - onlnf = fopen("/sys/devices/system/cpu/online", "r"); - if (!onlnf) - return cpu_map__default_new(); - - cpus = perf_cpu_map__read(onlnf); - fclose(onlnf); - return cpus; -} - struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) { struct perf_cpu_map *cpus = NULL; @@ -211,7 +220,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) int max_entries = 0; if (!cpu_list) - return cpu_map__read_all_cpu_map(); + return perf_cpu_map__new_online_cpus(); /* * must handle the case of empty cpumap to cover @@ -268,10 +277,12 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) if (nr_cpus > 0) cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); - else if (*cpu_list != '\0') - cpus = cpu_map__default_new(); - else - cpus = perf_cpu_map__dummy_new(); + else if (*cpu_list != '\0') { + pr_warning("Unexpected characters at end of cpu list ('%s'), using online CPUs.", + cpu_list); + cpus = perf_cpu_map__new_online_cpus(); + } else + cpus = perf_cpu_map__new_any_cpu(); invalid: free(tmp_cpus); out: @@ -300,7 +311,7 @@ int perf_cpu_map__nr(const struct perf_cpu_map *cpus) return cpus ? __perf_cpu_map__nr(cpus) : 1; } -bool perf_cpu_map__empty(const struct perf_cpu_map *map) +bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map) { return map ? __perf_cpu_map__cpu(map, 0).cpu == -1 : true; } diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 3acbbccc1901..058e3ff10f9b 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -39,7 +39,7 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, if (evsel->system_wide) { /* System wide: set the cpu map of the evsel to all online CPUs. */ perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__new(NULL); + evsel->cpus = perf_cpu_map__new_online_cpus(); } else if (evlist->has_user_cpus && evsel->is_pmu_core) { /* * User requested CPUs on a core PMU, ensure the requested CPUs @@ -619,7 +619,7 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist) /* One for each CPU */ nr_mmaps = perf_cpu_map__nr(evlist->all_cpus); - if (perf_cpu_map__empty(evlist->all_cpus)) { + if (perf_cpu_map__has_any_cpu_or_is_empty(evlist->all_cpus)) { /* Plus one for each thread */ nr_mmaps += perf_thread_map__nr(evlist->threads); /* Minus the per-thread CPU (-1) */ @@ -653,7 +653,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0) return -ENOMEM; - if (perf_cpu_map__empty(cpus)) + if (perf_cpu_map__has_any_cpu_or_is_empty(cpus)) return mmap_per_thread(evlist, ops, mp); return mmap_per_cpu(evlist, ops, mp); diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index 8b51b008a81f..c07160953224 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -120,7 +120,7 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, static struct perf_cpu_map *empty_cpu_map; if (empty_cpu_map == NULL) { - empty_cpu_map = perf_cpu_map__dummy_new(); + empty_cpu_map = perf_cpu_map__new_any_cpu(); if (empty_cpu_map == NULL) return -ENOMEM; } diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h index 5a062af8e9d8..5f08cab61ece 100644 --- a/tools/lib/perf/include/internal/mmap.h +++ b/tools/lib/perf/include/internal/mmap.h @@ -33,7 +33,8 @@ struct perf_mmap { bool overwrite; u64 flush; libperf_unmap_cb_t unmap_cb; - char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8); + void *event_copy; + size_t event_copy_sz; struct perf_mmap *next; }; diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h index e38d859a384d..228c6c629b0c 100644 --- a/tools/lib/perf/include/perf/cpumap.h +++ b/tools/lib/perf/include/perf/cpumap.h @@ -19,10 +19,23 @@ struct perf_cache { struct perf_cpu_map; /** - * perf_cpu_map__dummy_new - a map with a singular "any CPU"/dummy -1 value. + * perf_cpu_map__new_any_cpu - a map with a singular "any CPU"/dummy -1 value. + */ +LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_any_cpu(void); +/** + * perf_cpu_map__new_online_cpus - a map read from + * /sys/devices/system/cpu/online if + * available. If reading wasn't possible a map + * is created using the online processors + * assuming the first 'n' processors are all + * online. + */ +LIBPERF_API struct perf_cpu_map *perf_cpu_map__new_online_cpus(void); +/** + * perf_cpu_map__new - create a map from the given cpu_list such as "0-7". If no + * cpu_list argument is provided then + * perf_cpu_map__new_online_cpus is returned. */ -LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void); -LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void); LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file); LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); @@ -31,12 +44,23 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, LIBPERF_API struct perf_cpu_map *perf_cpu_map__intersect(struct perf_cpu_map *orig, struct perf_cpu_map *other); LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map); +/** + * perf_cpu_map__cpu - get the CPU value at the given index. Returns -1 if index + * is invalid. + */ LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); +/** + * perf_cpu_map__nr - for an empty map returns 1, as perf_cpu_map__cpu returns a + * cpu of -1 for an invalid index, this makes an empty map + * look like it contains the "any CPU"/dummy value. Otherwise + * the result is the number CPUs in the map plus one if the + * "any CPU"/dummy value is present. + */ LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus); /** - * perf_cpu_map__empty - is map either empty or the "any CPU"/dummy value. + * perf_cpu_map__has_any_cpu_or_is_empty - is map either empty or has the "any CPU"/dummy value. */ -LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map); +LIBPERF_API bool perf_cpu_map__has_any_cpu_or_is_empty(const 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); LIBPERF_API bool perf_cpu_map__equal(const struct perf_cpu_map *lhs, @@ -51,6 +75,12 @@ LIBPERF_API bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map); (idx) < perf_cpu_map__nr(cpus); \ (idx)++, (cpu) = perf_cpu_map__cpu(cpus, idx)) +#define perf_cpu_map__for_each_cpu_skip_any(_cpu, idx, cpus) \ + for ((idx) = 0, (_cpu) = perf_cpu_map__cpu(cpus, idx); \ + (idx) < perf_cpu_map__nr(cpus); \ + (idx)++, (_cpu) = perf_cpu_map__cpu(cpus, idx)) \ + if ((_cpu).cpu != -1) + #define perf_cpu_map__for_each_idx(idx, cpus) \ for ((idx) = 0; (idx) < perf_cpu_map__nr(cpus); (idx)++) diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map index 190b56ae923a..10b3f3722642 100644 --- a/tools/lib/perf/libperf.map +++ b/tools/lib/perf/libperf.map @@ -1,15 +1,15 @@ LIBPERF_0.0.1 { global: libperf_init; - perf_cpu_map__dummy_new; - perf_cpu_map__default_new; + perf_cpu_map__new_any_cpu; + perf_cpu_map__new_online_cpus; perf_cpu_map__get; perf_cpu_map__put; perf_cpu_map__new; perf_cpu_map__read; perf_cpu_map__nr; perf_cpu_map__cpu; - perf_cpu_map__empty; + perf_cpu_map__has_any_cpu_or_is_empty; perf_cpu_map__max; perf_cpu_map__has; perf_thread_map__new_array; diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c index 2184814b37dd..0c903c2372c9 100644 --- a/tools/lib/perf/mmap.c +++ b/tools/lib/perf/mmap.c @@ -19,6 +19,7 @@ void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev, bool overwrite, libperf_unmap_cb_t unmap_cb) { + /* Assume fields were zero initialized. */ map->fd = -1; map->overwrite = overwrite; map->unmap_cb = unmap_cb; @@ -51,13 +52,18 @@ int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp, void perf_mmap__munmap(struct perf_mmap *map) { - if (map && map->base != NULL) { + if (!map) + return; + + zfree(&map->event_copy); + map->event_copy_sz = 0; + if (map->base) { munmap(map->base, perf_mmap__mmap_len(map)); map->base = NULL; map->fd = -1; refcount_set(&map->refcnt, 0); } - if (map && map->unmap_cb) + if (map->unmap_cb) map->unmap_cb(map); } @@ -223,9 +229,17 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map, */ if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) { unsigned int offset = *startp; - unsigned int len = min(sizeof(*event), size), cpy; + unsigned int len = size, cpy; void *dst = map->event_copy; + if (size > map->event_copy_sz) { + dst = realloc(map->event_copy, size); + if (!dst) + return NULL; + map->event_copy = dst; + map->event_copy_sz = size; + } + do { cpy = min(map->mask + 1 - (offset & map->mask), len); memcpy(dst, &data[offset & map->mask], cpy); diff --git a/tools/lib/perf/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c index 87b0510a556f..c998b1dae863 100644 --- a/tools/lib/perf/tests/test-cpumap.c +++ b/tools/lib/perf/tests/test-cpumap.c @@ -21,7 +21,7 @@ int test_cpumap(int argc, char **argv) libperf_init(libperf_print); - cpus = perf_cpu_map__dummy_new(); + cpus = perf_cpu_map__new_any_cpu(); if (!cpus) return -1; @@ -29,7 +29,7 @@ int test_cpumap(int argc, char **argv) perf_cpu_map__put(cpus); perf_cpu_map__put(cpus); - cpus = perf_cpu_map__default_new(); + cpus = perf_cpu_map__new_online_cpus(); if (!cpus) return -1; diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c index ed616fc19b4f..10f70cb41ff1 100644 --- a/tools/lib/perf/tests/test-evlist.c +++ b/tools/lib/perf/tests/test-evlist.c @@ -46,7 +46,7 @@ static int test_stat_cpu(void) }; int err, idx; - cpus = perf_cpu_map__new(NULL); + cpus = perf_cpu_map__new_online_cpus(); __T("failed to create cpus", cpus); evlist = perf_evlist__new(); @@ -261,7 +261,7 @@ static int test_mmap_thread(void) threads = perf_thread_map__new_dummy(); __T("failed to create threads", threads); - cpus = perf_cpu_map__dummy_new(); + cpus = perf_cpu_map__new_any_cpu(); __T("failed to create cpus", cpus); perf_thread_map__set_pid(threads, 0, pid); @@ -350,7 +350,7 @@ static int test_mmap_cpus(void) attr.config = id; - cpus = perf_cpu_map__new(NULL); + cpus = perf_cpu_map__new_online_cpus(); __T("failed to create cpus", cpus); evlist = perf_evlist__new(); diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c index a11fc51bfb68..545ec3150546 100644 --- a/tools/lib/perf/tests/test-evsel.c +++ b/tools/lib/perf/tests/test-evsel.c @@ -27,7 +27,7 @@ static int test_stat_cpu(void) }; int err, idx; - cpus = perf_cpu_map__new(NULL); + cpus = perf_cpu_map__new_online_cpus(); __T("failed to create cpus", cpus); evsel = perf_evsel__new(&attr); diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index f533e76fb480..f5b81d439387 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -39,6 +39,9 @@ trace/beauty/generated/ pmu-events/pmu-events.c pmu-events/jevents pmu-events/metric_test.log +tests/shell/*.shellcheck_log +tests/shell/coresight/*.shellcheck_log +tests/shell/lib/*.shellcheck_log feature/ libapi/ libbpf/ @@ -49,3 +52,4 @@ libtraceevent/ libtraceevent_plugins/ fixdep Documentation/doc.dep +python_ext_build/ diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index a97f95825b14..19cc179be9a7 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -25,6 +25,7 @@ q quicker (less detailed) decoding A approximate IPC Z prefer to ignore timestamps (so-called "timeless" decoding) + T use the timestamp trace as kernel time The default is all events i.e. the same as --itrace=iybxwpe, except for perf script where it is --itrace=ce diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 0b4e79dbd3f6..379f9d7a8ab1 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -251,7 +251,8 @@ annotate.*:: addr2line binary to use for file names and line numbers. annotate.objdump:: - objdump binary to use for disassembly and annotations. + objdump binary to use for disassembly and annotations, + including in the 'perf test' command. annotate.disassembler_style:: Use this to change the default disassembler style to some other value @@ -722,7 +723,6 @@ session-<NAME>.*:: Defines new record session for daemon. The value is record's command line without the 'record' keyword. - SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index d5f78e125efe..1b90575ee3c8 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -81,11 +81,13 @@ For Intel systems precise event sampling is implemented with PEBS which supports up to precise-level 2, and precise level 3 for some special cases -On AMD systems it is implemented using IBS (up to precise-level 2). -The precise modifier works with event types 0x76 (cpu-cycles, CPU -clocks not halted) and 0xC1 (micro-ops retired). Both events map to -IBS execution sampling (IBS op) with the IBS Op Counter Control bit -(IbsOpCntCtl) set respectively (see the +On AMD systems it is implemented using IBS OP (up to precise-level 2). +Unlike Intel PEBS which provides levels of precision, AMD core pmu is +inherently non-precise and IBS is inherently precise. (i.e. ibs_op//, +ibs_op//p, ibs_op//pp and ibs_op//ppp are all same). The precise modifier +works with event types 0x76 (cpu-cycles, CPU clocks not halted) and 0xC1 +(micro-ops retired). Both events map to IBS execution sampling (IBS op) +with the IBS Op Counter Control bit (IbsOpCntCtl) set respectively (see the Core Complex (CCX) -> Processor x86 Core -> Instruction Based Sampling (IBS) section of the [AMD Processor Programming Reference (PPR)] relevant to the family, model and stepping of the processor being used). diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index 503abcba1438..f5938d616d75 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -119,7 +119,7 @@ INFO OPTIONS CONTENTION OPTIONS --------------- +------------------ -k:: --key=<value>:: diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 1889f66addf2..6015fdd08fb6 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -445,6 +445,10 @@ following filters are defined: 4th-Gen Xeon+ server), the save branch type is unconditionally enabled when the taken branch stack sampling is enabled. - priv: save privilege state during sampling in case binary is not available later + - counter: save occurrences of the event since the last branch entry. Currently, the + feature is only supported by a newer CPU, e.g., Intel Sierra Forest and + later platforms. An error out is expected if it's used on the unsupported + kernel or CPUs. + The option requires at least one branch type among any, any_call, any_ret, ind_call, cond. diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 8f789fa1242e..5af2e432b54f 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -422,7 +422,34 @@ See perf list output for the possible metrics and metricgroups. -A:: --no-aggr:: -Do not aggregate counts across all monitored CPUs. +--no-merge:: +Do not aggregate/merge counts across monitored CPUs or PMUs. + +When multiple events are created from a single event specification, +stat will, by default, aggregate the event counts and show the result +in a single row. This option disables that behavior and shows the +individual events and counts. + +Multiple events are created from a single event specification when: + +1. PID monitoring isn't requested and the system has more than one + CPU. For example, a system with 8 SMT threads will have one event + opened on each thread and aggregation is performed across them. + +2. Prefix or glob wildcard matching is used for the PMU name. For + example, multiple memory controller PMUs may exist typically with a + suffix of _0, _1, etc. By default the event counts will all be + combined if the PMU is specified without the suffix such as + uncore_imc rather than uncore_imc_0. + +3. Aliases, which are listed immediately after the Kernel PMU events + by perf list, are used. + +--hybrid-merge:: +Merge core event counts from all core PMUs. In hybrid or big.LITTLE +systems by default each core PMU will report its count +separately. This option forces core PMU counts to be combined to give +a behavior closer to having a single CPU type in the system. --topdown:: Print top-down metrics supported by the CPU. This allows to determine @@ -475,29 +502,6 @@ highlight 'tma_frontend_bound'. This metric may be drilled into with Error out if the input is higher than the supported max level. ---no-merge:: -Do not merge results from same PMUs. - -When multiple events are created from a single event specification, -stat will, by default, aggregate the event counts and show the result -in a single row. This option disables that behavior and shows -the individual events and counts. - -Multiple events are created from a single event specification when: -1. Prefix or glob matching is used for the PMU name. -2. Aliases, which are listed immediately after the Kernel PMU events - by perf list, are used. - ---hybrid-merge:: -Merge the hybrid event counts from all PMUs. - -For hybrid events, by default, the stat aggregates and reports the event -counts per PMU. But sometimes, it's also useful to aggregate event counts -from all PMUs. This option enables that behavior and reports the counts -without PMUs. - -For non-hybrid events, it should be no effect. - --smi-cost:: Measure SMI cost if msr/aperf/ and msr/smi/ events are supported. diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index ba3df49c169d..a7cf7bc2f968 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -64,6 +64,9 @@ OPTIONS perf-event-open - Print perf_event_open() arguments and return value +--debug-file:: + Write debug output to a specified file. + DESCRIPTION ----------- Performance counters for Linux are a new kernel-based subsystem diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index b3e6ed10f40c..aa55850fbc21 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -476,6 +476,11 @@ else else CFLAGS += -DHAVE_DWARF_GETLOCATIONS_SUPPORT endif # dwarf_getlocations + ifneq ($(feature-dwarf_getcfi), 1) + msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.142); + else + CFLAGS += -DHAVE_DWARF_CFI_SUPPORT + endif # dwarf_getcfi endif # Dwarf support endif # libelf support endif # NO_LIBELF @@ -680,15 +685,15 @@ ifndef BUILD_BPF_SKEL endif ifeq ($(BUILD_BPF_SKEL),1) - ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),) - dummy := $(warning Warning: Disabled BPF skeletons as libbpf is required) - BUILD_BPF_SKEL := 0 - else ifeq ($(filter -DHAVE_LIBELF_SUPPORT, $(CFLAGS)),) + ifeq ($(filter -DHAVE_LIBELF_SUPPORT, $(CFLAGS)),) dummy := $(warning Warning: Disabled BPF skeletons as libelf is required by bpftool) BUILD_BPF_SKEL := 0 else ifeq ($(filter -DHAVE_ZLIB_SUPPORT, $(CFLAGS)),) dummy := $(warning Warning: Disabled BPF skeletons as zlib is required by bpftool) BUILD_BPF_SKEL := 0 + else ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),) + dummy := $(warning Warning: Disabled BPF skeletons as libbpf is required) + BUILD_BPF_SKEL := 0 else ifeq ($(call get-executable,$(CLANG)),) dummy := $(warning Warning: Disabled BPF skeletons as clang ($(CLANG)) is missing) BUILD_BPF_SKEL := 0 diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 058c9aecf608..27e7c478880f 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -134,6 +134,8 @@ include ../scripts/utilities.mak # x86 instruction decoder - new instructions test # # Define GEN_VMLINUX_H to generate vmlinux.h from the BTF. +# +# Define NO_SHELLCHECK if you do not want to run shellcheck during build # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL @@ -227,8 +229,15 @@ else force_fixdep := $(config) endif +# Runs shellcheck on perf test shell scripts +ifeq ($(NO_SHELLCHECK),1) + SHELLCHECK := +else + SHELLCHECK := $(shell which shellcheck 2> /dev/null) +endif + export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK -export HOSTCC HOSTLD HOSTAR HOSTCFLAGS +export HOSTCC HOSTLD HOSTAR HOSTCFLAGS SHELLCHECK include $(srctree)/tools/build/Makefile.include @@ -1152,7 +1161,7 @@ bpf-skel-clean: clean:: $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBSYMBOL)-clean $(LIBPERF)-clean arm64-sysreg-defs-clean fixdep-clean python-clean bpf-skel-clean tests-coresight-targets-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-iostat $(LANG_BINDINGS) - $(Q)find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete + $(Q)find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete -o -name '*.shellcheck_log' -delete $(Q)$(RM) $(OUTPUT).config-detected $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)$(LIBJVMTI).so $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \ diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 2cf873d71dff..77e6663c1703 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -199,7 +199,7 @@ static int cs_etm_validate_config(struct auxtrace_record *itr, { int i, err = -EINVAL; struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus; - struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); + struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus(); /* Set option of each CPU we have */ for (i = 0; i < cpu__max_cpu().cpu; i++) { @@ -211,7 +211,7 @@ static int cs_etm_validate_config(struct auxtrace_record *itr, * program can run on any CPUs in this case, thus don't skip * validation. */ - if (!perf_cpu_map__empty(event_cpus) && + if (!perf_cpu_map__has_any_cpu_or_is_empty(event_cpus) && !perf_cpu_map__has(event_cpus, cpu)) continue; @@ -435,7 +435,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, * Also the case of per-cpu mmaps, need the contextID in order to be notified * when a context switch happened. */ - if (!perf_cpu_map__empty(cpus)) { + if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) { evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel, "timestamp", 1); evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel, @@ -461,7 +461,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, evsel->core.attr.sample_period = 1; /* In per-cpu case, always need the time of mmap events etc */ - if (!perf_cpu_map__empty(cpus)) + if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) evsel__set_sample_bit(evsel, TIME); err = cs_etm_validate_config(itr, cs_etm_evsel); @@ -536,10 +536,10 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused, int i; int etmv3 = 0, etmv4 = 0, ete = 0; struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus; - struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); + struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus(); /* cpu map is not empty, we have specific CPUs to work with */ - if (!perf_cpu_map__empty(event_cpus)) { + if (!perf_cpu_map__has_any_cpu_or_is_empty(event_cpus)) { for (i = 0; i < cpu__max_cpu().cpu; i++) { struct perf_cpu cpu = { .cpu = i, }; @@ -802,7 +802,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, u64 nr_cpu, type; struct perf_cpu_map *cpu_map; struct perf_cpu_map *event_cpus = session->evlist->core.user_requested_cpus; - struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL); + struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus(); struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; @@ -814,7 +814,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, return -EINVAL; /* If the cpu_map is empty all online CPUs are involved */ - if (perf_cpu_map__empty(event_cpus)) { + if (perf_cpu_map__has_any_cpu_or_is_empty(event_cpus)) { cpu_map = online_cpus; } else { /* Make sure all specified CPUs are online */ diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index e3acc739bd00..51ccbfd3d246 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -232,7 +232,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, * In the case of per-cpu mmaps, sample CPU for AUX event; * also enable the timestamp tracing for samples correlation. */ - if (!perf_cpu_map__empty(cpus)) { + if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) { evsel__set_sample_bit(arm_spe_evsel, CPU); evsel__set_config_if_unset(arm_spe_pmu, arm_spe_evsel, "ts_enable", 1); @@ -265,7 +265,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, tracking_evsel->core.attr.sample_period = 1; /* In per-cpu case, always need the time of mmap events etc */ - if (!perf_cpu_map__empty(cpus)) { + if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) { evsel__set_sample_bit(tracking_evsel, TIME); evsel__set_sample_bit(tracking_evsel, CPU); diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index a2eef9ec5491..97037499152e 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -57,7 +57,7 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus) int get_cpuid(char *buf, size_t sz) { - struct perf_cpu_map *cpus = perf_cpu_map__new(NULL); + struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus(); int ret; if (!cpus) diff --git a/tools/perf/arch/loongarch/annotate/instructions.c b/tools/perf/arch/loongarch/annotate/instructions.c index 98e19c5366ac..21cc7e4149f7 100644 --- a/tools/perf/arch/loongarch/annotate/instructions.c +++ b/tools/perf/arch/loongarch/annotate/instructions.c @@ -61,10 +61,10 @@ static int loongarch_jump__parse(struct arch *arch, struct ins_operands *ops, st const char *c = strchr(ops->raw, '#'); u64 start, end; - ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char); - ops->raw_func_start = strchr(ops->raw, '<'); + ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char); + ops->jump.raw_func_start = strchr(ops->raw, '<'); - if (ops->raw_func_start && c > ops->raw_func_start) + if (ops->jump.raw_func_start && c > ops->jump.raw_func_start) c = NULL; if (c++ != NULL) diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index 5741ffe47312..e65b7dbe27fb 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -14,66 +14,79 @@ #if defined(__x86_64__) -int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, - perf_event__handler_t process, - struct machine *machine) +struct perf_event__synthesize_extra_kmaps_cb_args { + struct perf_tool *tool; + perf_event__handler_t process; + struct machine *machine; + union perf_event *event; +}; + +static int perf_event__synthesize_extra_kmaps_cb(struct map *map, void *data) { - int rc = 0; - struct map_rb_node *pos; - struct maps *kmaps = machine__kernel_maps(machine); - union perf_event *event = zalloc(sizeof(event->mmap) + - machine->id_hdr_size); + struct perf_event__synthesize_extra_kmaps_cb_args *args = data; + union perf_event *event = args->event; + struct kmap *kmap; + size_t size; - if (!event) { - pr_debug("Not enough memory synthesizing mmap event " - "for extra kernel maps\n"); - return -1; - } + if (!__map__is_extra_kernel_map(map)) + return 0; - maps__for_each_entry(kmaps, pos) { - struct kmap *kmap; - size_t size; - struct map *map = pos->map; + kmap = map__kmap(map); - if (!__map__is_extra_kernel_map(map)) - continue; + size = sizeof(event->mmap) - sizeof(event->mmap.filename) + + PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) + + args->machine->id_hdr_size; - kmap = map__kmap(map); + memset(event, 0, size); - size = sizeof(event->mmap) - sizeof(event->mmap.filename) + - PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) + - machine->id_hdr_size; + event->mmap.header.type = PERF_RECORD_MMAP; - memset(event, 0, size); + /* + * kernel uses 0 for user space maps, see kernel/perf_event.c + * __perf_event_mmap + */ + if (machine__is_host(args->machine)) + event->header.misc = PERF_RECORD_MISC_KERNEL; + else + event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; - event->mmap.header.type = PERF_RECORD_MMAP; + event->mmap.header.size = size; - /* - * kernel uses 0 for user space maps, see kernel/perf_event.c - * __perf_event_mmap - */ - if (machine__is_host(machine)) - event->header.misc = PERF_RECORD_MISC_KERNEL; - else - event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; + event->mmap.start = map__start(map); + event->mmap.len = map__size(map); + event->mmap.pgoff = map__pgoff(map); + event->mmap.pid = args->machine->pid; - event->mmap.header.size = size; + strlcpy(event->mmap.filename, kmap->name, PATH_MAX); - event->mmap.start = map__start(map); - event->mmap.len = map__size(map); - event->mmap.pgoff = map__pgoff(map); - event->mmap.pid = machine->pid; + if (perf_tool__process_synth_event(args->tool, event, args->machine, args->process) != 0) + return -1; - strlcpy(event->mmap.filename, kmap->name, PATH_MAX); + return 0; +} - if (perf_tool__process_synth_event(tool, event, machine, - process) != 0) { - rc = -1; - break; - } +int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + int rc; + struct maps *kmaps = machine__kernel_maps(machine); + struct perf_event__synthesize_extra_kmaps_cb_args args = { + .tool = tool, + .process = process, + .machine = machine, + .event = zalloc(sizeof(args.event->mmap) + machine->id_hdr_size), + }; + + if (!args.event) { + pr_debug("Not enough memory synthesizing mmap event " + "for extra kernel maps\n"); + return -1; } - free(event); + rc = maps__for_each_map(kmaps, perf_event__synthesize_extra_kmaps_cb, &args); + + free(args.event); return rc; } diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index d2c8cac11470..af8ae4647585 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -143,7 +143,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, if (!opts->full_auxtrace) return 0; - if (opts->full_auxtrace && !perf_cpu_map__empty(cpus)) { + if (opts->full_auxtrace && !perf_cpu_map__has_any_cpu_or_is_empty(cpus)) { pr_err(INTEL_BTS_PMU_NAME " does not support per-cpu recording\n"); return -EINVAL; } @@ -224,7 +224,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, * In the case of per-cpu mmaps, we need the CPU on the * AUX event. */ - if (!perf_cpu_map__empty(cpus)) + if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) evsel__set_sample_bit(intel_bts_evsel, CPU); } diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index fa0c718b9e72..d199619df3ab 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -369,7 +369,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, ui__warning("Intel Processor Trace: TSC not available\n"); } - per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.user_requested_cpus); + per_cpu_mmaps = !perf_cpu_map__has_any_cpu_or_is_empty(session->evlist->core.user_requested_cpus); auxtrace_info->type = PERF_AUXTRACE_INTEL_PT; auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type; @@ -774,7 +774,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * Per-cpu recording needs sched_switch events to distinguish different * threads. */ - if (have_timing_info && !perf_cpu_map__empty(cpus) && + if (have_timing_info && !perf_cpu_map__has_any_cpu_or_is_empty(cpus) && !record_opts__no_switch_events(opts)) { if (perf_can_record_switch_events()) { bool cpu_wide = !target__none(&opts->target) && @@ -832,7 +832,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * In the case of per-cpu mmaps, we need the CPU on the * AUX event. */ - if (!perf_cpu_map__empty(cpus)) + if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) evsel__set_sample_bit(intel_pt_evsel, CPU); } @@ -858,7 +858,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, tracking_evsel->immediate = true; /* In per-cpu case, always need the time of mmap events etc */ - if (!perf_cpu_map__empty(cpus)) { + if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) { evsel__set_sample_bit(tracking_evsel, TIME); /* And the CPU for switch events */ evsel__set_sample_bit(tracking_evsel, CPU); @@ -870,7 +870,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * Warn the user when we do not have enough information to decode i.e. * per-cpu with no sched_switch (except workload-only). */ - if (!ptr->have_sched_switch && !perf_cpu_map__empty(cpus) && + if (!ptr->have_sched_switch && !perf_cpu_map__has_any_cpu_or_is_empty(cpus) && !target__none(&opts->target) && !intel_pt_evsel->core.attr.exclude_user) ui__warning("Intel Processor Trace decoding will not be possible except for kernel tracing!\n"); diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 6bfffe83dde9..d3db73dac66a 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -330,7 +330,7 @@ int bench_epoll_ctl(int argc, const char **argv) act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); - cpu = perf_cpu_map__new(NULL); + cpu = perf_cpu_map__new_online_cpus(); if (!cpu) goto errmem; diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index cb5174b53940..06bb3187660a 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -444,7 +444,7 @@ int bench_epoll_wait(int argc, const char **argv) act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); - cpu = perf_cpu_map__new(NULL); + cpu = perf_cpu_map__new_online_cpus(); if (!cpu) goto errmem; diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index 2005a3fa3026..0c69d20efa32 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -138,7 +138,7 @@ int bench_futex_hash(int argc, const char **argv) exit(EXIT_FAILURE); } - cpu = perf_cpu_map__new(NULL); + cpu = perf_cpu_map__new_online_cpus(); if (!cpu) goto errmem; diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 092cbd52db82..7a4973346180 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -172,7 +172,7 @@ int bench_futex_lock_pi(int argc, const char **argv) if (argc) goto err; - cpu = perf_cpu_map__new(NULL); + cpu = perf_cpu_map__new_online_cpus(); if (!cpu) err(EXIT_FAILURE, "calloc"); diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index c0035990a33c..d9ad736c1a3e 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -174,7 +174,7 @@ int bench_futex_requeue(int argc, const char **argv) if (argc) goto err; - cpu = perf_cpu_map__new(NULL); + cpu = perf_cpu_map__new_online_cpus(); if (!cpu) err(EXIT_FAILURE, "cpu_map__new"); diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 5ab0234d74e6..b66df553e561 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -264,7 +264,7 @@ int bench_futex_wake_parallel(int argc, const char **argv) err(EXIT_FAILURE, "mlockall"); } - cpu = perf_cpu_map__new(NULL); + cpu = perf_cpu_map__new_online_cpus(); if (!cpu) err(EXIT_FAILURE, "calloc"); diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index 18a5894af8bb..690fd6d3da13 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -149,7 +149,7 @@ int bench_futex_wake(int argc, const char **argv) exit(EXIT_FAILURE); } - cpu = perf_cpu_map__new(NULL); + cpu = perf_cpu_map__new_online_cpus(); if (!cpu) err(EXIT_FAILURE, "calloc"); diff --git a/tools/perf/bench/sched-seccomp-notify.c b/tools/perf/bench/sched-seccomp-notify.c index a01c40131493..269c1f4a6852 100644 --- a/tools/perf/bench/sched-seccomp-notify.c +++ b/tools/perf/bench/sched-seccomp-notify.c @@ -32,7 +32,7 @@ static bool sync_mode; static const struct option options[] = { OPT_U64('l', "loop", &loops, "Specify number of loops"), OPT_BOOLEAN('s', "sync-mode", &sync_mode, - "Enable the synchronious mode for seccomp notifications"), + "Enable the synchronous mode for seccomp notifications"), OPT_END() }; diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index aeeb801f1ed7..d880f1b039fd 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -45,7 +45,6 @@ struct perf_annotate { struct perf_tool tool; struct perf_session *session; - struct annotation_options opts; #ifdef HAVE_SLANG_SUPPORT bool use_tui; #endif @@ -94,6 +93,7 @@ static void process_basic_block(struct addr_map_symbol *start, struct annotation *notes = sym ? symbol__annotation(sym) : NULL; struct block_range_iter iter; struct block_range *entry; + struct annotated_branch *branch; /* * Sanity; NULL isn't executable and the CPU cannot execute backwards @@ -105,6 +105,8 @@ static void process_basic_block(struct addr_map_symbol *start, if (!block_range_iter__valid(&iter)) return; + branch = annotation__get_branch(notes); + /* * First block in range is a branch target. */ @@ -118,8 +120,8 @@ static void process_basic_block(struct addr_map_symbol *start, entry->coverage++; entry->sym = sym; - if (notes) - notes->max_coverage = max(notes->max_coverage, entry->coverage); + if (branch) + branch->max_coverage = max(branch->max_coverage, entry->coverage); } while (block_range_iter__next(&iter)); @@ -315,9 +317,9 @@ static int hist_entry__tty_annotate(struct hist_entry *he, struct perf_annotate *ann) { if (!ann->use_stdio2) - return symbol__tty_annotate(&he->ms, evsel, &ann->opts); + return symbol__tty_annotate(&he->ms, evsel); - return symbol__tty_annotate2(&he->ms, evsel, &ann->opts); + return symbol__tty_annotate2(&he->ms, evsel); } static void hists__find_annotations(struct hists *hists, @@ -363,7 +365,6 @@ find_next: int ret; int (*annotate)(struct hist_entry *he, struct evsel *evsel, - struct annotation_options *options, struct hist_browser_timer *hbt); annotate = dlsym(perf_gtk_handle, @@ -373,14 +374,14 @@ find_next: return; } - ret = annotate(he, evsel, &ann->opts, NULL); + ret = annotate(he, evsel, NULL); if (!ret || !ann->skip_missing) return; /* skip missing symbols */ nd = rb_next(nd); } else if (use_browser == 1) { - key = hist_entry__tui_annotate(he, evsel, NULL, &ann->opts); + key = hist_entry__tui_annotate(he, evsel, NULL); switch (key) { case -1: @@ -422,9 +423,9 @@ static int __cmd_annotate(struct perf_annotate *ann) goto out; } - if (!ann->opts.objdump_path) { + if (!annotate_opts.objdump_path) { ret = perf_env__lookup_objdump(&session->header.env, - &ann->opts.objdump_path); + &annotate_opts.objdump_path); if (ret) goto out; } @@ -558,9 +559,9 @@ int cmd_annotate(int argc, const char **argv) "file", "vmlinux pathname"), OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules, "load module symbols - WARNING: use only with -k and LIVE kernel"), - OPT_BOOLEAN('l', "print-line", &annotate.opts.print_lines, + OPT_BOOLEAN('l', "print-line", &annotate_opts.print_lines, "print matching source lines (may be slow)"), - OPT_BOOLEAN('P', "full-paths", &annotate.opts.full_path, + OPT_BOOLEAN('P', "full-paths", &annotate_opts.full_path, "Don't shorten the displayed pathnames"), OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing, "Skip symbols that cannot be annotated"), @@ -571,15 +572,15 @@ int cmd_annotate(int argc, const char **argv) OPT_CALLBACK(0, "symfs", NULL, "directory", "Look for files with symbols relative to this directory", symbol__config_symfs), - OPT_BOOLEAN(0, "source", &annotate.opts.annotate_src, + OPT_BOOLEAN(0, "source", &annotate_opts.annotate_src, "Interleave source code with assembly code (default)"), - OPT_BOOLEAN(0, "asm-raw", &annotate.opts.show_asm_raw, + OPT_BOOLEAN(0, "asm-raw", &annotate_opts.show_asm_raw, "Display raw encoding of assembly instructions (default)"), OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), - OPT_STRING(0, "prefix", &annotate.opts.prefix, "prefix", + OPT_STRING(0, "prefix", &annotate_opts.prefix, "prefix", "Add prefix to source file path names in programs (with --prefix-strip)"), - OPT_STRING(0, "prefix-strip", &annotate.opts.prefix_strip, "N", + OPT_STRING(0, "prefix-strip", &annotate_opts.prefix_strip, "N", "Strip first N entries of source file path name in programs (with --prefix)"), OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), @@ -598,7 +599,7 @@ int cmd_annotate(int argc, const char **argv) OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode", "'always' (default), 'never' or 'auto' only applicable to --stdio mode", stdio__config_color, "always"), - OPT_CALLBACK(0, "percent-type", &annotate.opts, "local-period", + OPT_CALLBACK(0, "percent-type", &annotate_opts, "local-period", "Set percent type local/global-period/hits", annotate_parse_percent_type), OPT_CALLBACK(0, "percent-limit", &annotate, "percent", @@ -614,13 +615,13 @@ int cmd_annotate(int argc, const char **argv) set_option_flag(options, 0, "show-total-period", PARSE_OPT_EXCLUSIVE); set_option_flag(options, 0, "show-nr-samples", PARSE_OPT_EXCLUSIVE); - annotation_options__init(&annotate.opts); + annotation_options__init(); ret = hists__init(); if (ret < 0) return ret; - annotation_config__init(&annotate.opts); + annotation_config__init(); argc = parse_options(argc, argv, options, annotate_usage, 0); if (argc) { @@ -635,13 +636,13 @@ int cmd_annotate(int argc, const char **argv) } if (disassembler_style) { - annotate.opts.disassembler_style = strdup(disassembler_style); - if (!annotate.opts.disassembler_style) + annotate_opts.disassembler_style = strdup(disassembler_style); + if (!annotate_opts.disassembler_style) return -ENOMEM; } if (objdump_path) { - annotate.opts.objdump_path = strdup(objdump_path); - if (!annotate.opts.objdump_path) + annotate_opts.objdump_path = strdup(objdump_path); + if (!annotate_opts.objdump_path) return -ENOMEM; } if (addr2line_path) { @@ -650,7 +651,7 @@ int cmd_annotate(int argc, const char **argv) return -ENOMEM; } - if (annotate_check_args(&annotate.opts) < 0) + if (annotate_check_args() < 0) return -EINVAL; #ifdef HAVE_GTK2_SUPPORT @@ -731,7 +732,7 @@ out_delete: #ifndef NDEBUG perf_session__delete(annotate.session); #endif - annotation_options__exit(&annotate.opts); + annotation_options__exit(); return ret; } diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index a4cf9de7a7b5..f78eea9e2153 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -2320,7 +2320,7 @@ static int setup_nodes(struct perf_session *session) nodes[node] = set; /* empty node, skip */ - if (perf_cpu_map__empty(map)) + if (perf_cpu_map__has_any_cpu_or_is_empty(map)) continue; perf_cpu_map__for_each_cpu(cpu, idx, map) { diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index ac2e6c75f912..eb30c8eca488 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -333,7 +333,7 @@ static int set_tracing_func_irqinfo(struct perf_ftrace *ftrace) static int reset_tracing_cpu(void) { - struct perf_cpu_map *cpumap = perf_cpu_map__new(NULL); + struct perf_cpu_map *cpumap = perf_cpu_map__new_online_cpus(); int ret; ret = set_tracing_cpumask(cpumap); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index c8cf2fdd9cff..eb3ef5c24b66 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -2265,6 +2265,12 @@ int cmd_inject(int argc, const char **argv) "perf inject [<options>]", NULL }; + + if (!inject.itrace_synth_opts.set) { + /* Disable eager loading of kernel symbols that adds overhead to perf inject. */ + symbol_conf.lazy_load_kernel_maps = true; + } + #ifndef HAVE_JITDUMP set_option_nobuild(options, 'j', "jit", "NO_LIBELF=1", true); #endif diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index a3ff2f4edbaa..230461280e45 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -2285,8 +2285,10 @@ setup_args: else ev_name = strdup(contention_tracepoints[j].name); - if (!ev_name) + if (!ev_name) { + free(rec_argv); return -ENOMEM; + } rec_argv[i++] = "-e"; rec_argv[i++] = ev_name; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index dcf288a4fb9a..a89013c44fd5 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -270,7 +270,7 @@ static int record__write(struct record *rec, struct mmap *map __maybe_unused, static int record__aio_enabled(struct record *rec); static int record__comp_enabled(struct record *rec); -static size_t zstd_compress(struct perf_session *session, struct mmap *map, +static ssize_t zstd_compress(struct perf_session *session, struct mmap *map, void *dst, size_t dst_size, void *src, size_t src_size); #ifdef HAVE_AIO_SUPPORT @@ -405,9 +405,13 @@ static int record__aio_pushfn(struct mmap *map, void *to, void *buf, size_t size */ if (record__comp_enabled(aio->rec)) { - size = zstd_compress(aio->rec->session, NULL, aio->data + aio->size, - mmap__mmap_len(map) - aio->size, - buf, size); + ssize_t compressed = zstd_compress(aio->rec->session, NULL, aio->data + aio->size, + mmap__mmap_len(map) - aio->size, + buf, size); + if (compressed < 0) + return (int)compressed; + + size = compressed; } else { memcpy(aio->data + aio->size, buf, size); } @@ -633,7 +637,13 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size) struct record *rec = to; if (record__comp_enabled(rec)) { - size = zstd_compress(rec->session, map, map->data, mmap__mmap_len(map), bf, size); + ssize_t compressed = zstd_compress(rec->session, map, map->data, + mmap__mmap_len(map), bf, size); + + if (compressed < 0) + return (int)compressed; + + size = compressed; bf = map->data; } @@ -1350,7 +1360,7 @@ static int record__open(struct record *rec) evlist__for_each_entry(evlist, pos) { try_again: if (evsel__open(pos, pos->core.cpus, pos->core.threads) < 0) { - if (evsel__fallback(pos, errno, msg, sizeof(msg))) { + if (evsel__fallback(pos, &opts->target, errno, msg, sizeof(msg))) { if (verbose > 0) ui__warning("%s\n", msg); goto try_again; @@ -1527,10 +1537,10 @@ static size_t process_comp_header(void *record, size_t increment) return size; } -static size_t zstd_compress(struct perf_session *session, struct mmap *map, +static ssize_t zstd_compress(struct perf_session *session, struct mmap *map, void *dst, size_t dst_size, void *src, size_t src_size) { - size_t compressed; + ssize_t compressed; size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed) - 1; struct zstd_data *zstd_data = &session->zstd_data; @@ -1539,6 +1549,8 @@ static size_t zstd_compress(struct perf_session *session, struct mmap *map, compressed = zstd_compress_stream_to_records(zstd_data, dst, dst_size, src, src_size, max_record_size, process_comp_header); + if (compressed < 0) + return compressed; if (map && map->file) { thread->bytes_transferred += src_size; @@ -1912,21 +1924,13 @@ static void __record__save_lost_samples(struct record *rec, struct evsel *evsel, static void record__read_lost_samples(struct record *rec) { struct perf_session *session = rec->session; - struct perf_record_lost_samples *lost; + struct perf_record_lost_samples *lost = NULL; struct evsel *evsel; /* there was an error during record__open */ if (session->evlist == NULL) return; - lost = zalloc(PERF_SAMPLE_MAX_SIZE); - if (lost == NULL) { - pr_debug("Memory allocation failed\n"); - return; - } - - lost->header.type = PERF_RECORD_LOST_SAMPLES; - evlist__for_each_entry(session->evlist, evsel) { struct xyarray *xy = evsel->core.sample_id; u64 lost_count; @@ -1949,6 +1953,14 @@ static void record__read_lost_samples(struct record *rec) } if (count.lost) { + if (!lost) { + lost = zalloc(PERF_SAMPLE_MAX_SIZE); + if (!lost) { + pr_debug("Memory allocation failed\n"); + return; + } + lost->header.type = PERF_RECORD_LOST_SAMPLES; + } __record__save_lost_samples(rec, evsel, lost, x, y, count.lost, 0); } @@ -1956,9 +1968,18 @@ static void record__read_lost_samples(struct record *rec) } lost_count = perf_bpf_filter__lost_count(evsel); - if (lost_count) + if (lost_count) { + if (!lost) { + lost = zalloc(PERF_SAMPLE_MAX_SIZE); + if (!lost) { + pr_debug("Memory allocation failed\n"); + return; + } + lost->header.type = PERF_RECORD_LOST_SAMPLES; + } __record__save_lost_samples(rec, evsel, lost, 0, 0, lost_count, PERF_RECORD_MISC_LOST_SAMPLES_BPF); + } } out: free(lost); @@ -2216,32 +2237,6 @@ static void hit_auxtrace_snapshot_trigger(struct record *rec) } } -static void record__uniquify_name(struct record *rec) -{ - struct evsel *pos; - struct evlist *evlist = rec->evlist; - char *new_name; - int ret; - - if (perf_pmus__num_core_pmus() == 1) - return; - - evlist__for_each_entry(evlist, pos) { - if (!evsel__is_hybrid(pos)) - continue; - - if (strchr(pos->name, '/')) - continue; - - ret = asprintf(&new_name, "%s/%s/", - pos->pmu_name, pos->name); - if (ret) { - free(pos->name); - pos->name = new_name; - } - } -} - static int record__terminate_thread(struct record_thread *thread_data) { int err; @@ -2475,7 +2470,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (data->is_pipe && rec->evlist->core.nr_entries == 1) rec->opts.sample_id = true; - record__uniquify_name(rec); + evlist__uniquify_name(rec->evlist); /* Debug message used by test scripts */ pr_debug3("perf record opening and mmapping events\n"); @@ -3580,9 +3575,7 @@ static int record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cp if (cpu_map__is_dummy(cpus)) return 0; - perf_cpu_map__for_each_cpu(cpu, idx, cpus) { - if (cpu.cpu == -1) - continue; + perf_cpu_map__for_each_cpu_skip_any(cpu, idx, cpus) { /* Return ENODEV is input cpu is greater than max cpu */ if ((unsigned long)cpu.cpu > mask->nbits) return -ENODEV; @@ -3989,6 +3982,8 @@ int cmd_record(int argc, const char **argv) # undef set_nobuild #endif + /* Disable eager loading of kernel symbols that adds overhead to perf record. */ + symbol_conf.lazy_load_kernel_maps = true; rec->opts.affinity = PERF_AFFINITY_SYS; rec->evlist = evlist__new(); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 9cb1da2dc0c0..178fb602bc98 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -98,7 +98,6 @@ struct report { bool skip_empty; int max_stack; struct perf_read_values show_threads_values; - struct annotation_options annotation_opts; const char *pretty_printing_style; const char *cpu_list; const char *symbol_filter_str; @@ -541,8 +540,7 @@ static int evlist__tui_block_hists_browse(struct evlist *evlist, struct report * evlist__for_each_entry(evlist, pos) { ret = report__browse_block_hists(&rep->block_reports[i++].hist, rep->min_percent, pos, - &rep->session->header.env, - &rep->annotation_opts); + &rep->session->header.env); if (ret != 0) return ret; } @@ -574,8 +572,7 @@ static int evlist__tty_browse_hists(struct evlist *evlist, struct report *rep, c if (rep->total_cycles_mode) { report__browse_block_hists(&rep->block_reports[i++].hist, - rep->min_percent, pos, - NULL, NULL); + rep->min_percent, pos, NULL); continue; } @@ -670,7 +667,7 @@ static int report__browse_hists(struct report *rep) } ret = evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent, - &session->header.env, true, &rep->annotation_opts); + &session->header.env, true); /* * Usually "ret" is the last pressed key, and we only * care if the key notifies us to switch data file. @@ -745,7 +742,7 @@ static int hists__resort_cb(struct hist_entry *he, void *arg) if (rep->symbol_ipc && sym && !sym->annotate2) { struct evsel *evsel = hists_to_evsel(he->hists); - symbol__annotate2(&he->ms, evsel, &rep->annotation_opts, NULL); + symbol__annotate2(&he->ms, evsel, NULL); } return 0; @@ -859,27 +856,47 @@ static struct task *tasks_list(struct task *task, struct machine *machine) return tasks_list(parent_task, machine); } -static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp) +struct maps__fprintf_task_args { + int indent; + FILE *fp; + size_t printed; +}; + +static int maps__fprintf_task_cb(struct map *map, void *data) { - size_t printed = 0; - struct map_rb_node *rb_node; + struct maps__fprintf_task_args *args = data; + const struct dso *dso = map__dso(map); + u32 prot = map__prot(map); + int ret; - maps__for_each_entry(maps, rb_node) { - struct map *map = rb_node->map; - const struct dso *dso = map__dso(map); - u32 prot = map__prot(map); + ret = fprintf(args->fp, + "%*s %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n", + args->indent, "", map__start(map), map__end(map), + prot & PROT_READ ? 'r' : '-', + prot & PROT_WRITE ? 'w' : '-', + prot & PROT_EXEC ? 'x' : '-', + map__flags(map) ? 's' : 'p', + map__pgoff(map), + dso->id.ino, dso->name); - printed += fprintf(fp, "%*s %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n", - indent, "", map__start(map), map__end(map), - prot & PROT_READ ? 'r' : '-', - prot & PROT_WRITE ? 'w' : '-', - prot & PROT_EXEC ? 'x' : '-', - map__flags(map) ? 's' : 'p', - map__pgoff(map), - dso->id.ino, dso->name); - } + if (ret < 0) + return ret; + + args->printed += ret; + return 0; +} + +static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp) +{ + struct maps__fprintf_task_args args = { + .indent = indent, + .fp = fp, + .printed = 0, + }; - return printed; + maps__for_each_map(maps, maps__fprintf_task_cb, &args); + + return args.printed; } static void task__print_level(struct task *task, FILE *fp, int level) @@ -1341,15 +1358,15 @@ int cmd_report(int argc, const char **argv) "list of cpus to profile"), OPT_BOOLEAN('I', "show-info", &report.show_full_info, "Display extended information about perf.data file"), - OPT_BOOLEAN(0, "source", &report.annotation_opts.annotate_src, + OPT_BOOLEAN(0, "source", &annotate_opts.annotate_src, "Interleave source code with assembly code (default)"), - OPT_BOOLEAN(0, "asm-raw", &report.annotation_opts.show_asm_raw, + OPT_BOOLEAN(0, "asm-raw", &annotate_opts.show_asm_raw, "Display raw encoding of assembly instructions (default)"), OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), - OPT_STRING(0, "prefix", &report.annotation_opts.prefix, "prefix", + OPT_STRING(0, "prefix", &annotate_opts.prefix, "prefix", "Add prefix to source file path names in programs (with --prefix-strip)"), - OPT_STRING(0, "prefix-strip", &report.annotation_opts.prefix_strip, "N", + OPT_STRING(0, "prefix-strip", &annotate_opts.prefix_strip, "N", "Strip first N entries of source file path name in programs (with --prefix)"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), @@ -1401,7 +1418,7 @@ int cmd_report(int argc, const char **argv) "Time span of interest (start,stop)"), OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name, "Show inline function"), - OPT_CALLBACK(0, "percent-type", &report.annotation_opts, "local-period", + OPT_CALLBACK(0, "percent-type", &annotate_opts, "local-period", "Set percent type local/global-period/hits", annotate_parse_percent_type), OPT_BOOLEAN(0, "ns", &symbol_conf.nanosecs, "Show times in nanosecs"), @@ -1426,7 +1443,14 @@ int cmd_report(int argc, const char **argv) if (ret < 0) goto exit; - annotation_options__init(&report.annotation_opts); + /* + * tasks_mode require access to exited threads to list those that are in + * the data file. Off-cpu events are synthesized after other events and + * reference exited threads. + */ + symbol_conf.keep_exited_threads = true; + + annotation_options__init(); ret = perf_config(report__config, &report); if (ret) @@ -1445,13 +1469,13 @@ int cmd_report(int argc, const char **argv) } if (disassembler_style) { - report.annotation_opts.disassembler_style = strdup(disassembler_style); - if (!report.annotation_opts.disassembler_style) + annotate_opts.disassembler_style = strdup(disassembler_style); + if (!annotate_opts.disassembler_style) return -ENOMEM; } if (objdump_path) { - report.annotation_opts.objdump_path = strdup(objdump_path); - if (!report.annotation_opts.objdump_path) + annotate_opts.objdump_path = strdup(objdump_path); + if (!annotate_opts.objdump_path) return -ENOMEM; } if (addr2line_path) { @@ -1460,7 +1484,7 @@ int cmd_report(int argc, const char **argv) return -ENOMEM; } - if (annotate_check_args(&report.annotation_opts) < 0) { + if (annotate_check_args() < 0) { ret = -EINVAL; goto exit; } @@ -1692,7 +1716,7 @@ repeat: */ symbol_conf.priv_size += sizeof(u32); } - annotation_config__init(&report.annotation_opts); + annotation_config__init(); } if (symbol__init(&session->header.env) < 0) @@ -1746,7 +1770,7 @@ error: zstd_fini(&(session->zstd_data)); perf_session__delete(session); exit: - annotation_options__exit(&report.annotation_opts); + annotation_options__exit(); free(sort_order_help); free(field_order_help); return ret; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index a3af805a1d57..5fe9abc6a524 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -653,7 +653,7 @@ static enum counter_recovery stat_handle_error(struct evsel *counter) if ((evsel__leader(counter) != counter) || !(counter->core.leader->nr_members > 1)) return COUNTER_SKIP; - } else if (evsel__fallback(counter, errno, msg, sizeof(msg))) { + } else if (evsel__fallback(counter, &target, errno, msg, sizeof(msg))) { if (verbose > 0) ui__warning("%s\n", msg); return COUNTER_RETRY; @@ -1204,8 +1204,9 @@ static struct option stat_options[] = { OPT_STRING('C', "cpu", &target.cpu_list, "cpu", "list of cpus to monitor in system-wide"), OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode, - "disable CPU count aggregation", AGGR_NONE), - OPT_BOOLEAN(0, "no-merge", &stat_config.no_merge, "Do not merge identical named events"), + "disable aggregation across CPUs or PMUs", AGGR_NONE), + OPT_SET_UINT(0, "no-merge", &stat_config.aggr_mode, + "disable aggregation the same as -A or -no-aggr", AGGR_NONE), OPT_BOOLEAN(0, "hybrid-merge", &stat_config.hybrid_merge, "Merge identical named hybrid events"), OPT_STRING('x', "field-separator", &stat_config.csv_sep, "separator", @@ -1255,7 +1256,7 @@ static struct option stat_options[] = { OPT_BOOLEAN(0, "metric-no-merge", &stat_config.metric_no_merge, "don't try to share events between metrics in a group"), OPT_BOOLEAN(0, "metric-no-threshold", &stat_config.metric_no_threshold, - "don't try to share events between metrics in a group "), + "disable adding events for the metric threshold calculation"), OPT_BOOLEAN(0, "topdown", &topdown_run, "measure top-down statistics"), OPT_UINTEGER(0, "td-level", &stat_config.topdown_level, @@ -1316,7 +1317,7 @@ static int cpu__get_cache_id_from_map(struct perf_cpu cpu, char *map) * be the first online CPU in the cache domain else use the * first online CPU of the cache domain as the ID. */ - if (perf_cpu_map__empty(cpu_map)) + if (perf_cpu_map__has_any_cpu_or_is_empty(cpu_map)) id = cpu.cpu; else id = perf_cpu_map__cpu(cpu_map, 0).cpu; @@ -1622,7 +1623,7 @@ static int perf_stat_init_aggr_mode(void) * taking the highest cpu number to be the size of * the aggregation translate cpumap. */ - if (!perf_cpu_map__empty(evsel_list->core.user_requested_cpus)) + if (!perf_cpu_map__has_any_cpu_or_is_empty(evsel_list->core.user_requested_cpus)) nr = perf_cpu_map__max(evsel_list->core.user_requested_cpus).cpu; else nr = 0; @@ -2289,7 +2290,7 @@ int process_stat_config_event(struct perf_session *session, perf_event__read_stat_config(&stat_config, &event->stat_config); - if (perf_cpu_map__empty(st->cpus)) { + if (perf_cpu_map__has_any_cpu_or_is_empty(st->cpus)) { if (st->aggr_mode != AGGR_UNSET) pr_warning("warning: processing task data, aggregation mode not set\n"); } else if (st->aggr_mode != AGGR_UNSET) { @@ -2695,15 +2696,19 @@ int cmd_stat(int argc, const char **argv) */ if (metrics) { const char *pmu = parse_events_option_args.pmu_filter ?: "all"; + int ret = metricgroup__parse_groups(evsel_list, pmu, metrics, + stat_config.metric_no_group, + stat_config.metric_no_merge, + stat_config.metric_no_threshold, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events); - metricgroup__parse_groups(evsel_list, pmu, metrics, - stat_config.metric_no_group, - stat_config.metric_no_merge, - stat_config.metric_no_threshold, - stat_config.user_requested_cpu_list, - stat_config.system_wide, - &stat_config.metric_events); zfree(&metrics); + if (ret) { + status = ret; + goto out; + } } if (add_default_attributes()) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index ea8c7eca5eee..baf1ab083436 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -147,7 +147,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) return err; } - err = symbol__annotate(&he->ms, evsel, &top->annotation_opts, NULL); + err = symbol__annotate(&he->ms, evsel, NULL); if (err == 0) { top->sym_filter_entry = he; } else { @@ -261,9 +261,9 @@ static void perf_top__show_details(struct perf_top *top) goto out_unlock; printf("Showing %s for %s\n", evsel__name(top->sym_evsel), symbol->name); - printf(" Events Pcnt (>=%d%%)\n", top->annotation_opts.min_pcnt); + printf(" Events Pcnt (>=%d%%)\n", annotate_opts.min_pcnt); - more = symbol__annotate_printf(&he->ms, top->sym_evsel, &top->annotation_opts); + more = symbol__annotate_printf(&he->ms, top->sym_evsel); if (top->evlist->enabled) { if (top->zero) @@ -450,7 +450,7 @@ static void perf_top__print_mapped_keys(struct perf_top *top) fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top->count_filter); - fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", top->annotation_opts.min_pcnt); + fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", annotate_opts.min_pcnt); fprintf(stdout, "\t[s] annotate symbol. \t(%s)\n", name?: "NULL"); fprintf(stdout, "\t[S] stop annotation.\n"); @@ -553,7 +553,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c) prompt_integer(&top->count_filter, "Enter display event count filter"); break; case 'F': - prompt_percent(&top->annotation_opts.min_pcnt, + prompt_percent(&annotate_opts.min_pcnt, "Enter details display event filter (percent)"); break; case 'K': @@ -646,8 +646,7 @@ repeat: } ret = evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, - &top->session->header.env, !top->record_opts.overwrite, - &top->annotation_opts); + &top->session->header.env, !top->record_opts.overwrite); if (ret == K_RELOAD) { top->zero = true; goto repeat; @@ -1027,8 +1026,8 @@ static int perf_top__start_counters(struct perf_top *top) evlist__for_each_entry(evlist, counter) { try_again: - if (evsel__open(counter, top->evlist->core.user_requested_cpus, - top->evlist->core.threads) < 0) { + if (evsel__open(counter, counter->core.cpus, + counter->core.threads) < 0) { /* * Specially handle overwrite fall back. @@ -1044,7 +1043,7 @@ try_again: perf_top_overwrite_fallback(top, counter)) goto try_again; - if (evsel__fallback(counter, errno, msg, sizeof(msg))) { + if (evsel__fallback(counter, &opts->target, errno, msg, sizeof(msg))) { if (verbose > 0) ui__warning("%s\n", msg); goto try_again; @@ -1241,9 +1240,9 @@ static int __cmd_top(struct perf_top *top) pthread_t thread, thread_process; int ret; - if (!top->annotation_opts.objdump_path) { + if (!annotate_opts.objdump_path) { ret = perf_env__lookup_objdump(&top->session->header.env, - &top->annotation_opts.objdump_path); + &annotate_opts.objdump_path); if (ret) return ret; } @@ -1299,6 +1298,7 @@ static int __cmd_top(struct perf_top *top) } } + evlist__uniquify_name(top->evlist); ret = perf_top__start_counters(top); if (ret) return ret; @@ -1536,9 +1536,9 @@ int cmd_top(int argc, const char **argv) "only consider symbols in these comms"), OPT_STRING(0, "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", "only consider these symbols"), - OPT_BOOLEAN(0, "source", &top.annotation_opts.annotate_src, + OPT_BOOLEAN(0, "source", &annotate_opts.annotate_src, "Interleave source code with assembly code (default)"), - OPT_BOOLEAN(0, "asm-raw", &top.annotation_opts.show_asm_raw, + OPT_BOOLEAN(0, "asm-raw", &annotate_opts.show_asm_raw, "Display raw encoding of assembly instructions (default)"), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), @@ -1549,9 +1549,9 @@ int cmd_top(int argc, const char **argv) "addr2line binary to use for line numbers"), OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), - OPT_STRING(0, "prefix", &top.annotation_opts.prefix, "prefix", + OPT_STRING(0, "prefix", &annotate_opts.prefix, "prefix", "Add prefix to source file path names in programs (with --prefix-strip)"), - OPT_STRING(0, "prefix-strip", &top.annotation_opts.prefix_strip, "N", + OPT_STRING(0, "prefix-strip", &annotate_opts.prefix_strip, "N", "Strip first N entries of source file path name in programs (with --prefix)"), OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"), OPT_CALLBACK(0, "percent-limit", &top, "percent", @@ -1609,10 +1609,10 @@ int cmd_top(int argc, const char **argv) if (status < 0) return status; - annotation_options__init(&top.annotation_opts); + annotation_options__init(); - top.annotation_opts.min_pcnt = 5; - top.annotation_opts.context = 4; + annotate_opts.min_pcnt = 5; + annotate_opts.context = 4; top.evlist = evlist__new(); if (top.evlist == NULL) @@ -1642,13 +1642,13 @@ int cmd_top(int argc, const char **argv) usage_with_options(top_usage, options); if (disassembler_style) { - top.annotation_opts.disassembler_style = strdup(disassembler_style); - if (!top.annotation_opts.disassembler_style) + annotate_opts.disassembler_style = strdup(disassembler_style); + if (!annotate_opts.disassembler_style) return -ENOMEM; } if (objdump_path) { - top.annotation_opts.objdump_path = strdup(objdump_path); - if (!top.annotation_opts.objdump_path) + annotate_opts.objdump_path = strdup(objdump_path); + if (!annotate_opts.objdump_path) return -ENOMEM; } if (addr2line_path) { @@ -1661,7 +1661,7 @@ int cmd_top(int argc, const char **argv) if (status) goto out_delete_evlist; - if (annotate_check_args(&top.annotation_opts) < 0) + if (annotate_check_args() < 0) goto out_delete_evlist; if (!top.evlist->core.nr_entries) { @@ -1787,7 +1787,7 @@ int cmd_top(int argc, const char **argv) if (status < 0) goto out_delete_evlist; - annotation_config__init(&top.annotation_opts); + annotation_config__init(); symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); status = symbol__init(NULL); @@ -1840,7 +1840,7 @@ int cmd_top(int argc, const char **argv) out_delete_evlist: evlist__delete(top.evlist); perf_session__delete(top.session); - annotation_options__exit(&top.annotation_opts); + annotation_options__exit(); return status; } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index e541d0e2777a..109b8e64fe69 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2470,9 +2470,8 @@ static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sam static const char *errno_to_name(struct evsel *evsel, int err) { struct perf_env *env = evsel__env(evsel); - const char *arch_name = perf_env__arch(env); - return arch_syscalls__strerrno(arch_name, err); + return perf_env__arch_strerrno(env, err); } static int trace__sys_exit(struct trace *trace, struct evsel *evsel, @@ -4264,12 +4263,11 @@ static size_t thread__dump_stats(struct thread_trace *ttrace, printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct); if (trace->errno_summary && stats->nr_failures) { - const char *arch_name = perf_env__arch(trace->host->env); int e; for (e = 0; e < stats->max_errno; ++e) { if (stats->errnos[e] != 0) - fprintf(fp, "\t\t\t\t%s: %d\n", arch_syscalls__strerrno(arch_name, e + 1), stats->errnos[e]); + fprintf(fp, "\t\t\t\t%s: %d\n", perf_env__arch_strerrno(trace->host->env, e + 1), stats->errnos[e]); } } } diff --git a/tools/perf/perf.c b/tools/perf/perf.c index d3fc8090413c..921bee0a6437 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -39,6 +39,7 @@ #include <linux/zalloc.h> static int use_pager = -1; +static FILE *debug_fp = NULL; struct cmd_struct { const char *cmd; @@ -162,6 +163,19 @@ static void commit_pager_choice(void) } } +static int set_debug_file(const char *path) +{ + debug_fp = fopen(path, "w"); + if (!debug_fp) { + fprintf(stderr, "Open debug file '%s' failed: %s\n", + path, strerror(errno)); + return -1; + } + + debug_set_file(debug_fp); + return 0; +} + struct option options[] = { OPT_ARGUMENT("help", "help"), OPT_ARGUMENT("version", "version"), @@ -174,6 +188,7 @@ struct option options[] = { OPT_ARGUMENT("list-cmds", "list-cmds"), OPT_ARGUMENT("list-opts", "list-opts"), OPT_ARGUMENT("debug", "debug"), + OPT_ARGUMENT("debug-file", "debug-file"), OPT_END() }; @@ -287,6 +302,18 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) (*argv)++; (*argc)--; + } else if (!strcmp(cmd, "--debug-file")) { + if (*argc < 2) { + fprintf(stderr, "No path given for --debug-file.\n"); + usage(perf_usage_string); + } + + if (set_debug_file((*argv)[1])) + usage(perf_usage_string); + + (*argv)++; + (*argc)--; + } else { fprintf(stderr, "Unknown option: %s\n", cmd); usage(perf_usage_string); @@ -547,5 +574,8 @@ int main(int argc, const char **argv) fprintf(stderr, "Failed to run command '%s': %s\n", cmd, str_error_r(errno, sbuf, sizeof(sbuf))); out: + if (debug_fp) + fclose(debug_fp); + return 1; } diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json index 88b23b85e33c..879ff21e0b17 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json @@ -110,7 +110,7 @@ { "PublicDescription": "Flushes due to memory hazards", "EventCode": "0x121", - "EventName": "BPU_FLUSH_MEM_FAULT", + "EventName": "GPC_FLUSH_MEM_FAULT", "BriefDescription": "Flushes due to memory hazards" }, { diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/branch.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/branch.json new file mode 100644 index 000000000000..a632755fc086 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/branch.json @@ -0,0 +1,125 @@ +[ + { + "ArchStdEvent": "BR_IMMED_SPEC" + }, + { + "ArchStdEvent": "BR_RETURN_SPEC" + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC" + }, + { + "ArchStdEvent": "BR_MIS_PRED" + }, + { + "ArchStdEvent": "BR_PRED" + }, + { + "PublicDescription": "Instruction architecturally executed, branch not taken", + "EventCode": "0x8107", + "EventName": "BR_SKIP_RETIRED", + "BriefDescription": "Instruction architecturally executed, branch not taken" + }, + { + "PublicDescription": "Instruction architecturally executed, immediate branch taken", + "EventCode": "0x8108", + "EventName": "BR_IMMED_TAKEN_RETIRED", + "BriefDescription": "Instruction architecturally executed, immediate branch taken" + }, + { + "PublicDescription": "Instruction architecturally executed, indirect branch excluding return retired", + "EventCode": "0x810c", + "EventName": "BR_INDNR_TAKEN_RETIRED", + "BriefDescription": "Instruction architecturally executed, indirect branch excluding return retired" + }, + { + "PublicDescription": "Instruction architecturally executed, predicted immediate branch", + "EventCode": "0x8110", + "EventName": "BR_IMMED_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, predicted immediate branch" + }, + { + "PublicDescription": "Instruction architecturally executed, mispredicted immediate branch", + "EventCode": "0x8111", + "EventName": "BR_IMMED_MIS_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, mispredicted immediate branch" + }, + { + "PublicDescription": "Instruction architecturally executed, predicted indirect branch", + "EventCode": "0x8112", + "EventName": "BR_IND_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, predicted indirect branch" + }, + { + "PublicDescription": "Instruction architecturally executed, mispredicted indirect branch", + "EventCode": "0x8113", + "EventName": "BR_IND_MIS_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, mispredicted indirect branch" + }, + { + "PublicDescription": "Instruction architecturally executed, predicted procedure return", + "EventCode": "0x8114", + "EventName": "BR_RETURN_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, predicted procedure return" + }, + { + "PublicDescription": "Instruction architecturally executed, mispredicted procedure return", + "EventCode": "0x8115", + "EventName": "BR_RETURN_MIS_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, mispredicted procedure return" + }, + { + "PublicDescription": "Instruction architecturally executed, predicted indirect branch excluding return", + "EventCode": "0x8116", + "EventName": "BR_INDNR_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, predicted indirect branch excluding return" + }, + { + "PublicDescription": "Instruction architecturally executed, mispredicted indirect branch excluding return", + "EventCode": "0x8117", + "EventName": "BR_INDNR_MIS_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, mispredicted indirect branch excluding return" + }, + { + "PublicDescription": "Instruction architecturally executed, predicted branch, taken", + "EventCode": "0x8118", + "EventName": "BR_TAKEN_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, predicted branch, taken" + }, + { + "PublicDescription": "Instruction architecturally executed, mispredicted branch, taken", + "EventCode": "0x8119", + "EventName": "BR_TAKEN_MIS_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, mispredicted branch, taken" + }, + { + "PublicDescription": "Instruction architecturally executed, predicted branch, not taken", + "EventCode": "0x811a", + "EventName": "BR_SKIP_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, predicted branch, not taken" + }, + { + "PublicDescription": "Instruction architecturally executed, mispredicted branch, not taken", + "EventCode": "0x811b", + "EventName": "BR_SKIP_MIS_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, mispredicted branch, not taken" + }, + { + "PublicDescription": "Instruction architecturally executed, predicted branch", + "EventCode": "0x811c", + "EventName": "BR_PRED_RETIRED", + "BriefDescription": "Instruction architecturally executed, predicted branch" + }, + { + "PublicDescription": "Instruction architecturally executed, indirect branch", + "EventCode": "0x811d", + "EventName": "BR_IND_RETIRED", + "BriefDescription": "Instruction architecturally executed, indirect branch" + }, + { + "PublicDescription": "Branch Record captured.", + "EventCode": "0x811f", + "EventName": "BRB_FILTRATE", + "BriefDescription": "Branch Record captured." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/bus.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/bus.json new file mode 100644 index 000000000000..2aeb9907831d --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/bus.json @@ -0,0 +1,20 @@ +[ + { + "ArchStdEvent": "CPU_CYCLES" + }, + { + "ArchStdEvent": "BUS_CYCLES" + }, + { + "ArchStdEvent": "BUS_ACCESS_RD" + }, + { + "ArchStdEvent": "BUS_ACCESS_WR" + }, + { + "ArchStdEvent": "BUS_ACCESS" + }, + { + "ArchStdEvent": "CNT_CYCLES" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json new file mode 100644 index 000000000000..c50d8e930b05 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json @@ -0,0 +1,206 @@ +[ + { + "ArchStdEvent": "L1D_CACHE_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_WR" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD" + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_RD" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_RD" + }, + { + "ArchStdEvent": "L2D_CACHE_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR" + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM" + }, + { + "ArchStdEvent": "L2D_CACHE_WB_CLEAN" + }, + { + "ArchStdEvent": "L2D_CACHE_INVAL" + }, + { + "ArchStdEvent": "L1I_CACHE_REFILL" + }, + { + "ArchStdEvent": "L1I_TLB_REFILL" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL" + }, + { + "ArchStdEvent": "L1D_CACHE" + }, + { + "ArchStdEvent": "L1D_TLB_REFILL" + }, + { + "ArchStdEvent": "L1I_CACHE" + }, + { + "ArchStdEvent": "L2D_CACHE" + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL" + }, + { + "ArchStdEvent": "L2D_CACHE_WB" + }, + { + "ArchStdEvent": "L1D_TLB" + }, + { + "ArchStdEvent": "L1I_TLB" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL" + }, + { + "ArchStdEvent": "L2I_TLB_REFILL" + }, + { + "ArchStdEvent": "L2D_TLB" + }, + { + "ArchStdEvent": "L2I_TLB" + }, + { + "ArchStdEvent": "DTLB_WALK" + }, + { + "ArchStdEvent": "ITLB_WALK" + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR" + }, + { + "ArchStdEvent": "L1D_CACHE_LMISS_RD" + }, + { + "ArchStdEvent": "L1I_CACHE_LMISS" + }, + { + "ArchStdEvent": "L2D_CACHE_LMISS_RD" + }, + { + "PublicDescription": "Level 1 data or unified cache demand access", + "EventCode": "0x8140", + "EventName": "L1D_CACHE_RW", + "BriefDescription": "Level 1 data or unified cache demand access" + }, + { + "PublicDescription": "Level 1 data or unified cache preload or prefetch", + "EventCode": "0x8142", + "EventName": "L1D_CACHE_PRFM", + "BriefDescription": "Level 1 data or unified cache preload or prefetch" + }, + { + "PublicDescription": "Level 1 data or unified cache refill, preload or prefetch", + "EventCode": "0x8146", + "EventName": "L1D_CACHE_REFILL_PRFM", + "BriefDescription": "Level 1 data or unified cache refill, preload or prefetch" + }, + { + "ArchStdEvent": "L1D_TLB_RD" + }, + { + "ArchStdEvent": "L1D_TLB_WR" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_RD" + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR" + }, + { + "ArchStdEvent": "L2D_TLB_RD" + }, + { + "ArchStdEvent": "L2D_TLB_WR" + }, + { + "PublicDescription": "L1D TLB miss", + "EventCode": "0xD600", + "EventName": "L1D_TLB_MISS", + "BriefDescription": "L1D TLB miss" + }, + { + "PublicDescription": "Level 1 prefetcher, load prefetch requests generated", + "EventCode": "0xd606", + "EventName": "L1_PREFETCH_LD_GEN", + "BriefDescription": "Level 1 prefetcher, load prefetch requests generated" + }, + { + "PublicDescription": "Level 1 prefetcher, load prefetch fills into the level 1 cache", + "EventCode": "0xd607", + "EventName": "L1_PREFETCH_LD_FILL", + "BriefDescription": "Level 1 prefetcher, load prefetch fills into the level 1 cache" + }, + { + "PublicDescription": "Level 1 prefetcher, load prefetch to level 2 generated", + "EventCode": "0xd608", + "EventName": "L1_PREFETCH_L2_REQ", + "BriefDescription": "Level 1 prefetcher, load prefetch to level 2 generated" + }, + { + "PublicDescription": "L1 prefetcher, distance was reset", + "EventCode": "0xd609", + "EventName": "L1_PREFETCH_DIST_RST", + "BriefDescription": "L1 prefetcher, distance was reset" + }, + { + "PublicDescription": "L1 prefetcher, distance was increased", + "EventCode": "0xd60a", + "EventName": "L1_PREFETCH_DIST_INC", + "BriefDescription": "L1 prefetcher, distance was increased" + }, + { + "PublicDescription": "Level 1 prefetcher, table entry is trained", + "EventCode": "0xd60b", + "EventName": "L1_PREFETCH_ENTRY_TRAINED", + "BriefDescription": "Level 1 prefetcher, table entry is trained" + }, + { + "PublicDescription": "L1 data cache refill - Read or Write", + "EventCode": "0xd60e", + "EventName": "L1D_CACHE_REFILL_RW", + "BriefDescription": "L1 data cache refill - Read or Write" + }, + { + "PublicDescription": "Level 2 cache refill from instruction-side miss, including IMMU refills", + "EventCode": "0xD701", + "EventName": "L2C_INST_REFILL", + "BriefDescription": "Level 2 cache refill from instruction-side miss, including IMMU refills" + }, + { + "PublicDescription": "Level 2 cache refill from data-side miss, including DMMU refills", + "EventCode": "0xD702", + "EventName": "L2C_DATA_REFILL", + "BriefDescription": "Level 2 cache refill from data-side miss, including DMMU refills" + }, + { + "PublicDescription": "Level 2 cache prefetcher, load prefetch requests generated", + "EventCode": "0xD703", + "EventName": "L2_PREFETCH_REQ", + "BriefDescription": "Level 2 cache prefetcher, load prefetch requests generated" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/core-imp-def.json new file mode 100644 index 000000000000..eb5a2208d260 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/core-imp-def.json @@ -0,0 +1,464 @@ +[ + { + "PublicDescription": "Level 2 prefetch requests, refilled to L2 cache", + "EventCode": "0x10A", + "EventName": "L2_PREFETCH_REFILL", + "BriefDescription": "Level 2 prefetch requests, refilled to L2 cache" + }, + { + "PublicDescription": "Level 2 prefetch requests, late", + "EventCode": "0x10B", + "EventName": "L2_PREFETCH_UPGRADE", + "BriefDescription": "Level 2 prefetch requests, late" + }, + { + "PublicDescription": "Predictable branch speculatively executed that hit any level of BTB", + "EventCode": "0x110", + "EventName": "BPU_HIT_BTB", + "BriefDescription": "Predictable branch speculatively executed that hit any level of BTB" + }, + { + "PublicDescription": "Predictable conditional branch speculatively executed that hit any level of BTB", + "EventCode": "0x111", + "EventName": "BPU_CONDITIONAL_BRANCH_HIT_BTB", + "BriefDescription": "Predictable conditional branch speculatively executed that hit any level of BTB" + }, + { + "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor", + "EventCode": "0x112", + "EventName": "BPU_HIT_INDIRECT_PREDICTOR", + "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor" + }, + { + "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor", + "EventCode": "0x113", + "EventName": "BPU_HIT_RSB", + "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor" + }, + { + "PublicDescription": "Predictable unconditional branch speculatively executed that did not hit any level of BTB", + "EventCode": "0x114", + "EventName": "BPU_UNCONDITIONAL_BRANCH_MISS_BTB", + "BriefDescription": "Predictable unconditional branch speculatively executed that did not hit any level of BTB" + }, + { + "PublicDescription": "Predictable branch speculatively executed, unpredicted", + "EventCode": "0x115", + "EventName": "BPU_BRANCH_NO_HIT", + "BriefDescription": "Predictable branch speculatively executed, unpredicted" + }, + { + "PublicDescription": "Predictable branch speculatively executed that hit any level of BTB that mispredict", + "EventCode": "0x116", + "EventName": "BPU_HIT_BTB_AND_MISPREDICT", + "BriefDescription": "Predictable branch speculatively executed that hit any level of BTB that mispredict" + }, + { + "PublicDescription": "Predictable conditional branch speculatively executed that hit any level of BTB that (direction) mispredict", + "EventCode": "0x117", + "EventName": "BPU_CONDITIONAL_BRANCH_HIT_BTB_AND_MISPREDICT", + "BriefDescription": "Predictable conditional branch speculatively executed that hit any level of BTB that (direction) mispredict" + }, + { + "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor that mispredict", + "EventCode": "0x118", + "EventName": "BPU_INDIRECT_BRANCH_HIT_BTB_AND_MISPREDICT", + "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the indirect predictor that mispredict" + }, + { + "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor that mispredict", + "EventCode": "0x119", + "EventName": "BPU_HIT_RSB_AND_MISPREDICT", + "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the return predictor that mispredict" + }, + { + "PublicDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the overflow/underflow return predictor that mispredict", + "EventCode": "0x11a", + "EventName": "BPU_MISS_RSB_AND_MISPREDICT", + "BriefDescription": "Predictable taken branch speculatively executed that hit any level of BTB that access the overflow/underflow return predictor that mispredict" + }, + { + "PublicDescription": "Predictable branch speculatively executed, unpredicted, that mispredict", + "EventCode": "0x11b", + "EventName": "BPU_NO_PREDICTION_MISPREDICT", + "BriefDescription": "Predictable branch speculatively executed, unpredicted, that mispredict" + }, + { + "PublicDescription": "Preditable branch update the BTB region buffer entry", + "EventCode": "0x11c", + "EventName": "BPU_BTB_UPDATE", + "BriefDescription": "Preditable branch update the BTB region buffer entry" + }, + { + "PublicDescription": "Count predict pipe stalls due to speculative return address predictor full", + "EventCode": "0x11d", + "EventName": "BPU_RSB_FULL_STALL", + "BriefDescription": "Count predict pipe stalls due to speculative return address predictor full" + }, + { + "PublicDescription": "Macro-ops speculatively decoded", + "EventCode": "0x11f", + "EventName": "ICF_INST_SPEC_DECODE", + "BriefDescription": "Macro-ops speculatively decoded" + }, + { + "PublicDescription": "Flushes", + "EventCode": "0x120", + "EventName": "GPC_FLUSH", + "BriefDescription": "Flushes" + }, + { + "PublicDescription": "Flushes due to memory hazards", + "EventCode": "0x121", + "EventName": "GPC_FLUSH_MEM_FAULT", + "BriefDescription": "Flushes due to memory hazards" + }, + { + "PublicDescription": "ETM extout bit 0", + "EventCode": "0x141", + "EventName": "MSC_ETM_EXTOUT0", + "BriefDescription": "ETM extout bit 0" + }, + { + "PublicDescription": "ETM extout bit 1", + "EventCode": "0x142", + "EventName": "MSC_ETM_EXTOUT1", + "BriefDescription": "ETM extout bit 1" + }, + { + "PublicDescription": "ETM extout bit 2", + "EventCode": "0x143", + "EventName": "MSC_ETM_EXTOUT2", + "BriefDescription": "ETM extout bit 2" + }, + { + "PublicDescription": "ETM extout bit 3", + "EventCode": "0x144", + "EventName": "MSC_ETM_EXTOUT3", + "BriefDescription": "ETM extout bit 3" + }, + { + "PublicDescription": "Bus request sn", + "EventCode": "0x156", + "EventName": "L2C_SNOOP", + "BriefDescription": "Bus request sn" + }, + { + "PublicDescription": "L2 TXDAT LCRD blocked", + "EventCode": "0x169", + "EventName": "L2C_DAT_CRD_STALL", + "BriefDescription": "L2 TXDAT LCRD blocked" + }, + { + "PublicDescription": "L2 TXRSP LCRD blocked", + "EventCode": "0x16a", + "EventName": "L2C_RSP_CRD_STALL", + "BriefDescription": "L2 TXRSP LCRD blocked" + }, + { + "PublicDescription": "L2 TXREQ LCRD blocked", + "EventCode": "0x16b", + "EventName": "L2C_REQ_CRD_STALL", + "BriefDescription": "L2 TXREQ LCRD blocked" + }, + { + "PublicDescription": "Early mispredict", + "EventCode": "0xD100", + "EventName": "ICF_EARLY_MIS_PRED", + "BriefDescription": "Early mispredict" + }, + { + "PublicDescription": "FEQ full cycles", + "EventCode": "0xD101", + "EventName": "ICF_FEQ_FULL", + "BriefDescription": "FEQ full cycles" + }, + { + "PublicDescription": "Instruction FIFO Full", + "EventCode": "0xD102", + "EventName": "ICF_INST_FIFO_FULL", + "BriefDescription": "Instruction FIFO Full" + }, + { + "PublicDescription": "L1I TLB miss", + "EventCode": "0xD103", + "EventName": "L1I_TLB_MISS", + "BriefDescription": "L1I TLB miss" + }, + { + "PublicDescription": "ICF sent 0 instructions to IDR this cycle", + "EventCode": "0xD104", + "EventName": "ICF_STALL", + "BriefDescription": "ICF sent 0 instructions to IDR this cycle" + }, + { + "PublicDescription": "PC FIFO Full", + "EventCode": "0xD105", + "EventName": "ICF_PC_FIFO_FULL", + "BriefDescription": "PC FIFO Full" + }, + { + "PublicDescription": "Stall due to BOB ID", + "EventCode": "0xD200", + "EventName": "IDR_STALL_BOB_ID", + "BriefDescription": "Stall due to BOB ID" + }, + { + "PublicDescription": "Dispatch stall due to LOB entries", + "EventCode": "0xD201", + "EventName": "IDR_STALL_LOB_ID", + "BriefDescription": "Dispatch stall due to LOB entries" + }, + { + "PublicDescription": "Dispatch stall due to SOB entries", + "EventCode": "0xD202", + "EventName": "IDR_STALL_SOB_ID", + "BriefDescription": "Dispatch stall due to SOB entries" + }, + { + "PublicDescription": "Dispatch stall due to IXU scheduler entries", + "EventCode": "0xD203", + "EventName": "IDR_STALL_IXU_SCHED", + "BriefDescription": "Dispatch stall due to IXU scheduler entries" + }, + { + "PublicDescription": "Dispatch stall due to FSU scheduler entries", + "EventCode": "0xD204", + "EventName": "IDR_STALL_FSU_SCHED", + "BriefDescription": "Dispatch stall due to FSU scheduler entries" + }, + { + "PublicDescription": "Dispatch stall due to ROB entries", + "EventCode": "0xD205", + "EventName": "IDR_STALL_ROB_ID", + "BriefDescription": "Dispatch stall due to ROB entries" + }, + { + "PublicDescription": "Dispatch stall due to flush", + "EventCode": "0xD206", + "EventName": "IDR_STALL_FLUSH", + "BriefDescription": "Dispatch stall due to flush" + }, + { + "PublicDescription": "Dispatch stall due to WFI", + "EventCode": "0xD207", + "EventName": "IDR_STALL_WFI", + "BriefDescription": "Dispatch stall due to WFI" + }, + { + "PublicDescription": "Number of SWOB drains triggered by timeout", + "EventCode": "0xD208", + "EventName": "IDR_STALL_SWOB_TIMEOUT", + "BriefDescription": "Number of SWOB drains triggered by timeout" + }, + { + "PublicDescription": "Number of SWOB drains triggered by system register or special-purpose register read-after-write or specific special-purpose register writes that cause SWOB drain", + "EventCode": "0xD209", + "EventName": "IDR_STALL_SWOB_RAW", + "BriefDescription": "Number of SWOB drains triggered by system register or special-purpose register read-after-write or specific special-purpose register writes that cause SWOB drain" + }, + { + "PublicDescription": "Number of SWOB drains triggered by system register write when SWOB full", + "EventCode": "0xD20A", + "EventName": "IDR_STALL_SWOB_FULL", + "BriefDescription": "Number of SWOB drains triggered by system register write when SWOB full" + }, + { + "PublicDescription": "Dispatch stall due to L1 instruction cache miss", + "EventCode": "0xD20B", + "EventName": "STALL_FRONTEND_CACHE", + "BriefDescription": "Dispatch stall due to L1 instruction cache miss" + }, + { + "PublicDescription": "Dispatch stall due to L1 data cache miss", + "EventCode": "0xD20D", + "EventName": "STALL_BACKEND_CACHE", + "BriefDescription": "Dispatch stall due to L1 data cache miss" + }, + { + "PublicDescription": "Dispatch stall due to lack of any core resource", + "EventCode": "0xD20F", + "EventName": "STALL_BACKEND_RESOURCE", + "BriefDescription": "Dispatch stall due to lack of any core resource" + }, + { + "PublicDescription": "Instructions issued by the scheduler", + "EventCode": "0xD300", + "EventName": "IXU_NUM_UOPS_ISSUED", + "BriefDescription": "Instructions issued by the scheduler" + }, + { + "PublicDescription": "Any uop issued was canceled for any reason", + "EventCode": "0xD301", + "EventName": "IXU_ISSUE_CANCEL", + "BriefDescription": "Any uop issued was canceled for any reason" + }, + { + "PublicDescription": "A load wakeup to the scheduler has been canceled", + "EventCode": "0xD302", + "EventName": "IXU_LOAD_CANCEL", + "BriefDescription": "A load wakeup to the scheduler has been canceled" + }, + { + "PublicDescription": "The scheduler had to cancel one slow Uop due to resource conflict", + "EventCode": "0xD303", + "EventName": "IXU_SLOW_CANCEL", + "BriefDescription": "The scheduler had to cancel one slow Uop due to resource conflict" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXA", + "EventCode": "0xD304", + "EventName": "IXU_IXA_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXA" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXA Par 0", + "EventCode": "0xD305", + "EventName": "IXU_IXA_PAR0_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXA Par 0" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXA Par 1", + "EventCode": "0xD306", + "EventName": "IXU_IXA_PAR1_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXA Par 1" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXB", + "EventCode": "0xD307", + "EventName": "IXU_IXB_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXB" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXB Par 0", + "EventCode": "0xD308", + "EventName": "IXU_IXB_PAR0_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXB Par 0" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXB Par 1", + "EventCode": "0xD309", + "EventName": "IXU_IXB_PAR1_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXB Par 1" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXC", + "EventCode": "0xD30A", + "EventName": "IXU_IXC_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXC" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXC Par 0", + "EventCode": "0xD30B", + "EventName": "IXU_IXC_PAR0_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXC Par 0" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXC Par 1", + "EventCode": "0xD30C", + "EventName": "IXU_IXC_PAR1_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXC Par 1" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXD", + "EventCode": "0xD30D", + "EventName": "IXU_IXD_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXD" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXD Par 0", + "EventCode": "0xD30E", + "EventName": "IXU_IXD_PAR0_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXD Par 0" + }, + { + "PublicDescription": "Uops issued by the scheduler on IXD Par 1", + "EventCode": "0xD30F", + "EventName": "IXU_IXD_PAR1_ISSUED", + "BriefDescription": "Uops issued by the scheduler on IXD Par 1" + }, + { + "PublicDescription": "Uops issued by the FSU scheduler", + "EventCode": "0xD400", + "EventName": "FSU_ISSUED", + "BriefDescription": "Uops issued by the FSU scheduler" + }, + { + "PublicDescription": "Uops issued by the scheduler on FSX", + "EventCode": "0xD401", + "EventName": "FSU_FSX_ISSUED", + "BriefDescription": "Uops issued by the scheduler on FSX" + }, + { + "PublicDescription": "Uops issued by the scheduler on FSY", + "EventCode": "0xD402", + "EventName": "FSU_FSY_ISSUED", + "BriefDescription": "Uops issued by the scheduler on FSY" + }, + { + "PublicDescription": "Uops issued by the scheduler on FSZ", + "EventCode": "0xD403", + "EventName": "FSU_FSZ_ISSUED", + "BriefDescription": "Uops issued by the scheduler on FSZ" + }, + { + "PublicDescription": "Uops canceled (load cancels)", + "EventCode": "0xD404", + "EventName": "FSU_CANCEL", + "BriefDescription": "Uops canceled (load cancels)" + }, + { + "PublicDescription": "Count scheduler stalls due to divide/sqrt", + "EventCode": "0xD405", + "EventName": "FSU_DIV_SQRT_STALL", + "BriefDescription": "Count scheduler stalls due to divide/sqrt" + }, + { + "PublicDescription": "Number of SWOB drains", + "EventCode": "0xD500", + "EventName": "GPC_SWOB_DRAIN", + "BriefDescription": "Number of SWOB drains" + }, + { + "PublicDescription": "GPC detected a Breakpoint instruction match", + "EventCode": "0xD501", + "EventName": "BREAKPOINT_MATCH", + "BriefDescription": "GPC detected a Breakpoint instruction match" + }, + { + "PublicDescription": "Core progress monitor triggered", + "EventCode": "0xd502", + "EventName": "GPC_CPM_TRIGGER", + "BriefDescription": "Core progress monitor triggered" + }, + { + "PublicDescription": "Fill buffer full", + "EventCode": "0xD601", + "EventName": "OFB_FULL", + "BriefDescription": "Fill buffer full" + }, + { + "PublicDescription": "Load satisified from store forwarded data", + "EventCode": "0xD605", + "EventName": "LD_FROM_ST_FWD", + "BriefDescription": "Load satisified from store forwarded data" + }, + { + "PublicDescription": "Store retirement pipe stall", + "EventCode": "0xD60C", + "EventName": "LSU_ST_RETIRE_STALL", + "BriefDescription": "Store retirement pipe stall" + }, + { + "PublicDescription": "LSU detected a Watchpoint data match", + "EventCode": "0xD60D", + "EventName": "WATCHPOINT_MATCH", + "BriefDescription": "LSU detected a Watchpoint data match" + }, + { + "PublicDescription": "Counts cycles that MSC is telling GPC to stall commit due to ETM ISTALL feature", + "EventCode": "0xda00", + "EventName": "MSC_ETM_COMMIT_STALL", + "BriefDescription": "Counts cycles that MSC is telling GPC to stall commit due to ETM ISTALL feature" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/exception.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/exception.json new file mode 100644 index 000000000000..bd59ba7b74e4 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/exception.json @@ -0,0 +1,47 @@ +[ + { + "ArchStdEvent": "EXC_UNDEF" + }, + { + "ArchStdEvent": "EXC_SVC" + }, + { + "ArchStdEvent": "EXC_PABORT" + }, + { + "ArchStdEvent": "EXC_DABORT" + }, + { + "ArchStdEvent": "EXC_IRQ" + }, + { + "ArchStdEvent": "EXC_FIQ" + }, + { + "ArchStdEvent": "EXC_HVC" + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT" + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT" + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER" + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ" + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ" + }, + { + "ArchStdEvent": "EXC_TAKEN" + }, + { + "ArchStdEvent": "EXC_RETURN" + }, + { + "ArchStdEvent": "EXC_SMC" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/instruction.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/instruction.json new file mode 100644 index 000000000000..a6a20f541e33 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/instruction.json @@ -0,0 +1,128 @@ +[ + { + "ArchStdEvent": "SW_INCR" + }, + { + "ArchStdEvent": "ST_RETIRED" + }, + { + "ArchStdEvent": "LD_SPEC" + }, + { + "ArchStdEvent": "ST_SPEC" + }, + { + "ArchStdEvent": "LDST_SPEC" + }, + { + "ArchStdEvent": "DP_SPEC" + }, + { + "ArchStdEvent": "ASE_SPEC" + }, + { + "ArchStdEvent": "VFP_SPEC" + }, + { + "ArchStdEvent": "PC_WRITE_SPEC" + }, + { + "ArchStdEvent": "BR_IMMED_RETIRED" + }, + { + "ArchStdEvent": "BR_RETURN_RETIRED" + }, + { + "ArchStdEvent": "CRYPTO_SPEC" + }, + { + "ArchStdEvent": "ISB_SPEC" + }, + { + "ArchStdEvent": "DSB_SPEC" + }, + { + "ArchStdEvent": "DMB_SPEC" + }, + { + "ArchStdEvent": "RC_LD_SPEC" + }, + { + "ArchStdEvent": "RC_ST_SPEC" + }, + { + "ArchStdEvent": "INST_RETIRED" + }, + { + "ArchStdEvent": "CID_WRITE_RETIRED" + }, + { + "ArchStdEvent": "PC_WRITE_RETIRED" + }, + { + "ArchStdEvent": "INST_SPEC" + }, + { + "ArchStdEvent": "TTBR_WRITE_RETIRED" + }, + { + "ArchStdEvent": "BR_RETIRED" + }, + { + "ArchStdEvent": "BR_MIS_PRED_RETIRED" + }, + { + "ArchStdEvent": "OP_RETIRED" + }, + { + "ArchStdEvent": "OP_SPEC" + }, + { + "PublicDescription": "Operation speculatively executed - ASE Scalar", + "EventCode": "0xd210", + "EventName": "ASE_SCALAR_SPEC", + "BriefDescription": "Operation speculatively executed - ASE Scalar" + }, + { + "PublicDescription": "Operation speculatively executed - ASE Vector", + "EventCode": "0xd211", + "EventName": "ASE_VECTOR_SPEC", + "BriefDescription": "Operation speculatively executed - ASE Vector" + }, + { + "PublicDescription": "Barrier speculatively executed, CSDB", + "EventCode": "0x7f", + "EventName": "CSDB_SPEC", + "BriefDescription": "Barrier speculatively executed, CSDB" + }, + { + "PublicDescription": "Prefetch sent to L2.", + "EventCode": "0xd106", + "EventName": "ICF_PREFETCH_DISPATCH", + "BriefDescription": "Prefetch sent to L2." + }, + { + "PublicDescription": "Prefetch response received but was dropped since we don't support inflight upgrades.", + "EventCode": "0xd107", + "EventName": "ICF_PREFETCH_DROPPED_NO_UPGRADE", + "BriefDescription": "Prefetch response received but was dropped since we don't support inflight upgrades." + }, + { + "PublicDescription": "Prefetch request missed TLB.", + "EventCode": "0xd108", + "EventName": "ICF_PREFETCH_DROPPED_TLB_MISS", + "BriefDescription": "Prefetch request missed TLB." + }, + { + "PublicDescription": "Prefetch request dropped since duplicate was found in TLB.", + "EventCode": "0xd109", + "EventName": "ICF_PREFETCH_DROPPED_DUPLICATE", + "BriefDescription": "Prefetch request dropped since duplicate was found in TLB." + }, + { + "PublicDescription": "Prefetch request dropped since it was found in cache.", + "EventCode": "0xd10a", + "EventName": "ICF_PREFETCH_DROPPED_CACHE_HIT", + "BriefDescription": "Prefetch request dropped since it was found in cache." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/intrinsic.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/intrinsic.json new file mode 100644 index 000000000000..7ecffb989ae0 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/intrinsic.json @@ -0,0 +1,14 @@ +[ + { + "ArchStdEvent": "LDREX_SPEC" + }, + { + "ArchStdEvent": "STREX_PASS_SPEC" + }, + { + "ArchStdEvent": "STREX_FAIL_SPEC" + }, + { + "ArchStdEvent": "STREX_SPEC" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json new file mode 100644 index 000000000000..a211d94aacde --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/memory.json @@ -0,0 +1,41 @@ +[ + { + "ArchStdEvent": "LD_RETIRED" + }, + { + "ArchStdEvent": "MEM_ACCESS_RD" + }, + { + "ArchStdEvent": "MEM_ACCESS_WR" + }, + { + "ArchStdEvent": "LD_ALIGN_LAT" + }, + { + "ArchStdEvent": "ST_ALIGN_LAT" + }, + { + "ArchStdEvent": "MEM_ACCESS" + }, + { + "ArchStdEvent": "MEMORY_ERROR" + }, + { + "ArchStdEvent": "LDST_ALIGN_LAT" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED_RD" + }, + { + "ArchStdEvent": "MEM_ACCESS_CHECKED_WR" + }, + { + "PublicDescription": "Flushes due to memory hazards", + "EventCode": "0x121", + "EventName": "BPU_FLUSH_MEM_FAULT", + "BriefDescription": "Flushes due to memory hazards" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json new file mode 100644 index 000000000000..c5d1d22bd034 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/metrics.json @@ -0,0 +1,442 @@ +[ + { + "MetricName": "branch_miss_pred_rate", + "MetricExpr": "BR_MIS_PRED / BR_PRED", + "BriefDescription": "Branch predictor misprediction rate. May not count branches that are never resolved because they are in the misprediction shadow of an earlier branch", + "MetricGroup": "branch", + "ScaleUnit": "100%" + }, + { + "MetricName": "bus_utilization", + "MetricExpr": "BUS_ACCESS / (BUS_CYCLES * 1)", + "BriefDescription": "Core-to-uncore bus utilization", + "MetricGroup": "Bus", + "ScaleUnit": "100percent of bus cycles" + }, + { + "MetricName": "l1d_cache_miss_ratio", + "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE", + "BriefDescription": "This metric measures the ratio of level 1 data cache accesses missed to the total number of level 1 data cache accesses. This gives an indication of the effectiveness of the level 1 data cache.", + "MetricGroup": "Miss_Ratio;L1D_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "l1i_cache_miss_ratio", + "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE", + "BriefDescription": "This metric measures the ratio of level 1 instruction cache accesses missed to the total number of level 1 instruction cache accesses. This gives an indication of the effectiveness of the level 1 instruction cache.", + "MetricGroup": "Miss_Ratio;L1I_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "Miss_Ratio;l1d_cache_read_miss", + "MetricExpr": "L1D_CACHE_LMISS_RD / L1D_CACHE_RD", + "BriefDescription": "L1D cache read miss rate", + "MetricGroup": "Cache", + "ScaleUnit": "1per cache read access" + }, + { + "MetricName": "l2_cache_miss_ratio", + "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE", + "BriefDescription": "This metric measures the ratio of level 2 cache accesses missed to the total number of level 2 cache accesses. This gives an indication of the effectiveness of the level 2 cache, which is a unified cache that stores both data and instruction. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", + "MetricGroup": "Miss_Ratio;L2_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "l1i_cache_read_miss_rate", + "MetricExpr": "L1I_CACHE_LMISS / L1I_CACHE", + "BriefDescription": "L1I cache read miss rate", + "MetricGroup": "Cache", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "l2d_cache_read_miss_rate", + "MetricExpr": "L2D_CACHE_LMISS_RD / L2D_CACHE_RD", + "BriefDescription": "L2 cache read miss rate", + "MetricGroup": "Cache", + "ScaleUnit": "1per cache read access" + }, + { + "MetricName": "l1d_cache_miss_mpki", + "MetricExpr": "(L1D_CACHE_LMISS_RD * 1e3) / INST_RETIRED", + "BriefDescription": "Misses per thousand instructions (data)", + "MetricGroup": "Cache", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l1i_cache_miss_mpki", + "MetricExpr": "(L1I_CACHE_LMISS * 1e3) / INST_RETIRED", + "BriefDescription": "Misses per thousand instructions (instruction)", + "MetricGroup": "Cache", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "simd_percentage", + "MetricExpr": "ASE_SPEC / INST_SPEC", + "BriefDescription": "This metric measures advanced SIMD operations as a percentage of total operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "100percent of operations" + }, + { + "MetricName": "crypto_percentage", + "MetricExpr": "CRYPTO_SPEC / INST_SPEC", + "BriefDescription": "This metric measures crypto operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "100percent of operations" + }, + { + "MetricName": "gflops", + "MetricExpr": "VFP_SPEC / (duration_time * 1e9)", + "BriefDescription": "Giga-floating point operations per second", + "MetricGroup": "InstructionMix" + }, + { + "MetricName": "integer_dp_percentage", + "MetricExpr": "DP_SPEC / INST_SPEC", + "BriefDescription": "This metric measures scalar integer operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "100percent of operations" + }, + { + "MetricName": "ipc", + "MetricExpr": "INST_RETIRED / CPU_CYCLES", + "BriefDescription": "This metric measures the number of instructions retired per cycle.", + "MetricGroup": "General", + "ScaleUnit": "1per cycle" + }, + { + "MetricName": "load_percentage", + "MetricExpr": "LD_SPEC / INST_SPEC", + "BriefDescription": "This metric measures load operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "100percent of operations" + }, + { + "MetricName": "load_store_spec_rate", + "MetricExpr": "LDST_SPEC / INST_SPEC", + "BriefDescription": "The rate of load or store instructions speculatively executed to overall instructions speclatively executed", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "100percent of operations" + }, + { + "MetricName": "retired_mips", + "MetricExpr": "INST_RETIRED / (duration_time * 1e6)", + "BriefDescription": "Millions of instructions per second", + "MetricGroup": "InstructionMix" + }, + { + "MetricName": "spec_utilization_mips", + "MetricExpr": "INST_SPEC / (duration_time * 1e6)", + "BriefDescription": "Millions of instructions per second", + "MetricGroup": "PEutilization" + }, + { + "MetricName": "pc_write_spec_rate", + "MetricExpr": "PC_WRITE_SPEC / INST_SPEC", + "BriefDescription": "The rate of software change of the PC speculatively executed to overall instructions speclatively executed", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "100percent of operations" + }, + { + "MetricName": "store_percentage", + "MetricExpr": "ST_SPEC / INST_SPEC", + "BriefDescription": "This metric measures store operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "100percent of operations" + }, + { + "MetricName": "scalar_fp_percentage", + "MetricExpr": "VFP_SPEC / INST_SPEC", + "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "100percent of operations" + }, + { + "MetricName": "retired_rate", + "MetricExpr": "OP_RETIRED / OP_SPEC", + "BriefDescription": "Of all the micro-operations issued, what percentage are retired(committed)", + "MetricGroup": "General", + "ScaleUnit": "100%" + }, + { + "MetricName": "wasted", + "MetricExpr": "1 - (OP_RETIRED / (CPU_CYCLES * #slots))", + "BriefDescription": "Of all the micro-operations issued, what proportion are lost", + "MetricGroup": "General", + "ScaleUnit": "100%" + }, + { + "MetricName": "wasted_rate", + "MetricExpr": "1 - OP_RETIRED / OP_SPEC", + "BriefDescription": "Of all the micro-operations issued, what percentage are not retired(committed)", + "MetricGroup": "General", + "ScaleUnit": "100%" + }, + { + "MetricName": "stall_backend_cache_rate", + "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES", + "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and cache miss", + "MetricGroup": "Stall", + "ScaleUnit": "100percent of cycles" + }, + { + "MetricName": "stall_backend_resource_rate", + "MetricExpr": "STALL_BACKEND_RESOURCE / CPU_CYCLES", + "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and resource full", + "MetricGroup": "Stall", + "ScaleUnit": "100percent of cycles" + }, + { + "MetricName": "stall_backend_tlb_rate", + "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES", + "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and TLB miss", + "MetricGroup": "Stall", + "ScaleUnit": "100percent of cycles" + }, + { + "MetricName": "stall_frontend_cache_rate", + "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES", + "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and cache miss", + "MetricGroup": "Stall", + "ScaleUnit": "100percent of cycles" + }, + { + "MetricName": "stall_frontend_tlb_rate", + "MetricExpr": "STALL_FRONTEND_TLB / CPU_CYCLES", + "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and TLB miss", + "MetricGroup": "Stall", + "ScaleUnit": "100percent of cycles" + }, + { + "MetricName": "dtlb_walk_ratio", + "MetricExpr": "DTLB_WALK / L1D_TLB", + "BriefDescription": "This metric measures the ratio of data TLB Walks to the total number of data TLB accesses. This gives an indication of the effectiveness of the data TLB accesses.", + "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "MetricName": "itlb_walk_ratio", + "MetricExpr": "ITLB_WALK / L1I_TLB", + "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of instruction TLB accesses. This gives an indication of the effectiveness of the instruction TLB accesses.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "ArchStdEvent": "backend_bound" + }, + { + "ArchStdEvent": "frontend_bound", + "MetricExpr": "100 - (retired_fraction + slots_lost_misspeculation_fraction + backend_bound)" + }, + { + "MetricName": "slots_lost_misspeculation_fraction", + "MetricExpr": "(OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots)", + "BriefDescription": "Fraction of slots lost due to misspeculation", + "DefaultMetricgroupName": "TopdownL1", + "MetricGroup": "Default;TopdownL1", + "ScaleUnit": "100percent of slots" + }, + { + "MetricName": "retired_fraction", + "MetricExpr": "OP_RETIRED / (CPU_CYCLES * #slots)", + "BriefDescription": "Fraction of slots retiring, useful work", + "DefaultMetricgroupName": "TopdownL1", + "MetricGroup": "Default;TopdownL1", + "ScaleUnit": "100percent of slots" + }, + { + "MetricName": "backend_core", + "MetricExpr": "(backend_bound / 100) - backend_memory", + "BriefDescription": "Fraction of slots the CPU was stalled due to backend non-memory subsystem issues", + "MetricGroup": "TopdownL2", + "ScaleUnit": "100%" + }, + { + "MetricName": "backend_memory", + "MetricExpr": "(STALL_BACKEND_TLB + STALL_BACKEND_CACHE) / CPU_CYCLES", + "BriefDescription": "Fraction of slots the CPU was stalled due to backend memory subsystem issues (cache/tlb miss)", + "MetricGroup": "TopdownL2", + "ScaleUnit": "100%" + }, + { + "MetricName": "branch_mispredict", + "MetricExpr": "(BR_MIS_PRED_RETIRED / GPC_FLUSH) * slots_lost_misspeculation_fraction", + "BriefDescription": "Fraction of slots lost due to branch misprediciton", + "MetricGroup": "TopdownL2", + "ScaleUnit": "1percent of slots" + }, + { + "MetricName": "frontend_bandwidth", + "MetricExpr": "frontend_bound - frontend_latency", + "BriefDescription": "Fraction of slots the CPU did not dispatch at full bandwidth - able to dispatch partial slots only (1, 2, or 3 uops)", + "MetricGroup": "TopdownL2", + "ScaleUnit": "1percent of slots" + }, + { + "MetricName": "frontend_latency", + "MetricExpr": "(STALL_FRONTEND - ((STALL_SLOT_FRONTEND - ((frontend_bound / 100) * CPU_CYCLES * #slots)) / #slots)) / CPU_CYCLES", + "BriefDescription": "Fraction of slots the CPU was stalled due to frontend latency issues (cache/tlb miss); nothing to dispatch", + "MetricGroup": "TopdownL2", + "ScaleUnit": "100percent of slots" + }, + { + "MetricName": "other_miss_pred", + "MetricExpr": "slots_lost_misspeculation_fraction - branch_mispredict", + "BriefDescription": "Fraction of slots lost due to other/non-branch misprediction misspeculation", + "MetricGroup": "TopdownL2", + "ScaleUnit": "1percent of slots" + }, + { + "MetricName": "pipe_utilization", + "MetricExpr": "100 * ((IXU_NUM_UOPS_ISSUED + FSU_ISSUED) / (CPU_CYCLES * 6))", + "BriefDescription": "Fraction of execute slots utilized", + "MetricGroup": "TopdownL2", + "ScaleUnit": "1percent of slots" + }, + { + "MetricName": "d_cache_l2_miss_rate", + "MetricExpr": "STALL_BACKEND_MEM / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled due to data L2 cache miss", + "MetricGroup": "TopdownL3", + "ScaleUnit": "100percent of cycles" + }, + { + "MetricName": "d_cache_miss_rate", + "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled due to data cache miss", + "MetricGroup": "TopdownL3", + "ScaleUnit": "100percent of cycles" + }, + { + "MetricName": "d_tlb_miss_rate", + "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled due to data TLB miss", + "MetricGroup": "TopdownL3", + "ScaleUnit": "100percent of cycles" + }, + { + "MetricName": "fsu_pipe_utilization", + "MetricExpr": "FSU_ISSUED / (CPU_CYCLES * 2)", + "BriefDescription": "Fraction of FSU execute slots utilized", + "MetricGroup": "TopdownL3", + "ScaleUnit": "100percent of slots" + }, + { + "MetricName": "i_cache_miss_rate", + "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction cache miss", + "MetricGroup": "TopdownL3", + "ScaleUnit": "100percent of slots" + }, + { + "MetricName": "i_tlb_miss_rate", + "MetricExpr": "STALL_FRONTEND_TLB / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction TLB miss", + "MetricGroup": "TopdownL3", + "ScaleUnit": "100percent of slots" + }, + { + "MetricName": "ixu_pipe_utilization", + "MetricExpr": "IXU_NUM_UOPS_ISSUED / (CPU_CYCLES * #slots)", + "BriefDescription": "Fraction of IXU execute slots utilized", + "MetricGroup": "TopdownL3", + "ScaleUnit": "100percent of slots" + }, + { + "MetricName": "stall_recovery_rate", + "MetricExpr": "IDR_STALL_FLUSH / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled due to flush recovery", + "MetricGroup": "TopdownL3", + "ScaleUnit": "100percent of slots" + }, + { + "MetricName": "stall_fsu_sched_rate", + "MetricExpr": "IDR_STALL_FSU_SCHED / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled and FSU was full", + "MetricGroup": "TopdownL4", + "ScaleUnit": "100percent of cycles" + }, + { + "MetricName": "stall_ixu_sched_rate", + "MetricExpr": "IDR_STALL_IXU_SCHED / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled and IXU was full", + "MetricGroup": "TopdownL4", + "ScaleUnit": "100percent of cycles" + }, + { + "MetricName": "stall_lob_id_rate", + "MetricExpr": "IDR_STALL_LOB_ID / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled and LOB was full", + "MetricGroup": "TopdownL4", + "ScaleUnit": "100percent of cycles" + }, + { + "MetricName": "stall_rob_id_rate", + "MetricExpr": "IDR_STALL_ROB_ID / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled and ROB was full", + "MetricGroup": "TopdownL4", + "ScaleUnit": "100percent of cycles" + }, + { + "MetricName": "stall_sob_id_rate", + "MetricExpr": "IDR_STALL_SOB_ID / CPU_CYCLES", + "BriefDescription": "Fraction of cycles the CPU was stalled and SOB was full", + "MetricGroup": "TopdownL4", + "ScaleUnit": "100percent of cycles" + }, + { + "MetricName": "l1d_cache_access_demand", + "MetricExpr": "L1D_CACHE_RW / L1D_CACHE", + "BriefDescription": "L1D cache access - demand", + "MetricGroup": "Cache", + "ScaleUnit": "100percent of cache acceses" + }, + { + "MetricName": "l1d_cache_access_prefetces", + "MetricExpr": "L1D_CACHE_PRFM / L1D_CACHE", + "BriefDescription": "L1D cache access - prefetch", + "MetricGroup": "Cache", + "ScaleUnit": "100percent of cache acceses" + }, + { + "MetricName": "l1d_cache_demand_misses", + "MetricExpr": "L1D_CACHE_REFILL_RW / L1D_CACHE", + "BriefDescription": "L1D cache demand misses", + "MetricGroup": "Cache", + "ScaleUnit": "100percent of cache acceses" + }, + { + "MetricName": "l1d_cache_demand_misses_read", + "MetricExpr": "L1D_CACHE_REFILL_RD / L1D_CACHE", + "BriefDescription": "L1D cache demand misses - read", + "MetricGroup": "Cache", + "ScaleUnit": "100percent of cache acceses" + }, + { + "MetricName": "l1d_cache_demand_misses_write", + "MetricExpr": "L1D_CACHE_REFILL_WR / L1D_CACHE", + "BriefDescription": "L1D cache demand misses - write", + "MetricGroup": "Cache", + "ScaleUnit": "100percent of cache acceses" + }, + { + "MetricName": "l1d_cache_prefetch_misses", + "MetricExpr": "L1D_CACHE_REFILL_PRFM / L1D_CACHE", + "BriefDescription": "L1D cache prefetch misses", + "MetricGroup": "Cache", + "ScaleUnit": "100percent of cache acceses" + }, + { + "MetricName": "ase_scalar_mix", + "MetricExpr": "ASE_SCALAR_SPEC / OP_SPEC", + "BriefDescription": "Proportion of advanced SIMD data processing operations (excluding DP_SPEC/LD_SPEC) scalar operations", + "MetricGroup": "Instructions", + "ScaleUnit": "100percent of cache acceses" + }, + { + "MetricName": "ase_vector_mix", + "MetricExpr": "ASE_VECTOR_SPEC / OP_SPEC", + "BriefDescription": "Proportion of advanced SIMD data processing operations (excluding DP_SPEC/LD_SPEC) vector operations", + "MetricGroup": "Instructions", + "ScaleUnit": "100percent of cache acceses" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/mmu.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/mmu.json new file mode 100644 index 000000000000..66d83b680651 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/mmu.json @@ -0,0 +1,170 @@ +[ + { + "PublicDescription": "Level 2 data translation buffer allocation", + "EventCode": "0xD800", + "EventName": "MMU_D_OTB_ALLOC", + "BriefDescription": "Level 2 data translation buffer allocation" + }, + { + "PublicDescription": "Data TLB translation cache hit on S1L2 walk cache entry", + "EventCode": "0xd801", + "EventName": "MMU_D_TRANS_CACHE_HIT_S1L2_WALK", + "BriefDescription": "Data TLB translation cache hit on S1L2 walk cache entry" + }, + { + "PublicDescription": "Data TLB translation cache hit on S1L1 walk cache entry", + "EventCode": "0xd802", + "EventName": "MMU_D_TRANS_CACHE_HIT_S1L1_WALK", + "BriefDescription": "Data TLB translation cache hit on S1L1 walk cache entry" + }, + { + "PublicDescription": "Data TLB translation cache hit on S1L0 walk cache entry", + "EventCode": "0xd803", + "EventName": "MMU_D_TRANS_CACHE_HIT_S1L0_WALK", + "BriefDescription": "Data TLB translation cache hit on S1L0 walk cache entry" + }, + { + "PublicDescription": "Data TLB translation cache hit on S2L2 walk cache entry", + "EventCode": "0xd804", + "EventName": "MMU_D_TRANS_CACHE_HIT_S2L2_WALK", + "BriefDescription": "Data TLB translation cache hit on S2L2 walk cache entry" + }, + { + "PublicDescrition": "Data TLB translation cache hit on S2L1 walk cache entry", + "EventCode": "0xd805", + "EventName": "MMU_D_TRANS_CACHE_HIT_S2L1_WALK", + "BriefDescription": "Data TLB translation cache hit on S2L1 walk cache entry" + }, + { + "PublicDescrition": "Data TLB translation cache hit on S2L0 walk cache entry", + "EventCode": "0xd806", + "EventName": "MMU_D_TRANS_CACHE_HIT_S2L0_WALK", + "BriefDescription": "Data TLB translation cache hit on S2L0 walk cache entry" + }, + { + "PublicDescrition": "Data-side S1 page walk cache lookup", + "EventCode": "0xd807", + "EventName": "MMU_D_S1_WALK_CACHE_LOOKUP", + "BriefDescription": "Data-side S1 page walk cache lookup" + }, + { + "PublicDescrition": "Data-side S1 page walk cache refill", + "EventCode": "0xd808", + "EventName": "MMU_D_S1_WALK_CACHE_REFILL", + "BriefDescription": "Data-side S1 page walk cache refill" + }, + { + "PublicDescrition": "Data-side S2 page walk cache lookup", + "EventCode": "0xd809", + "EventName": "MMU_D_S2_WALK_CACHE_LOOKUP", + "BriefDescription": "Data-side S2 page walk cache lookup" + }, + { + "PublicDescrition": "Data-side S2 page walk cache refill", + "EventCode": "0xd80a", + "EventName": "MMU_D_S2_WALK_CACHE_REFILL", + "BriefDescription": "Data-side S2 page walk cache refill" + }, + { + "PublicDescription": "Data-side S1 table walk fault", + "EventCode": "0xD80B", + "EventName": "MMU_D_S1_WALK_FAULT", + "BriefDescription": "Data-side S1 table walk fault" + }, + { + "PublicDescription": "Data-side S2 table walk fault", + "EventCode": "0xD80C", + "EventName": "MMU_D_S2_WALK_FAULT", + "BriefDescription": "Data-side S2 table walk fault" + }, + { + "PublicDescription": "Data-side table walk steps or descriptor fetches", + "EventCode": "0xD80D", + "EventName": "MMU_D_WALK_STEPS", + "BriefDescription": "Data-side table walk steps or descriptor fetches" + }, + { + "PublicDescription": "Level 2 instruction translation buffer allocation", + "EventCode": "0xD900", + "EventName": "MMU_I_OTB_ALLOC", + "BriefDescription": "Level 2 instruction translation buffer allocation" + }, + { + "PublicDescrition": "Instruction TLB translation cache hit on S1L2 walk cache entry", + "EventCode": "0xd901", + "EventName": "MMU_I_TRANS_CACHE_HIT_S1L2_WALK", + "BriefDescription": "Instruction TLB translation cache hit on S1L2 walk cache entry" + }, + { + "PublicDescrition": "Instruction TLB translation cache hit on S1L1 walk cache entry", + "EventCode": "0xd902", + "EventName": "MMU_I_TRANS_CACHE_HIT_S1L1_WALK", + "BriefDescription": "Instruction TLB translation cache hit on S1L1 walk cache entry" + }, + { + "PublicDescrition": "Instruction TLB translation cache hit on S1L0 walk cache entry", + "EventCode": "0xd903", + "EventName": "MMU_I_TRANS_CACHE_HIT_S1L0_WALK", + "BriefDescription": "Instruction TLB translation cache hit on S1L0 walk cache entry" + }, + { + "PublicDescrition": "Instruction TLB translation cache hit on S2L2 walk cache entry", + "EventCode": "0xd904", + "EventName": "MMU_I_TRANS_CACHE_HIT_S2L2_WALK", + "BriefDescription": "Instruction TLB translation cache hit on S2L2 walk cache entry" + }, + { + "PublicDescrition": "Instruction TLB translation cache hit on S2L1 walk cache entry", + "EventCode": "0xd905", + "EventName": "MMU_I_TRANS_CACHE_HIT_S2L1_WALK", + "BriefDescription": "Instruction TLB translation cache hit on S2L1 walk cache entry" + }, + { + "PublicDescrition": "Instruction TLB translation cache hit on S2L0 walk cache entry", + "EventCode": "0xd906", + "EventName": "MMU_I_TRANS_CACHE_HIT_S2L0_WALK", + "BriefDescription": "Instruction TLB translation cache hit on S2L0 walk cache entry" + }, + { + "PublicDescrition": "Instruction-side S1 page walk cache lookup", + "EventCode": "0xd907", + "EventName": "MMU_I_S1_WALK_CACHE_LOOKUP", + "BriefDescription": "Instruction-side S1 page walk cache lookup" + }, + { + "PublicDescrition": "Instruction-side S1 page walk cache refill", + "EventCode": "0xd908", + "EventName": "MMU_I_S1_WALK_CACHE_REFILL", + "BriefDescription": "Instruction-side S1 page walk cache refill" + }, + { + "PublicDescrition": "Instruction-side S2 page walk cache lookup", + "EventCode": "0xd909", + "EventName": "MMU_I_S2_WALK_CACHE_LOOKUP", + "BriefDescription": "Instruction-side S2 page walk cache lookup" + }, + { + "PublicDescrition": "Instruction-side S2 page walk cache refill", + "EventCode": "0xd90a", + "EventName": "MMU_I_S2_WALK_CACHE_REFILL", + "BriefDescription": "Instruction-side S2 page walk cache refill" + }, + { + "PublicDescription": "Instruction-side S1 table walk fault", + "EventCode": "0xD90B", + "EventName": "MMU_I_S1_WALK_FAULT", + "BriefDescription": "Instruction-side S1 table walk fault" + }, + { + "PublicDescription": "Instruction-side S2 table walk fault", + "EventCode": "0xD90C", + "EventName": "MMU_I_S2_WALK_FAULT", + "BriefDescription": "Instruction-side S2 table walk fault" + }, + { + "PublicDescription": "Instruction-side table walk steps or descriptor fetches", + "EventCode": "0xD90D", + "EventName": "MMU_I_WALK_STEPS", + "BriefDescription": "Instruction-side table walk steps or descriptor fetches" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/pipeline.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/pipeline.json new file mode 100644 index 000000000000..2fb2d1f183fc --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/pipeline.json @@ -0,0 +1,41 @@ +[ + { + "ArchStdEvent": "STALL_FRONTEND", + "Errata": "Errata AC03_CPU_29", + "BriefDescription": "Impacted by errata, use metrics instead -" + }, + { + "ArchStdEvent": "STALL_BACKEND" + }, + { + "ArchStdEvent": "STALL", + "Errata": "Errata AC03_CPU_29", + "BriefDescription": "Impacted by errata, use metrics instead -" + }, + { + "ArchStdEvent": "STALL_SLOT_BACKEND" + }, + { + "ArchStdEvent": "STALL_SLOT_FRONTEND", + "Errata": "Errata AC03_CPU_29", + "BriefDescription": "Impacted by errata, use metrics instead -" + }, + { + "ArchStdEvent": "STALL_SLOT" + }, + { + "ArchStdEvent": "STALL_BACKEND_MEM" + }, + { + "PublicDescription": "Frontend stall cycles, TLB", + "EventCode": "0x815c", + "EventName": "STALL_FRONTEND_TLB", + "BriefDescription": "Frontend stall cycles, TLB" + }, + { + "PublicDescription": "Backend stall cycles, TLB", + "EventCode": "0x8167", + "EventName": "STALL_BACKEND_TLB", + "BriefDescription": "Backend stall cycles, TLB" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/spe.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/spe.json new file mode 100644 index 000000000000..20f2165c85fe --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/spe.json @@ -0,0 +1,14 @@ +[ + { + "ArchStdEvent": "SAMPLE_POP" + }, + { + "ArchStdEvent": "SAMPLE_FEED" + }, + { + "ArchStdEvent": "SAMPLE_FILTRATE" + }, + { + "ArchStdEvent": "SAMPLE_COLLISION" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index 5b58db5032c1..f4d1ca4d1493 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -42,3 +42,4 @@ 0x00000000480fd010,v1,hisilicon/hip08,core 0x00000000500f0000,v1,ampere/emag,core 0x00000000c00fac30,v1,ampere/ampereone,core +0x00000000c00fac40,v1,ampere/ampereonex,core diff --git a/tools/perf/pmu-events/arch/powerpc/power10/datasource.json b/tools/perf/pmu-events/arch/powerpc/power10/datasource.json index 6b0356f2d301..0eeaaf1a95b8 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/datasource.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/datasource.json @@ -100,6 +100,11 @@ "BriefDescription": "The processor's instruction cache was reloaded from a source beyond the local core's L2 due to a demand miss." }, { + "EventCode": "0x0003C0000000C040", + "EventName": "PM_DATA_FROM_L2MISS_DSRC", + "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss." + }, + { "EventCode": "0x000380000010C040", "EventName": "PM_INST_FROM_L2MISS_ALL", "BriefDescription": "The processor's instruction cache was reloaded from a source beyond the local core's L2 due to a demand miss or prefetch reload." @@ -161,10 +166,15 @@ }, { "EventCode": "0x000780000000C040", - "EventName": "PM_INST_FROM_L3MISS", + "EventName": "PM_INST_FROM_L3MISS_DSRC", "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss." }, { + "EventCode": "0x0007C0000000C040", + "EventName": "PM_DATA_FROM_L3MISS_DSRC", + "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss." + }, + { "EventCode": "0x000780000010C040", "EventName": "PM_INST_FROM_L3MISS_ALL", "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss or prefetch reload." @@ -981,7 +991,7 @@ }, { "EventCode": "0x0003C0000000C142", - "EventName": "PM_MRK_DATA_FROM_L2MISS", + "EventName": "PM_MRK_DATA_FROM_L2MISS_DSRC", "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss for a marked instruction." }, { @@ -1046,12 +1056,12 @@ }, { "EventCode": "0x000780000000C142", - "EventName": "PM_MRK_INST_FROM_L3MISS", + "EventName": "PM_MRK_INST_FROM_L3MISS_DSRC", "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction." }, { "EventCode": "0x0007C0000000C142", - "EventName": "PM_MRK_DATA_FROM_L3MISS", + "EventName": "PM_MRK_DATA_FROM_L3MISS_DSRC", "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction." }, { diff --git a/tools/perf/pmu-events/arch/riscv/mapfile.csv b/tools/perf/pmu-events/arch/riscv/mapfile.csv index c61b3d6ef616..cfc449b19810 100644 --- a/tools/perf/pmu-events/arch/riscv/mapfile.csv +++ b/tools/perf/pmu-events/arch/riscv/mapfile.csv @@ -15,3 +15,5 @@ # #MVENDORID-MARCHID-MIMPID,Version,Filename,EventType 0x489-0x8000000000000007-0x[[:xdigit:]]+,v1,sifive/u74,core +0x5b7-0x0-0x0,v1,thead/c900-legacy,core +0x67e-0x80000000db0000[89]0-0x[[:xdigit:]]+,v1,starfive/dubhe-80,core diff --git a/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/common.json b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/common.json new file mode 100644 index 000000000000..fbffcacb2ace --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/common.json @@ -0,0 +1,172 @@ +[ + { + "EventName": "ACCESS_MMU_STLB", + "EventCode": "0x1", + "BriefDescription": "access MMU STLB" + }, + { + "EventName": "MISS_MMU_STLB", + "EventCode": "0x2", + "BriefDescription": "miss MMU STLB" + }, + { + "EventName": "ACCESS_MMU_PTE_C", + "EventCode": "0x3", + "BriefDescription": "access MMU PTE-Cache" + }, + { + "EventName": "MISS_MMU_PTE_C", + "EventCode": "0x4", + "BriefDescription": "miss MMU PTE-Cache" + }, + { + "EventName": "ROB_FLUSH", + "EventCode": "0x5", + "BriefDescription": "ROB flush (all kinds of exceptions)" + }, + { + "EventName": "BTB_PREDICTION_MISS", + "EventCode": "0x6", + "BriefDescription": "BTB prediction miss" + }, + { + "EventName": "ITLB_MISS", + "EventCode": "0x7", + "BriefDescription": "ITLB miss" + }, + { + "EventName": "SYNC_DEL_FETCH_G", + "EventCode": "0x8", + "BriefDescription": "SYNC delivery a fetch-group" + }, + { + "EventName": "ICACHE_MISS", + "EventCode": "0x9", + "BriefDescription": "ICache miss" + }, + { + "EventName": "BPU_BR_RETIRE", + "EventCode": "0xA", + "BriefDescription": "condition branch instruction retire" + }, + { + "EventName": "BPU_BR_MISS", + "EventCode": "0xB", + "BriefDescription": "condition branch instruction miss" + }, + { + "EventName": "RET_INS_RETIRE", + "EventCode": "0xC", + "BriefDescription": "return instruction retire" + }, + { + "EventName": "RET_INS_MISS", + "EventCode": "0xD", + "BriefDescription": "return instruction miss" + }, + { + "EventName": "INDIRECT_JR_MISS", + "EventCode": "0xE", + "BriefDescription": "indirect JR instruction miss (inlcude without target)" + }, + { + "EventName": "IBUF_VAL_ID_NORDY", + "EventCode": "0xF", + "BriefDescription": "IBUF valid while ID not ready" + }, + { + "EventName": "IBUF_NOVAL_ID_RDY", + "EventCode": "0x10", + "BriefDescription": "IBUF not valid while ID ready" + }, + { + "EventName": "REN_INT_PHY_REG_NORDY", + "EventCode": "0x11", + "BriefDescription": "REN integer physical register file is not ready" + }, + { + "EventName": "REN_FP_PHY_REG_NORDY", + "EventCode": "0x12", + "BriefDescription": "REN floating point physical register file is not ready" + }, + { + "EventName": "REN_CP_NORDY", + "EventCode": "0x13", + "BriefDescription": "REN checkpoint is not ready" + }, + { + "EventName": "DEC_VAL_ROB_NORDY", + "EventCode": "0x14", + "BriefDescription": "DEC is valid and ROB is not ready" + }, + { + "EventName": "OOD_FLUSH_LS_DEP", + "EventCode": "0x15", + "BriefDescription": "out of order flush due to load/store dependency" + }, + { + "EventName": "BRU_RET_IJR_INS", + "EventCode": "0x16", + "BriefDescription": "BRU retire an IJR instruction" + }, + { + "EventName": "ACCESS_DTLB", + "EventCode": "0x17", + "BriefDescription": "access DTLB" + }, + { + "EventName": "MISS_DTLB", + "EventCode": "0x18", + "BriefDescription": "miss DTLB" + }, + { + "EventName": "LOAD_INS_DCACHE", + "EventCode": "0x19", + "BriefDescription": "load instruction access DCache" + }, + { + "EventName": "LOAD_INS_MISS_DCACHE", + "EventCode": "0x1A", + "BriefDescription": "load instruction miss DCache" + }, + { + "EventName": "STORE_INS_DCACHE", + "EventCode": "0x1B", + "BriefDescription": "store/amo instruction access DCache" + }, + { + "EventName": "STORE_INS_MISS_DCACHE", + "EventCode": "0x1C", + "BriefDescription": "store/amo instruction miss DCache" + }, + { + "EventName": "LOAD_SCACHE", + "EventCode": "0x1D", + "BriefDescription": "load access SCache" + }, + { + "EventName": "STORE_SCACHE", + "EventCode": "0x1E", + "BriefDescription": "store access SCache" + }, + { + "EventName": "LOAD_MISS_SCACHE", + "EventCode": "0x1F", + "BriefDescription": "load miss SCache" + }, + { + "EventName": "STORE_MISS_SCACHE", + "EventCode": "0x20", + "BriefDescription": "store miss SCache" + }, + { + "EventName": "L2C_PF_REQ", + "EventCode": "0x21", + "BriefDescription": "L2C data-prefetcher request" + }, + { + "EventName": "L2C_PF_HIT", + "EventCode": "0x22", + "BriefDescription": "L2C data-prefetcher hit" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json new file mode 100644 index 000000000000..9b4a032186a7 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json @@ -0,0 +1,68 @@ +[ + { + "ArchStdEvent": "FW_MISALIGNED_LOAD" + }, + { + "ArchStdEvent": "FW_MISALIGNED_STORE" + }, + { + "ArchStdEvent": "FW_ACCESS_LOAD" + }, + { + "ArchStdEvent": "FW_ACCESS_STORE" + }, + { + "ArchStdEvent": "FW_ILLEGAL_INSN" + }, + { + "ArchStdEvent": "FW_SET_TIMER" + }, + { + "ArchStdEvent": "FW_IPI_SENT" + }, + { + "ArchStdEvent": "FW_IPI_RECEIVED" + }, + { + "ArchStdEvent": "FW_FENCE_I_SENT" + }, + { + "ArchStdEvent": "FW_FENCE_I_RECEIVED" + }, + { + "ArchStdEvent": "FW_SFENCE_VMA_SENT" + }, + { + "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED" + }, + { + "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED" + }, + { + "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED" + }, + { + "ArchStdEvent": "FW_HFENCE_GVMA_SENT" + }, + { + "ArchStdEvent": "FW_HFENCE_GVMA_RECEIVED" + }, + { + "ArchStdEvent": "FW_HFENCE_GVMA_VMID_SENT" + }, + { + "ArchStdEvent": "FW_HFENCE_GVMA_VMID_RECEIVED" + }, + { + "ArchStdEvent": "FW_HFENCE_VVMA_SENT" + }, + { + "ArchStdEvent": "FW_HFENCE_VVMA_RECEIVED" + }, + { + "ArchStdEvent": "FW_HFENCE_VVMA_ASID_SENT" + }, + { + "ArchStdEvent": "FW_HFENCE_VVMA_ASID_RECEIVED" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/cache.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/cache.json new file mode 100644 index 000000000000..2b142348d635 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/cache.json @@ -0,0 +1,67 @@ +[ + { + "EventName": "L1_ICACHE_ACCESS", + "EventCode": "0x00000001", + "BriefDescription": "L1 instruction cache access" + }, + { + "EventName": "L1_ICACHE_MISS", + "EventCode": "0x00000002", + "BriefDescription": "L1 instruction cache miss" + }, + { + "EventName": "ITLB_MISS", + "EventCode": "0x00000003", + "BriefDescription": "I-UTLB miss" + }, + { + "EventName": "DTLB_MISS", + "EventCode": "0x00000004", + "BriefDescription": "D-UTLB miss" + }, + { + "EventName": "JTLB_MISS", + "EventCode": "0x00000005", + "BriefDescription": "JTLB miss" + }, + { + "EventName": "L1_DCACHE_READ_ACCESS", + "EventCode": "0x0000000c", + "BriefDescription": "L1 data cache read access" + }, + { + "EventName": "L1_DCACHE_READ_MISS", + "EventCode": "0x0000000d", + "BriefDescription": "L1 data cache read miss" + }, + { + "EventName": "L1_DCACHE_WRITE_ACCESS", + "EventCode": "0x0000000e", + "BriefDescription": "L1 data cache write access" + }, + { + "EventName": "L1_DCACHE_WRITE_MISS", + "EventCode": "0x0000000f", + "BriefDescription": "L1 data cache write miss" + }, + { + "EventName": "LL_CACHE_READ_ACCESS", + "EventCode": "0x00000010", + "BriefDescription": "LL Cache read access" + }, + { + "EventName": "LL_CACHE_READ_MISS", + "EventCode": "0x00000011", + "BriefDescription": "LL Cache read miss" + }, + { + "EventName": "LL_CACHE_WRITE_ACCESS", + "EventCode": "0x00000012", + "BriefDescription": "LL Cache write access" + }, + { + "EventName": "LL_CACHE_WRITE_MISS", + "EventCode": "0x00000013", + "BriefDescription": "LL Cache write miss" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json new file mode 100644 index 000000000000..9b4a032186a7 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json @@ -0,0 +1,68 @@ +[ + { + "ArchStdEvent": "FW_MISALIGNED_LOAD" + }, + { + "ArchStdEvent": "FW_MISALIGNED_STORE" + }, + { + "ArchStdEvent": "FW_ACCESS_LOAD" + }, + { + "ArchStdEvent": "FW_ACCESS_STORE" + }, + { + "ArchStdEvent": "FW_ILLEGAL_INSN" + }, + { + "ArchStdEvent": "FW_SET_TIMER" + }, + { + "ArchStdEvent": "FW_IPI_SENT" + }, + { + "ArchStdEvent": "FW_IPI_RECEIVED" + }, + { + "ArchStdEvent": "FW_FENCE_I_SENT" + }, + { + "ArchStdEvent": "FW_FENCE_I_RECEIVED" + }, + { + "ArchStdEvent": "FW_SFENCE_VMA_SENT" + }, + { + "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED" + }, + { + "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED" + }, + { + "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED" + }, + { + "ArchStdEvent": "FW_HFENCE_GVMA_SENT" + }, + { + "ArchStdEvent": "FW_HFENCE_GVMA_RECEIVED" + }, + { + "ArchStdEvent": "FW_HFENCE_GVMA_VMID_SENT" + }, + { + "ArchStdEvent": "FW_HFENCE_GVMA_VMID_RECEIVED" + }, + { + "ArchStdEvent": "FW_HFENCE_VVMA_SENT" + }, + { + "ArchStdEvent": "FW_HFENCE_VVMA_RECEIVED" + }, + { + "ArchStdEvent": "FW_HFENCE_VVMA_ASID_SENT" + }, + { + "ArchStdEvent": "FW_HFENCE_VVMA_ASID_RECEIVED" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/instruction.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/instruction.json new file mode 100644 index 000000000000..c822b5373333 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/instruction.json @@ -0,0 +1,72 @@ +[ + { + "EventName": "INST_BRANCH_MISPREDICT", + "EventCode": "0x00000006", + "BriefDescription": "Mispredicted branch instructions" + }, + { + "EventName": "INST_BRANCH", + "EventCode": "0x00000007", + "BriefDescription": "Retired branch instructions" + }, + { + "EventName": "INST_JMP_MISPREDICT", + "EventCode": "0x00000008", + "BriefDescription": "Indirect branch mispredict" + }, + { + "EventName": "INST_JMP", + "EventCode": "0x00000009", + "BriefDescription": "Retired jmp instructions" + }, + { + "EventName": "INST_STORE", + "EventCode": "0x0000000b", + "BriefDescription": "Retired store instructions" + }, + { + "EventName": "INST_ALU", + "EventCode": "0x0000001d", + "BriefDescription": "Retired ALU instructions" + }, + { + "EventName": "INST_LDST", + "EventCode": "0x0000001e", + "BriefDescription": "Retired Load/Store instructions" + }, + { + "EventName": "INST_VECTOR", + "EventCode": "0x0000001f", + "BriefDescription": "Retired Vector instructions" + }, + { + "EventName": "INST_CSR", + "EventCode": "0x00000020", + "BriefDescription": "Retired CSR instructions" + }, + { + "EventName": "INST_SYNC", + "EventCode": "0x00000021", + "BriefDescription": "Retired sync instructions (AMO/LR/SC instructions)" + }, + { + "EventName": "INST_UNALIGNED_ACCESS", + "EventCode": "0x00000022", + "BriefDescription": "Retired Store/Load instructions with unaligned memory access" + }, + { + "EventName": "INST_ECALL", + "EventCode": "0x00000025", + "BriefDescription": "Retired ecall instructions" + }, + { + "EventName": "INST_LONG_JP", + "EventCode": "0x00000026", + "BriefDescription": "Retired long jump instructions" + }, + { + "EventName": "INST_FP", + "EventCode": "0x0000002a", + "BriefDescription": "Retired FPU instructions" + } +] diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/microarch.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/microarch.json new file mode 100644 index 000000000000..0ab6f288af91 --- /dev/null +++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/microarch.json @@ -0,0 +1,80 @@ +[ + { + "EventName": "LSU_SPEC_FAIL", + "EventCode": "0x0000000a", + "BriefDescription": "LSU speculation fail" + }, + { + "EventName": "IDU_RF_PIPE_FAIL", + "EventCode": "0x00000014", + "BriefDescription": "Instruction decode unit launch pipeline failed in RF state" + }, + { + "EventName": "IDU_RF_REG_FAIL", + "EventCode": "0x00000015", + "BriefDescription": "Instruction decode unit launch register file fail in RF state" + }, + { + "EventName": "IDU_RF_INSTRUCTION", + "EventCode": "0x00000016", + "BriefDescription": "retired instruction count of Instruction decode unit in RF (Register File) stage" + }, + { + "EventName": "LSU_4K_STALL", + "EventCode": "0x00000017", + "BriefDescription": "LSU stall times for long distance data access (Over 4K)", + "PublicDescription": "This stall occurs when translate virtual address with page offset over 4k" + }, + { + "EventName": "LSU_OTHER_STALL", + "EventCode": "0x00000018", + "BriefDescription": "LSU stall times for other reasons (except the 4k stall)" + }, + { + "EventName": "LSU_SQ_OTHER_DIS", + "EventCode": "0x00000019", + "BriefDescription": "LSU store queue discard others" + }, + { + "EventName": "LSU_SQ_DATA_DISCARD", + "EventCode": "0x0000001a", + "BriefDescription": "LSU store queue discard data (uops)" + }, + { + "EventName": "BRANCH_DIRECTION_MISPREDICTION", + "EventCode": "0x0000001b", + "BriefDescription": "Branch misprediction in BTB" + }, + { + "EventName": "BRANCH_DIRECTION_PREDICTION", + "EventCode": "0x0000001c", + "BriefDescription": "All branch prediction in BTB", + "PublicDescription": "This event including both successful prediction and failed prediction in BTB" + }, + { + "EventName": "INTERRUPT_ACK_COUNT", + "EventCode": "0x00000023", + "BriefDescription": "acknowledged interrupt count" + }, + { + "EventName": "INTERRUPT_OFF_CYCLE", + "EventCode": "0x00000024", + "BriefDescription": "PLIC arbitration time when the interrupt is not responded", + "PublicDescription": "The arbitration time is recorded while meeting any of the following:\n- CPU is M-mode and MIE == 0\n- CPU is S-mode and delegation and SIE == 0\n" + }, + { + "EventName": "IFU_STALLED_CYCLE", + "EventCode": "0x00000027", + "BriefDescription": "Number of stall cycles of the instruction fetch unit (IFU)." + }, + { + "EventName": "IDU_STALLED_CYCLE", + "EventCode": "0x00000028", + "BriefDescription": "hpcp_backend_stall Number of stall cycles of the instruction decoding unit (IDU) and next-level pipeline unit." + }, + { + "EventName": "SYNC_STALL", + "EventCode": "0x00000029", + "BriefDescription": "Sync instruction stall cycle fence/fence.i/sync/sfence" + } +] diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 84c132af3dfa..8bc6c0707856 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -1863,6 +1863,12 @@ "ScaleUnit": "1GHz" }, { + "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)", + "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", + "MetricName": "upi_data_receive_bw", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", "MetricName": "upi_data_transmit_bw", diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index e98602c66707..71d78a7841ea 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -1847,6 +1847,12 @@ "ScaleUnit": "1GHz" }, { + "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)", + "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", + "MetricName": "upi_data_receive_bw", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", "MetricName": "upi_data_transmit_bw", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index 06c6d67cb76b..e31a4aac9f20 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -1965,6 +1965,12 @@ "ScaleUnit": "1GHz" }, { + "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)", + "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", + "MetricName": "upi_data_receive_bw", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", "MetricName": "upi_data_transmit_bw", diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index 4a8f8eeb7525..ec3aa5ef00a3 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -1807,6 +1807,12 @@ "ScaleUnit": "1GHz" }, { + "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data receive bandwidth (MB/sec)", + "MetricExpr": "UNC_UPI_RxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", + "MetricName": "upi_data_receive_bw", + "ScaleUnit": "1MB/s" + }, + { "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", "MetricName": "upi_data_transmit_bw", diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index 3c091ab75305..0093c998cb6e 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -83,7 +83,7 @@ def c_len(s: str) -> int: """Return the length of s a C string This doesn't handle all escape characters properly. It first assumes - all \ are for escaping, it then adjusts as it will have over counted + all \\ are for escaping, it then adjusts as it will have over counted \\. The code uses \000 rather than \0 as a terminator as an adjacent number would be folded into a string of \0 (ie. "\0" + "5" doesn't equal a terminator followed by the number 5 but the escape of diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py index d59ff53f1d94..de58991c78bb 100755 --- a/tools/perf/scripts/python/arm-cs-trace-disasm.py +++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py @@ -45,8 +45,8 @@ parser = OptionParser(option_list=option_list) # Initialize global dicts and regular expression disasm_cache = dict() cpu_data = dict() -disasm_re = re.compile("^\s*([0-9a-fA-F]+):") -disasm_func_re = re.compile("^\s*([0-9a-fA-F]+)\s.*:") +disasm_re = re.compile(r"^\s*([0-9a-fA-F]+):") +disasm_func_re = re.compile(r"^\s*([0-9a-fA-F]+)\s.*:") cache_size = 64*1024 glb_source_file_name = None diff --git a/tools/perf/scripts/python/compaction-times.py b/tools/perf/scripts/python/compaction-times.py index 2560a042dc6f..9401f7c14747 100644 --- a/tools/perf/scripts/python/compaction-times.py +++ b/tools/perf/scripts/python/compaction-times.py @@ -260,7 +260,7 @@ def pr_help(): comm_re = None pid_re = None -pid_regex = "^(\d*)-(\d*)$|^(\d*)$" +pid_regex = r"^(\d*)-(\d*)$|^(\d*)$" opt_proc = popt.DISP_DFL opt_disp = topt.DISP_ALL diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 13f2d8a81610..121cf61ba1b3 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -677,8 +677,8 @@ class CallGraphModelBase(TreeModel): # sqlite supports GLOB (text only) which uses * and ? and is case sensitive if not self.glb.dbref.is_sqlite3: # Escape % and _ - s = value.replace("%", "\%") - s = s.replace("_", "\_") + s = value.replace("%", "\\%") + s = s.replace("_", "\\_") # Translate * and ? into SQL LIKE pattern characters % and _ trans = string.maketrans("*?", "%_") match = " LIKE '" + str(s).translate(trans) + "'" diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 2b45ffa462a6..53ba9c3e20e0 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -77,3 +77,17 @@ CFLAGS_python-use.o += -DPYTHONPATH="BUILD_STR($(OUTPUT)python)" -DPYTHON="BUI CFLAGS_dwarf-unwind.o += -fno-optimize-sibling-calls perf-y += workloads/ + +ifdef SHELLCHECK + SHELL_TESTS := $(shell find tests/shell -executable -type f -name '*.sh') + TEST_LOGS := $(SHELL_TESTS:tests/shell/%=shell/%.shellcheck_log) +else + SHELL_TESTS := + TEST_LOGS := +endif + +$(OUTPUT)%.shellcheck_log: % + $(call rule_mkdir) + $(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false) + +perf-y += $(TEST_LOGS) diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 61186d0d1cfa..97e1bdd6ec0e 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -188,7 +188,7 @@ static int test__attr(struct test_suite *test __maybe_unused, int subtest __mayb if (perf_pmus__num_core_pmus() > 1) { /* * TODO: Attribute tests hard code the PMU type. If there are >1 - * core PMU then each PMU will have a different type whic + * core PMU then each PMU will have a different type which * requires additional support. */ pr_debug("Skip test on hybrid systems"); diff --git a/tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64 b/tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64 index fbb065842880..bed765450ca9 100644 --- a/tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64 +++ b/tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64 @@ -6,4 +6,4 @@ args = --no-bpf-event --user-regs=vg kill >/dev/null 2>&1 ret = 129 test_ret = true arch = aarch64 -auxv = auxv["AT_HWCAP"] & 0x200000 == 0 +auxv = auxv["AT_HWCAP"] & 0x400000 == 0 diff --git a/tools/perf/tests/attr/test-record-user-regs-sve-aarch64 b/tools/perf/tests/attr/test-record-user-regs-sve-aarch64 index c598c803221d..a65113cd7311 100644 --- a/tools/perf/tests/attr/test-record-user-regs-sve-aarch64 +++ b/tools/perf/tests/attr/test-record-user-regs-sve-aarch64 @@ -6,7 +6,7 @@ args = --no-bpf-event --user-regs=vg kill >/dev/null 2>&1 ret = 1 test_ret = true arch = aarch64 -auxv = auxv["AT_HWCAP"] & 0x200000 == 0x200000 +auxv = auxv["AT_HWCAP"] & 0x400000 == 0x400000 kernel_since = 6.1 [event:base-record] diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index cb6f1dd00dc4..4a5973f9bb9b 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -14,6 +14,7 @@ #include <sys/wait.h> #include <sys/stat.h> #include "builtin.h" +#include "config.h" #include "hist.h" #include "intlist.h" #include "tests.h" @@ -32,6 +33,7 @@ static bool dont_fork; const char *dso_to_test; +const char *test_objdump_path = "objdump"; /* * List of architecture specific tests. Not a weak symbol as the array length is @@ -60,8 +62,6 @@ static struct test_suite *generic_tests[] = { &suite__pmu, &suite__pmu_events, &suite__dso_data, - &suite__dso_data_cache, - &suite__dso_data_reopen, &suite__perf_evsel__roundtrip_name_test, #ifdef HAVE_LIBTRACEEVENT &suite__perf_evsel__tp_sched_test, @@ -513,6 +513,15 @@ static int run_workload(const char *work, int argc, const char **argv) return -1; } +static int perf_test__config(const char *var, const char *value, + void *data __maybe_unused) +{ + if (!strcmp(var, "annotate.objdump")) + test_objdump_path = value; + + return 0; +} + int cmd_test(int argc, const char **argv) { const char *test_usage[] = { @@ -529,6 +538,8 @@ int cmd_test(int argc, const char **argv) "Do not fork for testcase"), OPT_STRING('w', "workload", &workload, "work", "workload to run for testing"), OPT_STRING(0, "dso", &dso_to_test, "dso", "dso to test"), + OPT_STRING(0, "objdump", &test_objdump_path, "path", + "objdump binary to use for disassembly and annotations"), OPT_END() }; const char * const test_subcommands[] = { "list", NULL }; @@ -538,6 +549,8 @@ int cmd_test(int argc, const char **argv) if (ret < 0) return ret; + perf_config(perf_test__config, NULL); + /* Unbuffered output */ setvbuf(stdout, NULL, _IONBF, 0); diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 3af81012014e..7a3a7bbbec71 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -185,7 +185,7 @@ static int read_via_objdump(const char *filename, u64 addr, void *buf, int ret; fmt = "%s -z -d --start-address=0x%"PRIx64" --stop-address=0x%"PRIx64" %s"; - ret = snprintf(cmd, sizeof(cmd), fmt, "objdump", addr, addr + len, + ret = snprintf(cmd, sizeof(cmd), fmt, test_objdump_path, addr, addr + len, filename); if (ret <= 0 || (size_t)ret >= sizeof(cmd)) return -1; @@ -511,38 +511,6 @@ static void fs_something(void) } } -#ifdef __s390x__ -#include "header.h" // for get_cpuid() -#endif - -static const char *do_determine_event(bool excl_kernel) -{ - const char *event = excl_kernel ? "cycles:u" : "cycles"; - -#ifdef __s390x__ - char cpuid[128], model[16], model_c[16], cpum_cf_v[16]; - unsigned int family; - int ret, cpum_cf_a; - - if (get_cpuid(cpuid, sizeof(cpuid))) - goto out_clocks; - ret = sscanf(cpuid, "%*[^,],%u,%[^,],%[^,],%[^,],%x", &family, model_c, - model, cpum_cf_v, &cpum_cf_a); - if (ret != 5) /* Not available */ - goto out_clocks; - if (excl_kernel && (cpum_cf_a & 4)) - return event; - if (!excl_kernel && (cpum_cf_a & 2)) - return event; - - /* Fall through: missing authorization */ -out_clocks: - event = excl_kernel ? "cpu-clock:u" : "cpu-clock"; - -#endif - return event; -} - static void do_something(void) { fs_something(); @@ -583,8 +551,10 @@ static int do_test_code_reading(bool try_kcore) int err = -1, ret; pid_t pid; struct map *map; - bool have_vmlinux, have_kcore, excl_kernel = false; + bool have_vmlinux, have_kcore; struct dso *dso; + const char *events[] = { "cycles", "cycles:u", "cpu-clock", "cpu-clock:u", NULL }; + int evidx = 0; pid = getpid(); @@ -618,7 +588,7 @@ static int do_test_code_reading(bool try_kcore) /* No point getting kernel events if there is no kernel object */ if (!have_vmlinux && !have_kcore) - excl_kernel = true; + evidx++; threads = thread_map__new_by_tid(pid); if (!threads) { @@ -640,13 +610,13 @@ static int do_test_code_reading(bool try_kcore) goto out_put; } - cpus = perf_cpu_map__new(NULL); + cpus = perf_cpu_map__new_online_cpus(); if (!cpus) { pr_debug("perf_cpu_map__new failed\n"); goto out_put; } - while (1) { + while (events[evidx]) { const char *str; evlist = evlist__new(); @@ -657,7 +627,7 @@ static int do_test_code_reading(bool try_kcore) perf_evlist__set_maps(&evlist->core, cpus, threads); - str = do_determine_event(excl_kernel); + str = events[evidx]; pr_debug("Parsing event '%s'\n", str); ret = parse_event(evlist, str); if (ret < 0) { @@ -675,32 +645,32 @@ static int do_test_code_reading(bool try_kcore) ret = evlist__open(evlist); if (ret < 0) { - if (!excl_kernel) { - excl_kernel = true; - /* - * Both cpus and threads are now owned by evlist - * and will be freed by following perf_evlist__set_maps - * call. Getting reference to keep them alive. - */ - perf_cpu_map__get(cpus); - perf_thread_map__get(threads); - perf_evlist__set_maps(&evlist->core, NULL, NULL); - evlist__delete(evlist); - evlist = NULL; - continue; - } + evidx++; - if (verbose > 0) { + if (events[evidx] == NULL && verbose > 0) { char errbuf[512]; evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf)); pr_debug("perf_evlist__open() failed!\n%s\n", errbuf); } - goto out_put; + /* + * Both cpus and threads are now owned by evlist + * and will be freed by following perf_evlist__set_maps + * call. Getting reference to keep them alive. + */ + perf_cpu_map__get(cpus); + perf_thread_map__get(threads); + perf_evlist__set_maps(&evlist->core, NULL, NULL); + evlist__delete(evlist); + evlist = NULL; + continue; } break; } + if (events[evidx] == NULL) + goto out_put; + ret = evlist__mmap(evlist, UINT_MAX); if (ret < 0) { pr_debug("evlist__mmap failed\n"); @@ -721,7 +691,7 @@ static int do_test_code_reading(bool try_kcore) err = TEST_CODE_READING_NO_KERNEL_OBJ; else if (!have_vmlinux && !try_kcore) err = TEST_CODE_READING_NO_VMLINUX; - else if (excl_kernel) + else if (strstr(events[evidx], ":u")) err = TEST_CODE_READING_NO_ACCESS; else err = TEST_CODE_READING_OK; diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 7730fc2ab40b..bd8e396f3e57 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -213,7 +213,7 @@ static int test__cpu_map_intersect(struct test_suite *test __maybe_unused, static int test__cpu_map_equal(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { - struct perf_cpu_map *any = perf_cpu_map__dummy_new(); + struct perf_cpu_map *any = perf_cpu_map__new_any_cpu(); struct perf_cpu_map *one = perf_cpu_map__new("1"); struct perf_cpu_map *two = perf_cpu_map__new("2"); struct perf_cpu_map *empty = perf_cpu_map__intersect(one, two); diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 3419a4ab5590..2d67422c1222 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -394,6 +394,15 @@ static int test__dso_data_reopen(struct test_suite *test __maybe_unused, int sub return 0; } -DEFINE_SUITE("DSO data read", dso_data); -DEFINE_SUITE("DSO data cache", dso_data_cache); -DEFINE_SUITE("DSO data reopen", dso_data_reopen); + +static struct test_case tests__dso_data[] = { + TEST_CASE("read", dso_data), + TEST_CASE("cache", dso_data_cache), + TEST_CASE("reopen", dso_data_reopen), + { .name = NULL, } +}; + +struct test_suite suite__dso_data = { + .desc = "DSO data tests", + .test_cases = tests__dso_data, +}; diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index 8f4f9b632e1e..5a3b2bed07f3 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -81,7 +81,7 @@ static int test__keep_tracking(struct test_suite *test __maybe_unused, int subte threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); - cpus = perf_cpu_map__new(NULL); + cpus = perf_cpu_map__new_online_cpus(); CHECK_NOT_NULL__(cpus); evlist = evlist__new(); diff --git a/tools/perf/tests/make b/tools/perf/tests/make index d9945ed25bc5..8a4da7eb637a 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -183,7 +183,7 @@ run += make_install_prefix_slash # run += make_install_pdf run += make_minimal -old_libbpf := $(shell echo '\#include <bpf/libbpf.h>' | $(CC) -E -dM -x c -| egrep -q "define[[:space:]]+LIBBPF_MAJOR_VERSION[[:space:]]+0{1}") +old_libbpf := $(shell echo '\#include <bpf/libbpf.h>' | $(CC) -E -dM -x c -| grep -q -E "define[[:space:]]+LIBBPF_MAJOR_VERSION[[:space:]]+0{1}") ifneq ($(old_libbpf),) run += make_libbpf_dynamic diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c index 5bb1123a91a7..bb3fbfe5a73e 100644 --- a/tools/perf/tests/maps.c +++ b/tools/perf/tests/maps.c @@ -14,44 +14,59 @@ struct map_def { u64 end; }; +struct check_maps_cb_args { + struct map_def *merged; + unsigned int i; +}; + +static int check_maps_cb(struct map *map, void *data) +{ + struct check_maps_cb_args *args = data; + struct map_def *merged = &args->merged[args->i]; + + if (map__start(map) != merged->start || + map__end(map) != merged->end || + strcmp(map__dso(map)->name, merged->name) || + refcount_read(map__refcnt(map)) != 1) { + return 1; + } + args->i++; + return 0; +} + +static int failed_cb(struct map *map, void *data __maybe_unused) +{ + pr_debug("\tstart: %" PRIu64 " end: %" PRIu64 " name: '%s' refcnt: %d\n", + map__start(map), + map__end(map), + map__dso(map)->name, + refcount_read(map__refcnt(map))); + + return 0; +} + static int check_maps(struct map_def *merged, unsigned int size, struct maps *maps) { - struct map_rb_node *rb_node; - unsigned int i = 0; bool failed = false; if (maps__nr_maps(maps) != size) { pr_debug("Expected %d maps, got %d", size, maps__nr_maps(maps)); failed = true; } else { - maps__for_each_entry(maps, rb_node) { - struct map *map = rb_node->map; - - if (map__start(map) != merged[i].start || - map__end(map) != merged[i].end || - strcmp(map__dso(map)->name, merged[i].name) || - refcount_read(map__refcnt(map)) != 1) { - failed = true; - } - i++; - } + struct check_maps_cb_args args = { + .merged = merged, + .i = 0, + }; + failed = maps__for_each_map(maps, check_maps_cb, &args); } if (failed) { pr_debug("Expected:\n"); - for (i = 0; i < size; i++) { + for (unsigned int i = 0; i < size; i++) { pr_debug("\tstart: %" PRIu64 " end: %" PRIu64 " name: '%s' refcnt: 1\n", merged[i].start, merged[i].end, merged[i].name); } pr_debug("Got:\n"); - maps__for_each_entry(maps, rb_node) { - struct map *map = rb_node->map; - - pr_debug("\tstart: %" PRIu64 " end: %" PRIu64 " name: '%s' refcnt: %d\n", - map__start(map), - map__end(map), - map__dso(map)->name, - refcount_read(map__refcnt(map))); - } + maps__for_each_map(maps, failed_cb, NULL); } return failed ? TEST_FAIL : TEST_OK; } diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 886a13a77a16..012c8ae439fd 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -52,7 +52,7 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest return -1; } - cpus = perf_cpu_map__new(NULL); + cpus = perf_cpu_map__new_online_cpus(); if (cpus == NULL) { pr_debug("perf_cpu_map__new\n"); goto out_free_threads; diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index f3275be83a33..fb114118c876 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -37,7 +37,7 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __mayb return -1; } - cpus = perf_cpu_map__new(NULL); + cpus = perf_cpu_map__new_online_cpus(); if (cpus == NULL) { pr_debug("perf_cpu_map__new\n"); goto out_thread_map_delete; diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index f78be21a5999..fbdf710d5eea 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -162,6 +162,22 @@ static int test__checkevent_numeric(struct evlist *evlist) return TEST_OK; } + +static int assert_hw(struct perf_evsel *evsel, enum perf_hw_id id, const char *name) +{ + struct perf_pmu *pmu; + + if (evsel->attr.type == PERF_TYPE_HARDWARE) { + TEST_ASSERT_VAL("wrong config", test_perf_config(evsel, id)); + return 0; + } + pmu = perf_pmus__find_by_type(evsel->attr.type); + + TEST_ASSERT_VAL("unexpected PMU type", pmu); + TEST_ASSERT_VAL("PMU missing event", perf_pmu__have_event(pmu, name)); + return 0; +} + static int test__checkevent_symbolic_name(struct evlist *evlist) { struct perf_evsel *evsel; @@ -169,10 +185,12 @@ static int test__checkevent_symbolic_name(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 0 != evlist->core.nr_entries); perf_evlist__for_each_evsel(&evlist->core, evsel) { - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", - test_perf_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); + int ret = assert_hw(evsel, PERF_COUNT_HW_INSTRUCTIONS, "instructions"); + + if (ret) + return ret; } + return TEST_OK; } @@ -183,8 +201,10 @@ static int test__checkevent_symbolic_name_config(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of entries", 0 != evlist->core.nr_entries); perf_evlist__for_each_evsel(&evlist->core, evsel) { - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type); - TEST_ASSERT_VAL("wrong config", test_perf_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + int ret = assert_hw(evsel, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + + if (ret) + return ret; /* * The period value gets configured within evlist__config, * while this test executes only parse events method. @@ -861,10 +881,14 @@ static int test__group1(struct evlist *evlist) evlist__nr_groups(evlist) == num_core_entries()); for (int i = 0; i < num_core_entries(); i++) { + int ret; + /* instructions:k */ evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel)); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -878,8 +902,10 @@ static int test__group1(struct evlist *evlist) /* cycles:upp */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -907,6 +933,8 @@ static int test__group2(struct evlist *evlist) TEST_ASSERT_VAL("wrong number of groups", 1 == evlist__nr_groups(evlist)); evlist__for_each_entry(evlist, evsel) { + int ret; + if (evsel->core.attr.type == PERF_TYPE_SOFTWARE) { /* faults + :ku modifier */ leader = evsel; @@ -939,8 +967,10 @@ static int test__group2(struct evlist *evlist) continue; } /* cycles:k */ - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -957,6 +987,7 @@ static int test__group2(struct evlist *evlist) static int test__group3(struct evlist *evlist __maybe_unused) { struct evsel *evsel, *group1_leader = NULL, *group2_leader = NULL; + int ret; TEST_ASSERT_VAL("wrong number of entries", evlist->core.nr_entries == (3 * perf_pmus__num_core_pmus() + 2)); @@ -1045,8 +1076,10 @@ static int test__group3(struct evlist *evlist __maybe_unused) continue; } /* instructions:u */ - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1070,10 +1103,14 @@ static int test__group4(struct evlist *evlist __maybe_unused) num_core_entries() == evlist__nr_groups(evlist)); for (int i = 0; i < num_core_entries(); i++) { + int ret; + /* cycles:u + p */ evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel)); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1089,8 +1126,10 @@ static int test__group4(struct evlist *evlist __maybe_unused) /* instructions:kp + p */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1108,6 +1147,7 @@ static int test__group4(struct evlist *evlist __maybe_unused) static int test__group5(struct evlist *evlist __maybe_unused) { struct evsel *evsel = NULL, *leader; + int ret; TEST_ASSERT_VAL("wrong number of entries", evlist->core.nr_entries == (5 * num_core_entries())); @@ -1117,8 +1157,10 @@ static int test__group5(struct evlist *evlist __maybe_unused) for (int i = 0; i < num_core_entries(); i++) { /* cycles + G */ evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel)); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1133,8 +1175,10 @@ static int test__group5(struct evlist *evlist __maybe_unused) /* instructions + G */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1148,8 +1192,10 @@ static int test__group5(struct evlist *evlist __maybe_unused) for (int i = 0; i < num_core_entries(); i++) { /* cycles:G */ evsel = leader = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1164,8 +1210,10 @@ static int test__group5(struct evlist *evlist __maybe_unused) /* instructions:G */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1178,8 +1226,10 @@ static int test__group5(struct evlist *evlist __maybe_unused) for (int i = 0; i < num_core_entries(); i++) { /* cycles */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1201,10 +1251,14 @@ static int test__group_gh1(struct evlist *evlist) evlist__nr_groups(evlist) == num_core_entries()); for (int i = 0; i < num_core_entries(); i++) { + int ret; + /* cycles + :H group modifier */ evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel)); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1218,8 +1272,10 @@ static int test__group_gh1(struct evlist *evlist) /* cache-misses:G + :H group modifier */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1242,10 +1298,14 @@ static int test__group_gh2(struct evlist *evlist) evlist__nr_groups(evlist) == num_core_entries()); for (int i = 0; i < num_core_entries(); i++) { + int ret; + /* cycles + :G group modifier */ evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel)); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1259,8 +1319,10 @@ static int test__group_gh2(struct evlist *evlist) /* cache-misses:H + :G group modifier */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1283,10 +1345,14 @@ static int test__group_gh3(struct evlist *evlist) evlist__nr_groups(evlist) == num_core_entries()); for (int i = 0; i < num_core_entries(); i++) { + int ret; + /* cycles:G + :u group modifier */ evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel)); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1300,8 +1366,10 @@ static int test__group_gh3(struct evlist *evlist) /* cache-misses:H + :u group modifier */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1324,10 +1392,14 @@ static int test__group_gh4(struct evlist *evlist) evlist__nr_groups(evlist) == num_core_entries()); for (int i = 0; i < num_core_entries(); i++) { + int ret; + /* cycles:G + :uG group modifier */ evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel)); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1341,8 +1413,10 @@ static int test__group_gh4(struct evlist *evlist) /* cache-misses:H + :uG group modifier */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1363,10 +1437,14 @@ static int test__leader_sample1(struct evlist *evlist) evlist->core.nr_entries == (3 * num_core_entries())); for (int i = 0; i < num_core_entries(); i++) { + int ret; + /* cycles - sampling group leader */ evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel)); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1379,8 +1457,10 @@ static int test__leader_sample1(struct evlist *evlist) /* cache-misses - not sampling */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1392,8 +1472,10 @@ static int test__leader_sample1(struct evlist *evlist) /* branch-misses - not sampling */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_BRANCH_MISSES, "branch-misses"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -1415,10 +1497,14 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused) evlist->core.nr_entries == (2 * num_core_entries())); for (int i = 0; i < num_core_entries(); i++) { + int ret; + /* instructions - sampling group leader */ evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel)); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_INSTRUCTIONS)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_INSTRUCTIONS, "instructions"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1431,8 +1517,10 @@ static int test__leader_sample2(struct evlist *evlist __maybe_unused) /* branch-misses - not sampling */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_BRANCH_MISSES, "branch-misses"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv); @@ -1472,10 +1560,14 @@ static int test__pinned_group(struct evlist *evlist) evlist->core.nr_entries == (3 * num_core_entries())); for (int i = 0; i < num_core_entries(); i++) { + int ret; + /* cycles - group leader */ evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel)); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); /* TODO: The group modifier is not copied to the split group leader. */ @@ -1484,13 +1576,18 @@ static int test__pinned_group(struct evlist *evlist) /* cache-misses - can not be pinned, but will go on with the leader */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned); /* branch-misses - ditto */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_BRANCH_MISSES, "branch-misses"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong pinned", !evsel->core.attr.pinned); } return TEST_OK; @@ -1517,10 +1614,14 @@ static int test__exclusive_group(struct evlist *evlist) evlist->core.nr_entries == 3 * num_core_entries()); for (int i = 0; i < num_core_entries(); i++) { + int ret; + /* cycles - group leader */ evsel = leader = (i == 0 ? evlist__first(evlist) : evsel__next(evsel)); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong group name", !evsel->group_name); TEST_ASSERT_VAL("wrong leader", evsel__has_leader(evsel, leader)); /* TODO: The group modifier is not copied to the split group leader. */ @@ -1529,13 +1630,18 @@ static int test__exclusive_group(struct evlist *evlist) /* cache-misses - can not be pinned, but will go on with the leader */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->core.attr.type); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CACHE_MISSES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_CACHE_MISSES, "cache-misses"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclusive", !evsel->core.attr.exclusive); /* branch-misses - ditto */ evsel = evsel__next(evsel); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_BRANCH_MISSES)); + ret = assert_hw(&evsel->core, PERF_COUNT_HW_BRANCH_MISSES, "branch-misses"); + if (ret) + return ret; + TEST_ASSERT_VAL("wrong exclusive", !evsel->core.attr.exclusive); } return TEST_OK; @@ -1677,9 +1783,11 @@ static int test__checkevent_raw_pmu(struct evlist *evlist) static int test__sym_event_slash(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); + int ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + + if (ret) + return ret; - TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel); return TEST_OK; } @@ -1687,9 +1795,11 @@ static int test__sym_event_slash(struct evlist *evlist) static int test__sym_event_dc(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); + int ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + + if (ret) + return ret; - TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong exclude_user", evsel->core.attr.exclude_user); return TEST_OK; } @@ -1697,9 +1807,11 @@ static int test__sym_event_dc(struct evlist *evlist) static int test__term_equal_term(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); + int ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + + if (ret) + return ret; - TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "name") == 0); return TEST_OK; } @@ -1707,9 +1819,11 @@ static int test__term_equal_term(struct evlist *evlist) static int test__term_equal_legacy(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); + int ret = assert_hw(&evsel->core, PERF_COUNT_HW_CPU_CYCLES, "cycles"); + + if (ret) + return ret; - TEST_ASSERT_VAL("wrong type", evsel->core.attr.type == PERF_TYPE_HARDWARE); - TEST_ASSERT_VAL("wrong config", test_config(evsel, PERF_COUNT_HW_CPU_CYCLES)); TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "l1d") == 0); return TEST_OK; } @@ -2549,7 +2663,7 @@ static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest if (strchr(ent->d_name, '.')) continue; - /* exclude parametrized ones (name contains '?') */ + /* exclude parameterized ones (name contains '?') */ n = snprintf(pmu_event, sizeof(pmu_event), "%s%s", path, ent->d_name); if (n >= PATH_MAX) { pr_err("pmu event name crossed PATH_MAX(%d) size\n", PATH_MAX); @@ -2578,7 +2692,7 @@ static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest fclose(file); if (is_event_parameterized == 1) { - pr_debug("skipping parametrized PMU event: %s which contains ?\n", pmu_event); + pr_debug("skipping parameterized PMU event: %s which contains ?\n", pmu_event); continue; } diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index efcd71c2738a..bbe2ddeb9b74 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -93,7 +93,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); - cpus = perf_cpu_map__new(NULL); + cpus = perf_cpu_map__new_online_cpus(); CHECK_NOT_NULL__(cpus); evlist = evlist__new(); diff --git a/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c b/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c index a7e169d1bf64..5f886cd09e6b 100644 --- a/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c +++ b/tools/perf/tests/shell/coresight/memcpy_thread/memcpy_thread.c @@ -42,7 +42,6 @@ static pthread_t new_thr(void *(*fn) (void *arg), void *arg) int main(int argc, char **argv) { unsigned long i, len, size, thr; - pthread_t threads[256]; struct args args[256]; long long v; diff --git a/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c b/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c index c0158fac7d0b..e05a559253ca 100644 --- a/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c +++ b/tools/perf/tests/shell/coresight/thread_loop/thread_loop.c @@ -57,7 +57,6 @@ static pthread_t new_thr(void *(*fn) (void *arg), void *arg) int main(int argc, char **argv) { unsigned int i, len, thr; - pthread_t threads[256]; struct args args[256]; if (argc < 3) { diff --git a/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c b/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c index 8f6d384208ed..0fc7bf1a25af 100644 --- a/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c +++ b/tools/perf/tests/shell/coresight/unroll_loop_thread/unroll_loop_thread.c @@ -51,7 +51,6 @@ static pthread_t new_thr(void *(*fn) (void *arg), void *arg) int main(int argc, char **argv) { unsigned int i, thr; - pthread_t threads[256]; struct args args[256]; if (argc < 2) { diff --git a/tools/perf/tests/shell/diff.sh b/tools/perf/tests/shell/diff.sh new file mode 100755 index 000000000000..14b87af88703 --- /dev/null +++ b/tools/perf/tests/shell/diff.sh @@ -0,0 +1,108 @@ +#!/bin/sh +# perf diff tests +# SPDX-License-Identifier: GPL-2.0 + +set -e + +err=0 +perfdata1=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +perfdata2=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +perfdata3=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +testprog="perf test -w thloop" + +shelldir=$(dirname "$0") +# shellcheck source=lib/perf_has_symbol.sh +. "${shelldir}"/lib/perf_has_symbol.sh + +testsym="test_loop" + +skip_test_missing_symbol ${testsym} + +cleanup() { + rm -rf "${perfdata1}" + rm -rf "${perfdata1}".old + rm -rf "${perfdata2}" + rm -rf "${perfdata2}".old + rm -rf "${perfdata3}" + rm -rf "${perfdata3}".old + + trap - EXIT TERM INT +} + +trap_cleanup() { + cleanup + exit 1 +} +trap trap_cleanup EXIT TERM INT + +make_data() { + file="$1" + if ! perf record -o "${file}" ${testprog} 2> /dev/null + then + echo "Workload record [Failed record]" + echo 1 + return + fi + if ! perf report -i "${file}" -q | grep -q "${testsym}" + then + echo "Workload record [Failed missing output]" + echo 1 + return + fi + echo 0 +} + +test_two_files() { + echo "Basic two file diff test" + err=$(make_data "${perfdata1}") + if [ $err != 0 ] + then + return + fi + err=$(make_data "${perfdata2}") + if [ $err != 0 ] + then + return + fi + + if ! perf diff "${perfdata1}" "${perfdata2}" | grep -q "${testsym}" + then + echo "Basic two file diff test [Failed diff]" + err=1 + return + fi + echo "Basic two file diff test [Success]" +} + +test_three_files() { + echo "Basic three file diff test" + err=$(make_data "${perfdata1}") + if [ $err != 0 ] + then + return + fi + err=$(make_data "${perfdata2}") + if [ $err != 0 ] + then + return + fi + err=$(make_data "${perfdata3}") + if [ $err != 0 ] + then + return + fi + + if ! perf diff "${perfdata1}" "${perfdata2}" "${perfdata3}" | grep -q "${testsym}" + then + echo "Basic three file diff test [Failed diff]" + err=1 + return + fi + echo "Basic three file diff test [Success]" +} + +test_two_files +test_three_files + +cleanup +exit $err diff --git a/tools/perf/tests/shell/lib/perf_has_symbol.sh b/tools/perf/tests/shell/lib/perf_has_symbol.sh new file mode 100644 index 000000000000..5d59c32ae3e7 --- /dev/null +++ b/tools/perf/tests/shell/lib/perf_has_symbol.sh @@ -0,0 +1,21 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +perf_has_symbol() +{ + if perf test -vv "Symbols" 2>&1 | grep "[[:space:]]$1$"; then + echo "perf does have symbol '$1'" + return 0 + fi + echo "perf does not have symbol '$1'" + return 1 +} + +skip_test_missing_symbol() +{ + if ! perf_has_symbol "$1" ; then + echo "perf is missing symbols - skipping test" + exit 2 + fi + return 0 +} diff --git a/tools/perf/tests/shell/lib/setup_python.sh b/tools/perf/tests/shell/lib/setup_python.sh new file mode 100644 index 000000000000..c2fce1793538 --- /dev/null +++ b/tools/perf/tests/shell/lib/setup_python.sh @@ -0,0 +1,16 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +if [ "x$PYTHON" = "x" ] +then + python3 --version >/dev/null 2>&1 && PYTHON=python3 +fi +if [ "x$PYTHON" = "x" ] +then + python --version >/dev/null 2>&1 && PYTHON=python +fi +if [ "x$PYTHON" = "x" ] +then + echo Skipping test, python not detected please set environment variable PYTHON. + exit 2 +fi diff --git a/tools/perf/tests/shell/list.sh b/tools/perf/tests/shell/list.sh new file mode 100755 index 000000000000..22b004f2b23e --- /dev/null +++ b/tools/perf/tests/shell/list.sh @@ -0,0 +1,19 @@ +#!/bin/sh +# perf list tests +# SPDX-License-Identifier: GPL-2.0 + +set -e +err=0 + +shelldir=$(dirname "$0") +# shellcheck source=lib/setup_python.sh +. "${shelldir}"/lib/setup_python.sh + +test_list_json() { + echo "Json output test" + perf list -j | $PYTHON -m json.tool + echo "Json output test [Success]" +} + +test_list_json +exit $err diff --git a/tools/perf/tests/shell/pipe_test.sh b/tools/perf/tests/shell/pipe_test.sh index 8dd115dd35a7..a78d35d2cff0 100755 --- a/tools/perf/tests/shell/pipe_test.sh +++ b/tools/perf/tests/shell/pipe_test.sh @@ -2,10 +2,17 @@ # perf pipe recording and injection test # SPDX-License-Identifier: GPL-2.0 +shelldir=$(dirname "$0") +# shellcheck source=lib/perf_has_symbol.sh +. "${shelldir}"/lib/perf_has_symbol.sh + +sym="noploop" + +skip_test_missing_symbol ${sym} + data=$(mktemp /tmp/perf.data.XXXXXX) prog="perf test -w noploop" task="perf" -sym="noploop" if ! perf record -e task-clock:u -o - ${prog} | perf report -i - --task | grep ${task}; then echo "cannot find the test file in the perf report" diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index eebeea6bdc76..72c65570db37 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -45,7 +45,10 @@ trace_libc_inet_pton_backtrace() { ;; ppc64|ppc64le) eventattr='max-stack=4' - echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected + # Add gaih_inet to expected backtrace only if it is part of libc. + if nm $libc | grep -F -q gaih_inet.; then + echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected + fi echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected ;; diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh index 29443b8e8876..3d1a7759a7b2 100755 --- a/tools/perf/tests/shell/record.sh +++ b/tools/perf/tests/shell/record.sh @@ -8,10 +8,19 @@ shelldir=$(dirname "$0") # shellcheck source=lib/waiting.sh . "${shelldir}"/lib/waiting.sh +# shellcheck source=lib/perf_has_symbol.sh +. "${shelldir}"/lib/perf_has_symbol.sh + +testsym="test_loop" + +skip_test_missing_symbol ${testsym} + err=0 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) testprog="perf test -w thloop" -testsym="test_loop" +cpu_pmu_dir="/sys/bus/event_source/devices/cpu*" +br_cntr_file="/caps/branch_counter_nr" +br_cntr_output="branch stack counters" cleanup() { rm -rf "${perfdata}" @@ -155,10 +164,37 @@ test_workload() { echo "Basic target workload test [Success]" } +test_branch_counter() { + echo "Basic branch counter test" + # Check if the branch counter feature is supported + for dir in $cpu_pmu_dir + do + if [ ! -e "$dir$br_cntr_file" ] + then + echo "branch counter feature not supported on all core PMUs ($dir) [Skipped]" + return + fi + done + if ! perf record -o "${perfdata}" -j any,counter ${testprog} 2> /dev/null + then + echo "Basic branch counter test [Failed record]" + err=1 + return + fi + if ! perf report -i "${perfdata}" -D -q | grep -q "$br_cntr_output" + then + echo "Basic branch record test [Failed missing output]" + err=1 + return + fi + echo "Basic branch counter test [Success]" +} + test_per_thread test_register_capture test_system_wide test_workload +test_branch_counter cleanup exit $err diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh index a1ef8f0d2b5c..67c925f3a15a 100755 --- a/tools/perf/tests/shell/record_offcpu.sh +++ b/tools/perf/tests/shell/record_offcpu.sh @@ -77,9 +77,9 @@ test_offcpu_child() { err=1 return fi - # each process waits for read and write, so it should be more than 800 events + # each process waits at least for poll, so it should be more than 400 events if ! perf report -i ${perfdata} -s comm -q -n -t ';' --percent-limit=90 | \ - awk -F ";" '{ if (NF > 3 && int($3) < 800) exit 1; }' + awk -F ";" '{ if (NF > 3 && int($3) < 400) exit 1; }' then echo "Child task off-cpu test [Failed invalid output]" err=1 diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh index 196e22672c50..3bc900533a5d 100755 --- a/tools/perf/tests/shell/stat+json_output.sh +++ b/tools/perf/tests/shell/stat+json_output.sh @@ -8,20 +8,10 @@ set -e skip_test=0 +shelldir=$(dirname "$0") +# shellcheck source=lib/setup_python.sh +. "${shelldir}"/lib/setup_python.sh pythonchecker=$(dirname $0)/lib/perf_json_output_lint.py -if [ "x$PYTHON" == "x" ] -then - if which python3 > /dev/null - then - PYTHON=python3 - elif which python > /dev/null - then - PYTHON=python - else - echo Skipping test, python not detected please set environment variable PYTHON. - exit 2 - fi -fi stat_output=$(mktemp /tmp/__perf_test.stat_output.json.XXXXX) diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh index c77955419173..d2a3506e0d19 100755 --- a/tools/perf/tests/shell/stat_all_pmu.sh +++ b/tools/perf/tests/shell/stat_all_pmu.sh @@ -4,7 +4,7 @@ set -e -# Test all PMU events; however exclude parametrized ones (name contains '?') +# Test all PMU events; however exclude parameterized ones (name contains '?') for p in $(perf list --raw-dump pmu | sed 's/[[:graph:]]\+?[[:graph:]]\+[[:space:]]//g'); do echo "Testing $p" result=$(perf stat -e "$p" true 2>&1) diff --git a/tools/perf/tests/shell/stat_metrics_values.sh b/tools/perf/tests/shell/stat_metrics_values.sh index ad94c936de7e..7ca172599aa6 100755 --- a/tools/perf/tests/shell/stat_metrics_values.sh +++ b/tools/perf/tests/shell/stat_metrics_values.sh @@ -1,16 +1,10 @@ #!/bin/bash # perf metrics value validation # SPDX-License-Identifier: GPL-2.0 -if [ "x$PYTHON" == "x" ] -then - if which python3 > /dev/null - then - PYTHON=python3 - else - echo Skipping test, python3 not detected please set environment variable PYTHON. - exit 2 - fi -fi + +shelldir=$(dirname "$0") +# shellcheck source=lib/setup_python.sh +. "${shelldir}"/lib/setup_python.sh grep -q GenuineIntel /proc/cpuinfo || { echo Skipping non-Intel; exit 2; } diff --git a/tools/perf/tests/shell/test_arm_callgraph_fp.sh b/tools/perf/tests/shell/test_arm_callgraph_fp.sh index 66dfdfdad553..e342e6c8aa50 100755 --- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh +++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh @@ -2,8 +2,14 @@ # Check Arm64 callgraphs are complete in fp mode # SPDX-License-Identifier: GPL-2.0 +shelldir=$(dirname "$0") +# shellcheck source=lib/perf_has_symbol.sh +. "${shelldir}"/lib/perf_has_symbol.sh + lscpu | grep -q "aarch64" || exit 2 +skip_test_missing_symbol leafloop + PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX) TEST_PROGRAM="perf test -w leafloop" diff --git a/tools/perf/tests/shell/test_brstack.sh b/tools/perf/tests/shell/test_brstack.sh index 09908d71c994..5f14d0cb013f 100755 --- a/tools/perf/tests/shell/test_brstack.sh +++ b/tools/perf/tests/shell/test_brstack.sh @@ -4,6 +4,10 @@ # SPDX-License-Identifier: GPL-2.0 # German Gomez <german.gomez@arm.com>, 2022 +shelldir=$(dirname "$0") +# shellcheck source=lib/perf_has_symbol.sh +. "${shelldir}"/lib/perf_has_symbol.sh + # skip the test if the hardware doesn't support branch stack sampling # and if the architecture doesn't support filter types: any,save_type,u if ! perf record -o- --no-buildid --branch-filter any,save_type,u -- true > /dev/null 2>&1 ; then @@ -11,6 +15,8 @@ if ! perf record -o- --no-buildid --branch-filter any,save_type,u -- true > /dev exit 2 fi +skip_test_missing_symbol brstack_bench + TMPDIR=$(mktemp -d /tmp/__perf_test.program.XXXXX) TESTPROG="perf test -w brstack" diff --git a/tools/perf/tests/shell/test_data_symbol.sh b/tools/perf/tests/shell/test_data_symbol.sh index 69bb6fe86c50..3dfa91832aa8 100755 --- a/tools/perf/tests/shell/test_data_symbol.sh +++ b/tools/perf/tests/shell/test_data_symbol.sh @@ -4,6 +4,13 @@ # SPDX-License-Identifier: GPL-2.0 # Leo Yan <leo.yan@linaro.org>, 2022 +shelldir=$(dirname "$0") +# shellcheck source=lib/waiting.sh +. "${shelldir}"/lib/waiting.sh + +# shellcheck source=lib/perf_has_symbol.sh +. "${shelldir}"/lib/perf_has_symbol.sh + skip_if_no_mem_event() { perf mem record -e list 2>&1 | grep -E -q 'available' && return 0 return 2 @@ -11,8 +18,11 @@ skip_if_no_mem_event() { skip_if_no_mem_event || exit 2 +skip_test_missing_symbol buf1 + TEST_PROGRAM="perf test -w datasym" PERF_DATA=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +ERR_FILE=$(mktemp /tmp/__perf_test.stderr.XXXXX) check_result() { # The memory report format is as below: @@ -50,13 +60,15 @@ echo "Recording workload..." # specific CPU and test in per-CPU mode. is_amd=$(grep -E -c 'vendor_id.*AuthenticAMD' /proc/cpuinfo) if (($is_amd >= 1)); then - perf mem record -o ${PERF_DATA} -C 0 -- taskset -c 0 $TEST_PROGRAM & + perf mem record -vvv -o ${PERF_DATA} -C 0 -- taskset -c 0 $TEST_PROGRAM 2>"${ERR_FILE}" & else - perf mem record --all-user -o ${PERF_DATA} -- $TEST_PROGRAM & + perf mem record -vvv --all-user -o ${PERF_DATA} -- $TEST_PROGRAM 2>"${ERR_FILE}" & fi PERFPID=$! +wait_for_perf_to_start ${PERFPID} "${ERR_FILE}" + sleep 1 kill $PERFPID diff --git a/tools/perf/tests/shell/test_perf_data_converter_json.sh b/tools/perf/tests/shell/test_perf_data_converter_json.sh index 6ded58f98f55..c4f1b59d116f 100755 --- a/tools/perf/tests/shell/test_perf_data_converter_json.sh +++ b/tools/perf/tests/shell/test_perf_data_converter_json.sh @@ -6,16 +6,9 @@ set -e err=0 -if [ "$PYTHON" = "" ] ; then - if which python3 > /dev/null ; then - PYTHON=python3 - elif which python > /dev/null ; then - PYTHON=python - else - echo Skipping test, python not detected please set environment variable PYTHON. - exit 2 - fi -fi +shelldir=$(dirname "$0") +# shellcheck source=lib/setup_python.sh +. "${shelldir}"/lib/setup_python.sh perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) result=$(mktemp /tmp/__perf_test.output.json.XXXXX) diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c index 1de7478ec189..e6fd934b027a 100644 --- a/tools/perf/tests/sigtrap.c +++ b/tools/perf/tests/sigtrap.c @@ -57,36 +57,79 @@ static struct perf_event_attr make_event_attr(void) #ifdef HAVE_BPF_SKEL #include <bpf/btf.h> -static bool attr_has_sigtrap(void) +static struct btf *btf; + +static bool btf__available(void) { - bool ret = false; - struct btf *btf; - const struct btf_type *t; + if (btf == NULL) + btf = btf__load_vmlinux_btf(); + + return btf != NULL; +} + +static void btf__exit(void) +{ + btf__free(btf); + btf = NULL; +} + +static const struct btf_member *__btf_type__find_member_by_name(int type_id, const char *member_name) +{ + const struct btf_type *t = btf__type_by_id(btf, type_id); const struct btf_member *m; - const char *name; - int i, id; + int i; + + for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) { + const char *current_member_name = btf__name_by_offset(btf, m->name_off); + if (!strcmp(current_member_name, member_name)) + return m; + } - btf = btf__load_vmlinux_btf(); - if (btf == NULL) { + return NULL; +} + +static bool attr_has_sigtrap(void) +{ + int id; + + if (!btf__available()) { /* should be an old kernel */ return false; } id = btf__find_by_name_kind(btf, "perf_event_attr", BTF_KIND_STRUCT); if (id < 0) - goto out; + return false; - t = btf__type_by_id(btf, id); - for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) { - name = btf__name_by_offset(btf, m->name_off); - if (!strcmp(name, "sigtrap")) { - ret = true; - break; - } - } -out: - btf__free(btf); - return ret; + return __btf_type__find_member_by_name(id, "sigtrap") != NULL; +} + +static bool kernel_with_sleepable_spinlocks(void) +{ + const struct btf_member *member; + const struct btf_type *type; + const char *type_name; + int id; + + if (!btf__available()) + return false; + + id = btf__find_by_name_kind(btf, "spinlock", BTF_KIND_STRUCT); + if (id < 0) + return false; + + // Only RT has a "lock" member for "struct spinlock" + member = __btf_type__find_member_by_name(id, "lock"); + if (member == NULL) + return false; + + // But check its type as well + type = btf__type_by_id(btf, member->type); + if (!type || !btf_is_struct(type)) + return false; + + type_name = btf__name_by_offset(btf, type->name_off); + return type_name && !strcmp(type_name, "rt_mutex_base"); } #else /* !HAVE_BPF_SKEL */ static bool attr_has_sigtrap(void) @@ -109,6 +152,15 @@ static bool attr_has_sigtrap(void) return ret; } + +static bool kernel_with_sleepable_spinlocks(void) +{ + return false; +} + +static void btf__exit(void) +{ +} #endif /* HAVE_BPF_SKEL */ static void @@ -147,7 +199,7 @@ static int run_test_threads(pthread_t *threads, pthread_barrier_t *barrier) static int run_stress_test(int fd, pthread_t *threads, pthread_barrier_t *barrier) { - int ret; + int ret, expected_sigtraps; ctx.iterate_on = 3000; @@ -156,7 +208,16 @@ static int run_stress_test(int fd, pthread_t *threads, pthread_barrier_t *barrie ret = run_test_threads(threads, barrier); TEST_ASSERT_EQUAL("disable failed", ioctl(fd, PERF_EVENT_IOC_DISABLE, 0), 0); - TEST_ASSERT_EQUAL("unexpected sigtraps", ctx.signal_count, NUM_THREADS * ctx.iterate_on); + expected_sigtraps = NUM_THREADS * ctx.iterate_on; + + if (ctx.signal_count < expected_sigtraps && kernel_with_sleepable_spinlocks()) { + pr_debug("Expected %d sigtraps, got %d, running on a kernel with sleepable spinlocks.\n", + expected_sigtraps, ctx.signal_count); + pr_debug("See https://lore.kernel.org/all/e368f2c848d77fbc8d259f44e2055fe469c219cf.camel@gmx.de/\n"); + return TEST_SKIP; + } else + TEST_ASSERT_EQUAL("unexpected sigtraps", ctx.signal_count, expected_sigtraps); + TEST_ASSERT_EQUAL("missing signals or incorrectly delivered", ctx.tids_want_signal, 0); TEST_ASSERT_VAL("unexpected si_addr", ctx.first_siginfo.si_addr == &ctx.iterate_on); #if 0 /* FIXME: enable when libc's signal.h has si_perf_{type,data} */ @@ -221,6 +282,7 @@ out_restore_sigaction: sigaction(SIGTRAP, &oldact, NULL); out: pthread_barrier_destroy(&barrier); + btf__exit(); return ret; } diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 4d7493fa0105..290716783ac6 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -62,7 +62,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) } evlist__add(evlist, evsel); - cpus = perf_cpu_map__dummy_new(); + cpus = perf_cpu_map__new_any_cpu(); threads = thread_map__new_by_tid(getpid()); if (!cpus || !threads) { err = -ENOMEM; diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index e52b031bedc5..5cab17a1942e 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -351,7 +351,7 @@ static int test__switch_tracking(struct test_suite *test __maybe_unused, int sub goto out_err; } - cpus = perf_cpu_map__new(NULL); + cpus = perf_cpu_map__new_online_cpus(); if (!cpus) { pr_debug("perf_cpu_map__new failed!\n"); goto out_err; diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 968dddde6dda..d33d0952025c 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -70,7 +70,7 @@ static int test__task_exit(struct test_suite *test __maybe_unused, int subtest _ * evlist__prepare_workload we'll fill in the only thread * we're monitoring, the one forked there. */ - cpus = perf_cpu_map__dummy_new(); + cpus = perf_cpu_map__new_any_cpu(); threads = thread_map__new_by_tid(-1); if (!cpus || !threads) { err = -ENOMEM; diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index b394f3ac2d66..dad3d7414142 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -207,5 +207,6 @@ DECLARE_WORKLOAD(brstack); DECLARE_WORKLOAD(datasym); extern const char *dso_to_test; +extern const char *test_objdump_path; #endif /* TESTS_H */ diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index 9dee63734e66..2a842f53fbb5 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -215,7 +215,7 @@ static int test__session_topology(struct test_suite *test __maybe_unused, int su if (session_write_header(path)) goto free_path; - map = perf_cpu_map__new(NULL); + map = perf_cpu_map__new_online_cpus(); if (map == NULL) { pr_debug("failed to get system cpumap\n"); goto free_path; diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 1078a93b01aa..822f893e67d5 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -112,18 +112,92 @@ static bool is_ignored_symbol(const char *name, char type) return false; } +struct test__vmlinux_matches_kallsyms_cb_args { + struct machine kallsyms; + struct map *vmlinux_map; + bool header_printed; +}; + +static int test__vmlinux_matches_kallsyms_cb1(struct map *map, void *data) +{ + struct test__vmlinux_matches_kallsyms_cb_args *args = data; + struct dso *dso = map__dso(map); + /* + * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while + * the kernel will have the path for the vmlinux file being used, so use + * the short name, less descriptive but the same ("[kernel]" in both + * cases. + */ + struct map *pair = maps__find_by_name(args->kallsyms.kmaps, + (dso->kernel ? dso->short_name : dso->name)); + + if (pair) + map__set_priv(pair, 1); + else { + if (!args->header_printed) { + pr_info("WARN: Maps only in vmlinux:\n"); + args->header_printed = true; + } + map__fprintf(map, stderr); + } + return 0; +} + +static int test__vmlinux_matches_kallsyms_cb2(struct map *map, void *data) +{ + struct test__vmlinux_matches_kallsyms_cb_args *args = data; + struct map *pair; + u64 mem_start = map__unmap_ip(args->vmlinux_map, map__start(map)); + u64 mem_end = map__unmap_ip(args->vmlinux_map, map__end(map)); + + pair = maps__find(args->kallsyms.kmaps, mem_start); + if (pair == NULL || map__priv(pair)) + return 0; + + if (map__start(pair) == mem_start) { + struct dso *dso = map__dso(map); + + if (!args->header_printed) { + pr_info("WARN: Maps in vmlinux with a different name in kallsyms:\n"); + args->header_printed = true; + } + + pr_info("WARN: %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as", + map__start(map), map__end(map), map__pgoff(map), dso->name); + if (mem_end != map__end(pair)) + pr_info(":\nWARN: *%" PRIx64 "-%" PRIx64 " %" PRIx64, + map__start(pair), map__end(pair), map__pgoff(pair)); + pr_info(" %s\n", dso->name); + map__set_priv(pair, 1); + } + return 0; +} + +static int test__vmlinux_matches_kallsyms_cb3(struct map *map, void *data) +{ + struct test__vmlinux_matches_kallsyms_cb_args *args = data; + + if (!map__priv(map)) { + if (!args->header_printed) { + pr_info("WARN: Maps only in kallsyms:\n"); + args->header_printed = true; + } + map__fprintf(map, stderr); + } + return 0; +} + static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct rb_node *nd; struct symbol *sym; - struct map *kallsyms_map, *vmlinux_map; - struct map_rb_node *rb_node; - struct machine kallsyms, vmlinux; + struct map *kallsyms_map; + struct machine vmlinux; struct maps *maps; u64 mem_start, mem_end; - bool header_printed; + struct test__vmlinux_matches_kallsyms_cb_args args; /* * Step 1: @@ -131,7 +205,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused * Init the machines that will hold kernel, modules obtained from * both vmlinux + .ko files and from /proc/kallsyms split by modules. */ - machine__init(&kallsyms, "", HOST_KERNEL_ID); + machine__init(&args.kallsyms, "", HOST_KERNEL_ID); machine__init(&vmlinux, "", HOST_KERNEL_ID); maps = machine__kernel_maps(&vmlinux); @@ -143,7 +217,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused * load /proc/kallsyms. Also create the modules maps from /proc/modules * and find the .ko files that match them in /lib/modules/`uname -r`/. */ - if (machine__create_kernel_maps(&kallsyms) < 0) { + if (machine__create_kernel_maps(&args.kallsyms) < 0) { pr_debug("machine__create_kernel_maps failed"); err = TEST_SKIP; goto out; @@ -160,7 +234,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused * be compacted against the list of modules found in the "vmlinux" * code and with the one got from /proc/modules from the "kallsyms" code. */ - if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms") <= 0) { + if (machine__load_kallsyms(&args.kallsyms, "/proc/kallsyms") <= 0) { pr_debug("machine__load_kallsyms failed"); err = TEST_SKIP; goto out; @@ -174,7 +248,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused * to see if the running kernel was relocated by checking if it has the * same value in the vmlinux file we load. */ - kallsyms_map = machine__kernel_map(&kallsyms); + kallsyms_map = machine__kernel_map(&args.kallsyms); /* * Step 5: @@ -186,7 +260,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused goto out; } - vmlinux_map = machine__kernel_map(&vmlinux); + args.vmlinux_map = machine__kernel_map(&vmlinux); /* * Step 6: @@ -213,7 +287,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused * in the kallsyms dso. For the ones that are in both, check its names and * end addresses too. */ - map__for_each_symbol(vmlinux_map, sym, nd) { + map__for_each_symbol(args.vmlinux_map, sym, nd) { struct symbol *pair, *first_pair; sym = rb_entry(nd, struct symbol, rb_node); @@ -221,10 +295,10 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused if (sym->start == sym->end) continue; - mem_start = map__unmap_ip(vmlinux_map, sym->start); - mem_end = map__unmap_ip(vmlinux_map, sym->end); + mem_start = map__unmap_ip(args.vmlinux_map, sym->start); + mem_end = map__unmap_ip(args.vmlinux_map, sym->end); - first_pair = machine__find_kernel_symbol(&kallsyms, mem_start, NULL); + first_pair = machine__find_kernel_symbol(&args.kallsyms, mem_start, NULL); pair = first_pair; if (pair && UM(pair->start) == mem_start) { @@ -253,7 +327,8 @@ next_pair: */ continue; } else { - pair = machine__find_kernel_symbol_by_name(&kallsyms, sym->name, NULL); + pair = machine__find_kernel_symbol_by_name(&args.kallsyms, + sym->name, NULL); if (pair) { if (UM(pair->start) == mem_start) goto next_pair; @@ -267,7 +342,7 @@ next_pair: continue; } - } else if (mem_start == map__end(kallsyms.vmlinux_map)) { + } else if (mem_start == map__end(args.kallsyms.vmlinux_map)) { /* * Ignore aliases to _etext, i.e. to the end of the kernel text area, * such as __indirect_thunk_end. @@ -289,78 +364,18 @@ next_pair: if (verbose <= 0) goto out; - header_printed = false; - - maps__for_each_entry(maps, rb_node) { - struct map *map = rb_node->map; - struct dso *dso = map__dso(map); - /* - * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while - * the kernel will have the path for the vmlinux file being used, - * so use the short name, less descriptive but the same ("[kernel]" in - * both cases. - */ - struct map *pair = maps__find_by_name(kallsyms.kmaps, (dso->kernel ? - dso->short_name : - dso->name)); - if (pair) { - map__set_priv(pair, 1); - } else { - if (!header_printed) { - pr_info("WARN: Maps only in vmlinux:\n"); - header_printed = true; - } - map__fprintf(map, stderr); - } - } - - header_printed = false; - - maps__for_each_entry(maps, rb_node) { - struct map *pair, *map = rb_node->map; - - mem_start = map__unmap_ip(vmlinux_map, map__start(map)); - mem_end = map__unmap_ip(vmlinux_map, map__end(map)); + args.header_printed = false; + maps__for_each_map(maps, test__vmlinux_matches_kallsyms_cb1, &args); - pair = maps__find(kallsyms.kmaps, mem_start); - if (pair == NULL || map__priv(pair)) - continue; - - if (map__start(pair) == mem_start) { - struct dso *dso = map__dso(map); - - if (!header_printed) { - pr_info("WARN: Maps in vmlinux with a different name in kallsyms:\n"); - header_printed = true; - } - - pr_info("WARN: %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as", - map__start(map), map__end(map), map__pgoff(map), dso->name); - if (mem_end != map__end(pair)) - pr_info(":\nWARN: *%" PRIx64 "-%" PRIx64 " %" PRIx64, - map__start(pair), map__end(pair), map__pgoff(pair)); - pr_info(" %s\n", dso->name); - map__set_priv(pair, 1); - } - } - - header_printed = false; - - maps = machine__kernel_maps(&kallsyms); + args.header_printed = false; + maps__for_each_map(maps, test__vmlinux_matches_kallsyms_cb2, &args); - maps__for_each_entry(maps, rb_node) { - struct map *map = rb_node->map; + args.header_printed = false; + maps = machine__kernel_maps(&args.kallsyms); + maps__for_each_map(maps, test__vmlinux_matches_kallsyms_cb3, &args); - if (!map__priv(map)) { - if (!header_printed) { - pr_info("WARN: Maps only in kallsyms:\n"); - header_printed = true; - } - map__fprintf(map, stderr); - } - } out: - machine__exit(&kallsyms); + machine__exit(&args.kallsyms); machine__exit(&vmlinux); return err; } diff --git a/tools/perf/tests/workloads/thloop.c b/tools/perf/tests/workloads/thloop.c index af05269c2eb8..457b29f91c3e 100644 --- a/tools/perf/tests/workloads/thloop.c +++ b/tools/perf/tests/workloads/thloop.c @@ -7,7 +7,6 @@ #include "../tests.h" static volatile sig_atomic_t done; -static volatile unsigned count; /* We want to check this symbol in perf report */ noinline void test_loop(void); @@ -19,8 +18,7 @@ static void sighandler(int sig __maybe_unused) noinline void test_loop(void) { - while (!done) - __atomic_fetch_add(&count, 1, __ATOMIC_RELAXED); + while (!done); } static void *thfunc(void *arg) diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh index cc09dcaa891e..7df4bf5b55a3 100755 --- a/tools/perf/trace/beauty/arch_errno_names.sh +++ b/tools/perf/trace/beauty/arch_errno_names.sh @@ -57,13 +57,13 @@ create_arch_errno_table_func() archlist="$1" default="$2" - printf 'const char *arch_syscalls__strerrno(const char *arch, int err)\n' + printf 'arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch)\n' printf '{\n' for arch in $archlist; do printf '\tif (!strcmp(arch, "%s"))\n' $(arch_string "$arch") - printf '\t\treturn errno_to_name__%s(err);\n' $(arch_string "$arch") + printf '\t\treturn errno_to_name__%s;\n' $(arch_string "$arch") done - printf '\treturn errno_to_name__%s(err);\n' $(arch_string "$default") + printf '\treturn errno_to_name__%s;\n' $(arch_string "$default") printf '}\n' } @@ -76,7 +76,9 @@ EoHEADER # Create list of architectures that have a specific errno.h. archlist="" -for arch in $(find $toolsdir/arch -maxdepth 1 -mindepth 1 -type d -printf "%f\n" | sort -r); do +for f in $toolsdir/arch/*/include/uapi/asm/errno.h; do + d=${f%/include/uapi/asm/errno.h} + arch="${d##*/}" test -f $toolsdir/arch/$arch/include/uapi/asm/errno.h && archlist="$archlist $arch" done diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 788e8f6bd90e..9feb794f5c6e 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -251,6 +251,4 @@ size_t open__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool sh void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg, size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg)); -const char *arch_syscalls__strerrno(const char *arch, int err); - #endif /* _PERF_TRACE_BEAUTY_H */ diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh index 8059342ca412..9455d9672f14 100755 --- a/tools/perf/trace/beauty/prctl_option.sh +++ b/tools/perf/trace/beauty/prctl_option.sh @@ -4,9 +4,9 @@ [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *prctl_options[] = {\n" -regex='^#define[[:space:]]{1}PR_(\w+)[[:space:]]*([[:xdigit:]]+)([[:space:]]*\/.*)?$' +regex='^#define[[:space:]]{1}PR_(\w+)[[:space:]]*([[:xdigit:]]+)([[:space:]]*/.*)?$' grep -E $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \ - sed -r "s/$regex/\2 \1/g" | \ + sed -E "s%$regex%\2 \1%g" | \ sort -n | xargs printf "\t[%s] = \"%s\",\n" printf "};\n" diff --git a/tools/perf/trace/beauty/socket.sh b/tools/perf/trace/beauty/socket.sh index 8bc7ba62203e..670c6db298ae 100755 --- a/tools/perf/trace/beauty/socket.sh +++ b/tools/perf/trace/beauty/socket.sh @@ -18,10 +18,10 @@ grep -E $ipproto_regex ${uapi_header_dir}/in.h | \ printf "};\n\n" printf "static const char *socket_level[] = {\n" -socket_level_regex='^#define[[:space:]]+SOL_(\w+)[[:space:]]+([[:digit:]]+)([[:space:]]+\/.*)?' +socket_level_regex='^#define[[:space:]]+SOL_(\w+)[[:space:]]+([[:digit:]]+)([[:space:]]+/.*)?' grep -E $socket_level_regex ${beauty_header_dir}/socket.h | \ - sed -r "s/$socket_level_regex/\2 \1/g" | \ + sed -E "s%$socket_level_regex%\2 \1%g" | \ sort -n | xargs printf "\t[%s] = \"%s\",\n" printf "};\n\n" diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index ccdb2cd11fbf..cb2eb6dcb532 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -27,7 +27,6 @@ struct annotate_browser { struct rb_node *curr_hot; struct annotation_line *selection; struct arch *arch; - struct annotation_options *opts; bool searching_backwards; char search_bf[128]; }; @@ -38,11 +37,10 @@ static inline struct annotation *browser__annotation(struct ui_browser *browser) return symbol__annotation(ms->sym); } -static bool disasm_line__filter(struct ui_browser *browser, void *entry) +static bool disasm_line__filter(struct ui_browser *browser __maybe_unused, void *entry) { - struct annotation *notes = browser__annotation(browser); struct annotation_line *al = list_entry(entry, struct annotation_line, node); - return annotation_line__filter(al, notes); + return annotation_line__filter(al); } static int ui_browser__jumps_percent_color(struct ui_browser *browser, int nr, bool current) @@ -97,7 +95,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int struct annotation_write_ops ops = { .first_line = row == 0, .current_entry = is_current_entry, - .change_color = (!notes->options->hide_src_code && + .change_color = (!annotate_opts.hide_src_code && (!is_current_entry || (browser->use_navkeypressed && !browser->navkeypressed))), @@ -114,7 +112,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int if (!browser->navkeypressed) ops.width += 1; - annotation_line__write(al, notes, &ops, ab->opts); + annotation_line__write(al, notes, &ops); if (ops.current_entry) ab->selection = al; @@ -128,7 +126,7 @@ static int is_fused(struct annotate_browser *ab, struct disasm_line *cursor) while (pos && pos->al.offset == -1) { pos = list_prev_entry(pos, al.node); - if (!ab->opts->hide_src_code) + if (!annotate_opts.hide_src_code) diff++; } @@ -188,14 +186,14 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) * name right after the '<' token and probably treating this like a * 'call' instruction. */ - target = notes->offsets[cursor->ops.target.offset]; + target = notes->src->offsets[cursor->ops.target.offset]; if (target == NULL) { ui_helpline__printf("WARN: jump target inconsistency, press 'o', notes->offsets[%#x] = NULL\n", cursor->ops.target.offset); return; } - if (notes->options->hide_src_code) { + if (annotate_opts.hide_src_code) { from = cursor->al.idx_asm; to = target->idx_asm; } else { @@ -224,7 +222,7 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser) int ret = ui_browser__list_head_refresh(browser); int pcnt_width = annotation__pcnt_width(notes); - if (notes->options->jump_arrows) + if (annotate_opts.jump_arrows) annotate_browser__draw_current_jump(browser); ui_browser__set_color(browser, HE_COLORSET_NORMAL); @@ -258,7 +256,7 @@ static void disasm_rb_tree__insert(struct annotate_browser *browser, parent = *p; l = rb_entry(parent, struct annotation_line, rb_node); - if (disasm__cmp(al, l, browser->opts->percent_type) < 0) + if (disasm__cmp(al, l, annotate_opts.percent_type) < 0) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -270,7 +268,6 @@ static void disasm_rb_tree__insert(struct annotate_browser *browser, static void annotate_browser__set_top(struct annotate_browser *browser, struct annotation_line *pos, u32 idx) { - struct annotation *notes = browser__annotation(&browser->b); unsigned back; ui_browser__refresh_dimensions(&browser->b); @@ -280,7 +277,7 @@ static void annotate_browser__set_top(struct annotate_browser *browser, while (browser->b.top_idx != 0 && back != 0) { pos = list_entry(pos->node.prev, struct annotation_line, node); - if (annotation_line__filter(pos, notes)) + if (annotation_line__filter(pos)) continue; --browser->b.top_idx; @@ -294,11 +291,10 @@ static void annotate_browser__set_top(struct annotate_browser *browser, static void annotate_browser__set_rb_top(struct annotate_browser *browser, struct rb_node *nd) { - struct annotation *notes = browser__annotation(&browser->b); struct annotation_line * pos = rb_entry(nd, struct annotation_line, rb_node); u32 idx = pos->idx; - if (notes->options->hide_src_code) + if (annotate_opts.hide_src_code) idx = pos->idx_asm; annotate_browser__set_top(browser, pos, idx); browser->curr_hot = nd; @@ -331,13 +327,13 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser, double percent; percent = annotation_data__percent(&pos->al.data[i], - browser->opts->percent_type); + annotate_opts.percent_type); if (max_percent < percent) max_percent = percent; } - if (max_percent < 0.01 && pos->al.ipc == 0) { + if (max_percent < 0.01 && (!pos->al.cycles || pos->al.cycles->ipc == 0)) { RB_CLEAR_NODE(&pos->al.rb_node); continue; } @@ -380,12 +376,12 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser) browser->b.seek(&browser->b, offset, SEEK_CUR); al = list_entry(browser->b.top, struct annotation_line, node); - if (notes->options->hide_src_code) { + if (annotate_opts.hide_src_code) { if (al->idx_asm < offset) offset = al->idx; - browser->b.nr_entries = notes->nr_entries; - notes->options->hide_src_code = false; + browser->b.nr_entries = notes->src->nr_entries; + annotate_opts.hide_src_code = false; browser->b.seek(&browser->b, -offset, SEEK_CUR); browser->b.top_idx = al->idx - offset; browser->b.index = al->idx; @@ -402,8 +398,8 @@ static bool annotate_browser__toggle_source(struct annotate_browser *browser) if (al->idx_asm < offset) offset = al->idx_asm; - browser->b.nr_entries = notes->nr_asm_entries; - notes->options->hide_src_code = true; + browser->b.nr_entries = notes->src->nr_asm_entries; + annotate_opts.hide_src_code = true; browser->b.seek(&browser->b, -offset, SEEK_CUR); browser->b.top_idx = al->idx_asm - offset; browser->b.index = al->idx_asm; @@ -435,7 +431,7 @@ static void ui_browser__init_asm_mode(struct ui_browser *browser) { struct annotation *notes = browser__annotation(browser); ui_browser__reset_index(browser); - browser->nr_entries = notes->nr_asm_entries; + browser->nr_entries = notes->src->nr_asm_entries; } static int sym_title(struct symbol *sym, struct map *map, char *title, @@ -483,8 +479,8 @@ static bool annotate_browser__callq(struct annotate_browser *browser, target_ms.map = ms->map; target_ms.sym = dl->ops.target.sym; annotation__unlock(notes); - symbol__tui_annotate(&target_ms, evsel, hbt, browser->opts); - sym_title(ms->sym, ms->map, title, sizeof(title), browser->opts->percent_type); + symbol__tui_annotate(&target_ms, evsel, hbt); + sym_title(ms->sym, ms->map, title, sizeof(title), annotate_opts.percent_type); ui_browser__show_title(&browser->b, title); return true; } @@ -500,7 +496,7 @@ struct disasm_line *annotate_browser__find_offset(struct annotate_browser *brows list_for_each_entry(pos, ¬es->src->source, al.node) { if (pos->al.offset == offset) return pos; - if (!annotation_line__filter(&pos->al, notes)) + if (!annotation_line__filter(&pos->al)) ++*idx; } @@ -544,7 +540,7 @@ struct annotation_line *annotate_browser__find_string(struct annotate_browser *b *idx = browser->b.index; list_for_each_entry_continue(al, ¬es->src->source, node) { - if (annotation_line__filter(al, notes)) + if (annotation_line__filter(al)) continue; ++*idx; @@ -581,7 +577,7 @@ struct annotation_line *annotate_browser__find_string_reverse(struct annotate_br *idx = browser->b.index; list_for_each_entry_continue_reverse(al, ¬es->src->source, node) { - if (annotation_line__filter(al, notes)) + if (annotation_line__filter(al)) continue; --*idx; @@ -659,7 +655,6 @@ bool annotate_browser__continue_search_reverse(struct annotate_browser *browser, static int annotate_browser__show(struct ui_browser *browser, char *title, const char *help) { - struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); struct map_symbol *ms = browser->priv; struct symbol *sym = ms->sym; char symbol_dso[SYM_TITLE_MAX_SIZE]; @@ -667,7 +662,7 @@ static int annotate_browser__show(struct ui_browser *browser, char *title, const if (ui_browser__show(browser, title, help) < 0) return -1; - sym_title(sym, ms->map, symbol_dso, sizeof(symbol_dso), ab->opts->percent_type); + sym_title(sym, ms->map, symbol_dso, sizeof(symbol_dso), annotate_opts.percent_type); ui_browser__gotorc_title(browser, 0, 0); ui_browser__set_color(browser, HE_COLORSET_ROOT); @@ -809,7 +804,7 @@ static int annotate_browser__run(struct annotate_browser *browser, annotate_browser__show(&browser->b, title, help); continue; case 'k': - notes->options->show_linenr = !notes->options->show_linenr; + annotate_opts.show_linenr = !annotate_opts.show_linenr; continue; case 'l': annotate_browser__show_full_location (&browser->b); @@ -822,18 +817,18 @@ static int annotate_browser__run(struct annotate_browser *browser, ui_helpline__puts(help); continue; case 'o': - notes->options->use_offset = !notes->options->use_offset; + annotate_opts.use_offset = !annotate_opts.use_offset; annotation__update_column_widths(notes); continue; case 'O': - if (++notes->options->offset_level > ANNOTATION__MAX_OFFSET_LEVEL) - notes->options->offset_level = ANNOTATION__MIN_OFFSET_LEVEL; + if (++annotate_opts.offset_level > ANNOTATION__MAX_OFFSET_LEVEL) + annotate_opts.offset_level = ANNOTATION__MIN_OFFSET_LEVEL; continue; case 'j': - notes->options->jump_arrows = !notes->options->jump_arrows; + annotate_opts.jump_arrows = !annotate_opts.jump_arrows; continue; case 'J': - notes->options->show_nr_jumps = !notes->options->show_nr_jumps; + annotate_opts.show_nr_jumps = !annotate_opts.show_nr_jumps; annotation__update_column_widths(notes); continue; case '/': @@ -860,7 +855,7 @@ show_help: browser->b.height, browser->b.index, browser->b.top_idx, - notes->nr_asm_entries); + notes->src->nr_asm_entries); } continue; case K_ENTER: @@ -884,7 +879,7 @@ show_sup_ins: continue; } case 'P': - map_symbol__annotation_dump(ms, evsel, browser->opts); + map_symbol__annotation_dump(ms, evsel); continue; case 't': if (symbol_conf.show_total_period) { @@ -897,15 +892,15 @@ show_sup_ins: annotation__update_column_widths(notes); continue; case 'c': - if (notes->options->show_minmax_cycle) - notes->options->show_minmax_cycle = false; + if (annotate_opts.show_minmax_cycle) + annotate_opts.show_minmax_cycle = false; else - notes->options->show_minmax_cycle = true; + annotate_opts.show_minmax_cycle = true; annotation__update_column_widths(notes); continue; case 'p': case 'b': - switch_percent_type(browser->opts, key == 'b'); + switch_percent_type(&annotate_opts, key == 'b'); hists__scnprintf_title(hists, title, sizeof(title)); annotate_browser__show(&browser->b, title, help); continue; @@ -932,26 +927,23 @@ out: } int map_symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, - struct hist_browser_timer *hbt, - struct annotation_options *opts) + struct hist_browser_timer *hbt) { - return symbol__tui_annotate(ms, evsel, hbt, opts); + return symbol__tui_annotate(ms, evsel, hbt); } int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel, - struct hist_browser_timer *hbt, - struct annotation_options *opts) + struct hist_browser_timer *hbt) { /* reset abort key so that it can get Ctrl-C as a key */ SLang_reset_tty(); SLang_init_tty(0, 0, 0); - return map_symbol__tui_annotate(&he->ms, evsel, hbt, opts); + return map_symbol__tui_annotate(&he->ms, evsel, hbt); } int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, - struct hist_browser_timer *hbt, - struct annotation_options *opts) + struct hist_browser_timer *hbt) { struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); @@ -965,7 +957,6 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, .priv = ms, .use_navkeypressed = true, }, - .opts = opts, }; struct dso *dso; int ret = -1, err; @@ -979,7 +970,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, return -1; if (not_annotated) { - err = symbol__annotate2(ms, evsel, opts, &browser.arch); + err = symbol__annotate2(ms, evsel, &browser.arch); if (err) { char msg[BUFSIZ]; dso->annotate_warned = true; @@ -991,12 +982,12 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, ui_helpline__push("Press ESC to exit"); - browser.b.width = notes->max_line_len; - browser.b.nr_entries = notes->nr_entries; + browser.b.width = notes->src->max_line_len; + browser.b.nr_entries = notes->src->nr_entries; browser.b.entries = ¬es->src->source, browser.b.width += 18; /* Percentage */ - if (notes->options->hide_src_code) + if (annotate_opts.hide_src_code) ui_browser__init_asm_mode(&browser.b); ret = annotate_browser__run(&browser, evsel, hbt); @@ -1006,6 +997,6 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, out_free_offsets: if(not_annotated) - zfree(¬es->offsets); + zfree(¬es->src->offsets); return ret; } diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index f4812b226818..3061dea29e6b 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2250,8 +2250,7 @@ struct hist_browser *hist_browser__new(struct hists *hists) static struct hist_browser * perf_evsel_browser__new(struct evsel *evsel, struct hist_browser_timer *hbt, - struct perf_env *env, - struct annotation_options *annotation_opts) + struct perf_env *env) { struct hist_browser *browser = hist_browser__new(evsel__hists(evsel)); @@ -2259,7 +2258,6 @@ perf_evsel_browser__new(struct evsel *evsel, browser->hbt = hbt; browser->env = env; browser->title = hists_browser__scnprintf_title; - browser->annotation_opts = annotation_opts; } return browser; } @@ -2432,8 +2430,8 @@ do_annotate(struct hist_browser *browser, struct popup_action *act) struct hist_entry *he; int err; - if (!browser->annotation_opts->objdump_path && - perf_env__lookup_objdump(browser->env, &browser->annotation_opts->objdump_path)) + if (!annotate_opts.objdump_path && + perf_env__lookup_objdump(browser->env, &annotate_opts.objdump_path)) return 0; notes = symbol__annotation(act->ms.sym); @@ -2445,8 +2443,7 @@ do_annotate(struct hist_browser *browser, struct popup_action *act) else evsel = hists_to_evsel(browser->hists); - err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt, - browser->annotation_opts); + err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt); he = hist_browser__selected_entry(browser); /* * offer option to annotate the other branch source or target @@ -2943,11 +2940,10 @@ next: static int evsel__hists_browse(struct evsel *evsel, int nr_events, const char *helpline, bool left_exits, struct hist_browser_timer *hbt, float min_pcnt, - struct perf_env *env, bool warn_lost_event, - struct annotation_options *annotation_opts) + struct perf_env *env, bool warn_lost_event) { struct hists *hists = evsel__hists(evsel); - struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env, annotation_opts); + struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env); struct branch_info *bi = NULL; #define MAX_OPTIONS 16 char *options[MAX_OPTIONS]; @@ -3398,7 +3394,6 @@ out: struct evsel_menu { struct ui_browser b; struct evsel *selection; - struct annotation_options *annotation_opts; bool lost_events, lost_events_warned; float min_pcnt; struct perf_env *env; @@ -3499,8 +3494,7 @@ browse_hists: hbt->timer(hbt->arg); key = evsel__hists_browse(pos, nr_events, help, true, hbt, menu->min_pcnt, menu->env, - warn_lost_event, - menu->annotation_opts); + warn_lost_event); ui_browser__show_title(&menu->b, title); switch (key) { case K_TAB: @@ -3557,7 +3551,7 @@ static bool filter_group_entries(struct ui_browser *browser __maybe_unused, static int __evlist__tui_browse_hists(struct evlist *evlist, int nr_entries, const char *help, struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, - bool warn_lost_event, struct annotation_options *annotation_opts) + bool warn_lost_event) { struct evsel *pos; struct evsel_menu menu = { @@ -3572,7 +3566,6 @@ static int __evlist__tui_browse_hists(struct evlist *evlist, int nr_entries, con }, .min_pcnt = min_pcnt, .env = env, - .annotation_opts = annotation_opts, }; ui_helpline__push("Press ESC to exit"); @@ -3607,8 +3600,7 @@ static bool evlist__single_entry(struct evlist *evlist) } int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, - float min_pcnt, struct perf_env *env, bool warn_lost_event, - struct annotation_options *annotation_opts) + float min_pcnt, struct perf_env *env, bool warn_lost_event) { int nr_entries = evlist->core.nr_entries; @@ -3617,7 +3609,7 @@ single_entry: { struct evsel *first = evlist__first(evlist); return evsel__hists_browse(first, nr_entries, help, false, hbt, min_pcnt, - env, warn_lost_event, annotation_opts); + env, warn_lost_event); } } @@ -3635,7 +3627,7 @@ single_entry: { } return __evlist__tui_browse_hists(evlist, nr_entries, help, hbt, min_pcnt, env, - warn_lost_event, annotation_opts); + warn_lost_event); } static int block_hists_browser__title(struct hist_browser *browser, char *bf, @@ -3654,8 +3646,7 @@ static int block_hists_browser__title(struct hist_browser *browser, char *bf, } int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel, - float min_percent, struct perf_env *env, - struct annotation_options *annotation_opts) + float min_percent, struct perf_env *env) { struct hists *hists = &bh->block_hists; struct hist_browser *browser; @@ -3672,7 +3663,6 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel, browser->title = block_hists_browser__title; browser->min_pcnt = min_percent; browser->env = env; - browser->annotation_opts = annotation_opts; /* reset abort key so that it can get Ctrl-C as a key */ SLang_reset_tty(); diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h index 1e938d9ffa5e..de46f6c56b0e 100644 --- a/tools/perf/ui/browsers/hists.h +++ b/tools/perf/ui/browsers/hists.h @@ -4,7 +4,6 @@ #include "ui/browser.h" -struct annotation_options; struct evsel; struct hist_browser { @@ -15,7 +14,6 @@ struct hist_browser { struct hist_browser_timer *hbt; struct pstack *pstack; struct perf_env *env; - struct annotation_options *annotation_opts; struct evsel *block_evsel; int print_seq; bool show_dso; diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index 2effac77ca8c..394861245fd3 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -162,7 +162,6 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct map_symbol *ms, } static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel, - struct annotation_options *options, struct hist_browser_timer *hbt) { struct dso *dso = map__dso(ms->map); @@ -176,7 +175,7 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel, if (dso->annotate_warned) return -1; - err = symbol__annotate(ms, evsel, options, NULL); + err = symbol__annotate(ms, evsel, NULL); if (err) { char msg[BUFSIZ]; dso->annotate_warned = true; @@ -244,10 +243,9 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel, int hist_entry__gtk_annotate(struct hist_entry *he, struct evsel *evsel, - struct annotation_options *options, struct hist_browser_timer *hbt) { - return symbol__gtk_annotate(&he->ms, evsel, options, hbt); + return symbol__gtk_annotate(&he->ms, evsel, hbt); } void perf_gtk__show_annotations(void) diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h index 1e84dceb5267..a2b497f03fd6 100644 --- a/tools/perf/ui/gtk/gtk.h +++ b/tools/perf/ui/gtk/gtk.h @@ -56,13 +56,11 @@ struct evsel; struct evlist; struct hist_entry; struct hist_browser_timer; -struct annotation_options; int evlist__gtk_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt); int hist_entry__gtk_annotate(struct hist_entry *he, struct evsel *evsel, - struct annotation_options *options, struct hist_browser_timer *hbt); void perf_gtk__show_annotations(void); diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 988473bf907a..132508ebe125 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -195,6 +195,7 @@ endif perf-$(CONFIG_DWARF) += probe-finder.o perf-$(CONFIG_DWARF) += dwarf-aux.o perf-$(CONFIG_DWARF) += dwarf-regs.o +perf-$(CONFIG_DWARF) += debuginfo.o perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind-local.o diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 82956adf9963..c81fa0791918 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -57,6 +57,9 @@ #include <linux/ctype.h> +/* global annotation options */ +struct annotation_options annotate_opts; + static regex_t file_lineno; static struct ins_ops *ins__find(struct arch *arch, const char *name); @@ -85,6 +88,8 @@ struct arch { struct { char comment_char; char skip_functions_char; + char register_char; + char memory_ref_char; } objdump; }; @@ -188,6 +193,8 @@ static struct arch architectures[] = { .insn_suffix = "bwlq", .objdump = { .comment_char = '#', + .register_char = '%', + .memory_ref_char = '(', }, }, { @@ -340,10 +347,10 @@ bool ins__is_call(const struct ins *ins) */ static inline const char *validate_comma(const char *c, struct ins_operands *ops) { - if (ops->raw_comment && c > ops->raw_comment) + if (ops->jump.raw_comment && c > ops->jump.raw_comment) return NULL; - if (ops->raw_func_start && c > ops->raw_func_start) + if (ops->jump.raw_func_start && c > ops->jump.raw_func_start) return NULL; return c; @@ -359,8 +366,8 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s const char *c = strchr(ops->raw, ','); u64 start, end; - ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char); - ops->raw_func_start = strchr(ops->raw, '<'); + ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char); + ops->jump.raw_func_start = strchr(ops->raw, '<'); c = validate_comma(c, ops); @@ -462,7 +469,16 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size, ops->target.offset); } +static void jump__delete(struct ins_operands *ops __maybe_unused) +{ + /* + * The ops->jump.raw_comment and ops->jump.raw_func_start belong to the + * raw string, don't free them. + */ +} + static struct ins_ops jump_ops = { + .free = jump__delete, .parse = jump__parse, .scnprintf = jump__scnprintf, }; @@ -557,6 +573,34 @@ static struct ins_ops lock_ops = { .scnprintf = lock__scnprintf, }; +/* + * Check if the operand has more than one registers like x86 SIB addressing: + * 0x1234(%rax, %rbx, 8) + * + * But it doesn't care segment selectors like %gs:0x5678(%rcx), so just check + * the input string after 'memory_ref_char' if exists. + */ +static bool check_multi_regs(struct arch *arch, const char *op) +{ + int count = 0; + + if (arch->objdump.register_char == 0) + return false; + + if (arch->objdump.memory_ref_char) { + op = strchr(op, arch->objdump.memory_ref_char); + if (op == NULL) + return false; + } + + while ((op = strchr(op, arch->objdump.register_char)) != NULL) { + count++; + op++; + } + + return count > 1; +} + static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused) { char *s = strchr(ops->raw, ','), *target, *comment, prev; @@ -584,6 +628,8 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_sy if (ops->source.raw == NULL) return -1; + ops->source.multi_regs = check_multi_regs(arch, ops->source.raw); + target = skip_spaces(++s); comment = strchr(s, arch->objdump.comment_char); @@ -604,6 +650,8 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_sy if (ops->target.raw == NULL) goto out_free_source; + ops->target.multi_regs = check_multi_regs(arch, ops->target.raw); + if (comment == NULL) return 0; @@ -810,7 +858,6 @@ static __maybe_unused void annotated_source__delete(struct annotated_source *src if (src == NULL) return; zfree(&src->histograms); - zfree(&src->cycles_hist); free(src); } @@ -845,18 +892,6 @@ static int annotated_source__alloc_histograms(struct annotated_source *src, return src->histograms ? 0 : -1; } -/* The cycles histogram is lazily allocated. */ -static int symbol__alloc_hist_cycles(struct symbol *sym) -{ - struct annotation *notes = symbol__annotation(sym); - const size_t size = symbol__size(sym); - - notes->src->cycles_hist = calloc(size, sizeof(struct cyc_hist)); - if (notes->src->cycles_hist == NULL) - return -1; - return 0; -} - void symbol__annotate_zero_histograms(struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); @@ -865,9 +900,10 @@ void symbol__annotate_zero_histograms(struct symbol *sym) if (notes->src != NULL) { memset(notes->src->histograms, 0, notes->src->nr_histograms * notes->src->sizeof_sym_hist); - if (notes->src->cycles_hist) - memset(notes->src->cycles_hist, 0, - symbol__size(sym) * sizeof(struct cyc_hist)); + } + if (notes->branch && notes->branch->cycles_hist) { + memset(notes->branch->cycles_hist, 0, + symbol__size(sym) * sizeof(struct cyc_hist)); } annotation__unlock(notes); } @@ -958,23 +994,33 @@ static int __symbol__inc_addr_samples(struct map_symbol *ms, return 0; } +struct annotated_branch *annotation__get_branch(struct annotation *notes) +{ + if (notes == NULL) + return NULL; + + if (notes->branch == NULL) + notes->branch = zalloc(sizeof(*notes->branch)); + + return notes->branch; +} + static struct cyc_hist *symbol__cycles_hist(struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); + struct annotated_branch *branch; - if (notes->src == NULL) { - notes->src = annotated_source__new(); - if (notes->src == NULL) - return NULL; - goto alloc_cycles_hist; - } + branch = annotation__get_branch(notes); + if (branch == NULL) + return NULL; - if (!notes->src->cycles_hist) { -alloc_cycles_hist: - symbol__alloc_hist_cycles(sym); + if (branch->cycles_hist == NULL) { + const size_t size = symbol__size(sym); + + branch->cycles_hist = calloc(size, sizeof(struct cyc_hist)); } - return notes->src->cycles_hist; + return branch->cycles_hist; } struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists) @@ -1077,12 +1123,20 @@ static unsigned annotation__count_insn(struct annotation *notes, u64 start, u64 u64 offset; for (offset = start; offset <= end; offset++) { - if (notes->offsets[offset]) + if (notes->src->offsets[offset]) n_insn++; } return n_insn; } +static void annotated_branch__delete(struct annotated_branch *branch) +{ + if (branch) { + zfree(&branch->cycles_hist); + free(branch); + } +} + static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 end, struct cyc_hist *ch) { unsigned n_insn; @@ -1091,6 +1145,7 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 n_insn = annotation__count_insn(notes, start, end); if (n_insn && ch->num && ch->cycles) { + struct annotated_branch *branch; float ipc = n_insn / ((double)ch->cycles / (double)ch->num); /* Hide data when there are too many overlaps. */ @@ -1098,54 +1153,76 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 return; for (offset = start; offset <= end; offset++) { - struct annotation_line *al = notes->offsets[offset]; + struct annotation_line *al = notes->src->offsets[offset]; - if (al && al->ipc == 0.0) { - al->ipc = ipc; + if (al && al->cycles && al->cycles->ipc == 0.0) { + al->cycles->ipc = ipc; cover_insn++; } } - if (cover_insn) { - notes->hit_cycles += ch->cycles; - notes->hit_insn += n_insn * ch->num; - notes->cover_insn += cover_insn; + branch = annotation__get_branch(notes); + if (cover_insn && branch) { + branch->hit_cycles += ch->cycles; + branch->hit_insn += n_insn * ch->num; + branch->cover_insn += cover_insn; } } } -void annotation__compute_ipc(struct annotation *notes, size_t size) +static int annotation__compute_ipc(struct annotation *notes, size_t size) { + int err = 0; s64 offset; - if (!notes->src || !notes->src->cycles_hist) - return; + if (!notes->branch || !notes->branch->cycles_hist) + return 0; - notes->total_insn = annotation__count_insn(notes, 0, size - 1); - notes->hit_cycles = 0; - notes->hit_insn = 0; - notes->cover_insn = 0; + notes->branch->total_insn = annotation__count_insn(notes, 0, size - 1); + notes->branch->hit_cycles = 0; + notes->branch->hit_insn = 0; + notes->branch->cover_insn = 0; annotation__lock(notes); for (offset = size - 1; offset >= 0; --offset) { struct cyc_hist *ch; - ch = ¬es->src->cycles_hist[offset]; + ch = ¬es->branch->cycles_hist[offset]; if (ch && ch->cycles) { struct annotation_line *al; + al = notes->src->offsets[offset]; + if (al && al->cycles == NULL) { + al->cycles = zalloc(sizeof(*al->cycles)); + if (al->cycles == NULL) { + err = ENOMEM; + break; + } + } if (ch->have_start) annotation__count_and_fill(notes, ch->start, offset, ch); - al = notes->offsets[offset]; if (al && ch->num_aggr) { - al->cycles = ch->cycles_aggr / ch->num_aggr; - al->cycles_max = ch->cycles_max; - al->cycles_min = ch->cycles_min; + al->cycles->avg = ch->cycles_aggr / ch->num_aggr; + al->cycles->max = ch->cycles_max; + al->cycles->min = ch->cycles_min; } - notes->have_cycles = true; } } + + if (err) { + while (++offset < (s64)size) { + struct cyc_hist *ch = ¬es->branch->cycles_hist[offset]; + + if (ch && ch->cycles) { + struct annotation_line *al = notes->src->offsets[offset]; + if (al) + zfree(&al->cycles); + } + } + } + annotation__unlock(notes); + return 0; } int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, @@ -1225,6 +1302,7 @@ static void annotation_line__exit(struct annotation_line *al) { zfree_srcline(&al->path); zfree(&al->line); + zfree(&al->cycles); } static size_t disasm_line_size(int nr) @@ -1299,6 +1377,7 @@ int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool r void annotation__exit(struct annotation *notes) { annotated_source__delete(notes->src); + annotated_branch__delete(notes->branch); } static struct sharded_mutex *sharded_mutex; @@ -1817,7 +1896,6 @@ static int symbol__disassemble_bpf(struct symbol *sym, struct annotate_args *args) { struct annotation *notes = symbol__annotation(sym); - struct annotation_options *opts = args->options; struct bpf_prog_linfo *prog_linfo = NULL; struct bpf_prog_info_node *info_node; int len = sym->end - sym->start; @@ -1927,7 +2005,7 @@ static int symbol__disassemble_bpf(struct symbol *sym, prev_buf_size = buf_size; fflush(s); - if (!opts->hide_src_code && srcline) { + if (!annotate_opts.hide_src_code && srcline) { args->offset = -1; args->line = strdup(srcline); args->line_nr = 0; @@ -2050,7 +2128,7 @@ static char *expand_tabs(char *line, char **storage, size_t *storage_len) static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) { - struct annotation_options *opts = args->options; + struct annotation_options *opts = &annotate_opts; struct map *map = args->ms.map; struct dso *dso = map__dso(map); char *command; @@ -2113,12 +2191,13 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) err = asprintf(&command, "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 - " -l -d %s %s %s %c%s%c %s%s -C \"$1\"", + " %s -d %s %s %s %c%s%c %s%s -C \"$1\"", opts->objdump_path ?: "objdump", opts->disassembler_style ? "-M " : "", opts->disassembler_style ?: "", map__rip_2objdump(map, sym->start), map__rip_2objdump(map, sym->end), + opts->show_linenr ? "-l" : "", opts->show_asm_raw ? "" : "--no-show-raw-insn", opts->annotate_src ? "-S" : "", opts->prefix ? "--prefix " : "", @@ -2300,13 +2379,13 @@ void symbol__calc_percent(struct symbol *sym, struct evsel *evsel) } int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, - struct annotation_options *options, struct arch **parch) + struct arch **parch) { struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); struct annotate_args args = { .evsel = evsel, - .options = options, + .options = &annotate_opts, }; struct perf_env *env = evsel__env(evsel); const char *arch_name = perf_env__arch(env); @@ -2334,7 +2413,7 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, } args.ms = *ms; - if (notes->options && notes->options->full_addr) + if (annotate_opts.full_addr) notes->start = map__objdump_2mem(ms->map, ms->sym->start); else notes->start = map__rip_2objdump(ms->map, ms->sym->start); @@ -2342,12 +2421,12 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, return symbol__disassemble(sym, &args); } -static void insert_source_line(struct rb_root *root, struct annotation_line *al, - struct annotation_options *opts) +static void insert_source_line(struct rb_root *root, struct annotation_line *al) { struct annotation_line *iter; struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; + unsigned int percent_type = annotate_opts.percent_type; int i, ret; while (*p != NULL) { @@ -2358,7 +2437,7 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al, if (ret == 0) { for (i = 0; i < al->data_nr; i++) { iter->data[i].percent_sum += annotation_data__percent(&al->data[i], - opts->percent_type); + percent_type); } return; } @@ -2371,7 +2450,7 @@ static void insert_source_line(struct rb_root *root, struct annotation_line *al, for (i = 0; i < al->data_nr; i++) { al->data[i].percent_sum = annotation_data__percent(&al->data[i], - opts->percent_type); + percent_type); } rb_link_node(&al->rb_node, parent, p); @@ -2493,8 +2572,7 @@ static int annotated_source__addr_fmt_width(struct list_head *lines, u64 start) return 0; } -int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel, - struct annotation_options *opts) +int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel) { struct map *map = ms->map; struct symbol *sym = ms->sym; @@ -2505,6 +2583,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel, struct annotation *notes = symbol__annotation(sym); struct sym_hist *h = annotation__histogram(notes, evsel->core.idx); struct annotation_line *pos, *queue = NULL; + struct annotation_options *opts = &annotate_opts; u64 start = map__rip_2objdump(map, sym->start); int printed = 2, queue_len = 0, addr_fmt_width; int more = 0; @@ -2633,8 +2712,7 @@ static void FILE__write_graph(void *fp, int graph) fputs(s, fp); } -static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp, - struct annotation_options *opts) +static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp) { struct annotation *notes = symbol__annotation(sym); struct annotation_write_ops wops = { @@ -2649,9 +2727,9 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp, struct annotation_line *al; list_for_each_entry(al, ¬es->src->source, node) { - if (annotation_line__filter(al, notes)) + if (annotation_line__filter(al)) continue; - annotation_line__write(al, notes, &wops, opts); + annotation_line__write(al, notes, &wops); fputc('\n', fp); wops.first_line = false; } @@ -2659,8 +2737,7 @@ static int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp, return 0; } -int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel, - struct annotation_options *opts) +int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel) { const char *ev_name = evsel__name(evsel); char buf[1024]; @@ -2682,7 +2759,7 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel, fprintf(fp, "%s() %s\nEvent: %s\n\n", ms->sym->name, map__dso(ms->map)->long_name, ev_name); - symbol__annotate_fprintf2(ms->sym, fp, opts); + symbol__annotate_fprintf2(ms->sym, fp); fclose(fp); err = 0; @@ -2769,7 +2846,7 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym) return; for (offset = 0; offset < size; ++offset) { - struct annotation_line *al = notes->offsets[offset]; + struct annotation_line *al = notes->src->offsets[offset]; struct disasm_line *dl; dl = disasm_line(al); @@ -2777,7 +2854,7 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym) if (!disasm_line__is_valid_local_jump(dl, sym)) continue; - al = notes->offsets[dl->ops.target.offset]; + al = notes->src->offsets[dl->ops.target.offset]; /* * FIXME: Oops, no jump target? Buggy disassembler? Or do we @@ -2794,19 +2871,20 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym) void annotation__set_offsets(struct annotation *notes, s64 size) { struct annotation_line *al; + struct annotated_source *src = notes->src; - notes->max_line_len = 0; - notes->nr_entries = 0; - notes->nr_asm_entries = 0; + src->max_line_len = 0; + src->nr_entries = 0; + src->nr_asm_entries = 0; - list_for_each_entry(al, ¬es->src->source, node) { + list_for_each_entry(al, &src->source, node) { size_t line_len = strlen(al->line); - if (notes->max_line_len < line_len) - notes->max_line_len = line_len; - al->idx = notes->nr_entries++; + if (src->max_line_len < line_len) + src->max_line_len = line_len; + al->idx = src->nr_entries++; if (al->offset != -1) { - al->idx_asm = notes->nr_asm_entries++; + al->idx_asm = src->nr_asm_entries++; /* * FIXME: short term bandaid to cope with assembly * routines that comes with labels in the same column @@ -2815,7 +2893,7 @@ void annotation__set_offsets(struct annotation *notes, s64 size) * E.g. copy_user_generic_unrolled */ if (al->offset < size) - notes->offsets[al->offset] = al; + notes->src->offsets[al->offset] = al; } else al->idx_asm = -1; } @@ -2858,24 +2936,24 @@ void annotation__init_column_widths(struct annotation *notes, struct symbol *sym void annotation__update_column_widths(struct annotation *notes) { - if (notes->options->use_offset) + if (annotate_opts.use_offset) notes->widths.target = notes->widths.min_addr; - else if (notes->options->full_addr) + else if (annotate_opts.full_addr) notes->widths.target = BITS_PER_LONG / 4; else notes->widths.target = notes->widths.max_addr; notes->widths.addr = notes->widths.target; - if (notes->options->show_nr_jumps) + if (annotate_opts.show_nr_jumps) notes->widths.addr += notes->widths.jumps + 1; } void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *ms) { - notes->options->full_addr = !notes->options->full_addr; + annotate_opts.full_addr = !annotate_opts.full_addr; - if (notes->options->full_addr) + if (annotate_opts.full_addr) notes->start = map__objdump_2mem(ms->map, ms->sym->start); else notes->start = map__rip_2objdump(ms->map, ms->sym->start); @@ -2884,8 +2962,7 @@ void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *m } static void annotation__calc_lines(struct annotation *notes, struct map *map, - struct rb_root *root, - struct annotation_options *opts) + struct rb_root *root) { struct annotation_line *al; struct rb_root tmp_root = RB_ROOT; @@ -2898,7 +2975,7 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map, double percent; percent = annotation_data__percent(&al->data[i], - opts->percent_type); + annotate_opts.percent_type); if (percent > percent_max) percent_max = percent; @@ -2909,22 +2986,20 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map, al->path = get_srcline(map__dso(map), notes->start + al->offset, NULL, false, true, notes->start + al->offset); - insert_source_line(&tmp_root, al, opts); + insert_source_line(&tmp_root, al); } resort_source_line(root, &tmp_root); } -static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root, - struct annotation_options *opts) +static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root) { struct annotation *notes = symbol__annotation(ms->sym); - annotation__calc_lines(notes, ms->map, root, opts); + annotation__calc_lines(notes, ms->map, root); } -int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel, - struct annotation_options *opts) +int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel) { struct dso *dso = map__dso(ms->map); struct symbol *sym = ms->sym; @@ -2933,7 +3008,7 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel, char buf[1024]; int err; - err = symbol__annotate2(ms, evsel, opts, NULL); + err = symbol__annotate2(ms, evsel, NULL); if (err) { char msg[BUFSIZ]; @@ -2943,31 +3018,31 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel, return -1; } - if (opts->print_lines) { - srcline_full_filename = opts->full_path; - symbol__calc_lines(ms, &source_line, opts); + if (annotate_opts.print_lines) { + srcline_full_filename = annotate_opts.full_path; + symbol__calc_lines(ms, &source_line); print_summary(&source_line, dso->long_name); } hists__scnprintf_title(hists, buf, sizeof(buf)); fprintf(stdout, "%s, [percent: %s]\n%s() %s\n", - buf, percent_type_str(opts->percent_type), sym->name, dso->long_name); - symbol__annotate_fprintf2(sym, stdout, opts); + buf, percent_type_str(annotate_opts.percent_type), sym->name, + dso->long_name); + symbol__annotate_fprintf2(sym, stdout); annotated_source__purge(symbol__annotation(sym)->src); return 0; } -int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel, - struct annotation_options *opts) +int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel) { struct dso *dso = map__dso(ms->map); struct symbol *sym = ms->sym; struct rb_root source_line = RB_ROOT; int err; - err = symbol__annotate(ms, evsel, opts, NULL); + err = symbol__annotate(ms, evsel, NULL); if (err) { char msg[BUFSIZ]; @@ -2979,13 +3054,13 @@ int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel, symbol__calc_percent(sym, evsel); - if (opts->print_lines) { - srcline_full_filename = opts->full_path; - symbol__calc_lines(ms, &source_line, opts); + if (annotate_opts.print_lines) { + srcline_full_filename = annotate_opts.full_path; + symbol__calc_lines(ms, &source_line); print_summary(&source_line, dso->long_name); } - symbol__annotate_printf(ms, evsel, opts); + symbol__annotate_printf(ms, evsel); annotated_source__purge(symbol__annotation(sym)->src); @@ -3046,19 +3121,20 @@ call_like: obj__printf(obj, " "); } - disasm_line__scnprintf(dl, bf, size, !notes->options->use_offset, notes->widths.max_ins_name); + disasm_line__scnprintf(dl, bf, size, !annotate_opts.use_offset, notes->widths.max_ins_name); } static void ipc_coverage_string(char *bf, int size, struct annotation *notes) { double ipc = 0.0, coverage = 0.0; + struct annotated_branch *branch = annotation__get_branch(notes); - if (notes->hit_cycles) - ipc = notes->hit_insn / ((double)notes->hit_cycles); + if (branch && branch->hit_cycles) + ipc = branch->hit_insn / ((double)branch->hit_cycles); - if (notes->total_insn) { - coverage = notes->cover_insn * 100.0 / - ((double)notes->total_insn); + if (branch && branch->total_insn) { + coverage = branch->cover_insn * 100.0 / + ((double)branch->total_insn); } scnprintf(bf, size, "(Average IPC: %.2f, IPC Coverage: %.1f%%)", @@ -3083,8 +3159,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati int printed; if (first_line && (al->offset == -1 || percent_max == 0.0)) { - if (notes->have_cycles) { - if (al->ipc == 0.0 && al->cycles == 0) + if (notes->branch && al->cycles) { + if (al->cycles->ipc == 0.0 && al->cycles->avg == 0) show_title = true; } else show_title = true; @@ -3120,18 +3196,18 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati } } - if (notes->have_cycles) { - if (al->ipc) - obj__printf(obj, "%*.2f ", ANNOTATION__IPC_WIDTH - 1, al->ipc); + if (notes->branch) { + if (al->cycles && al->cycles->ipc) + obj__printf(obj, "%*.2f ", ANNOTATION__IPC_WIDTH - 1, al->cycles->ipc); else if (!show_title) obj__printf(obj, "%*s", ANNOTATION__IPC_WIDTH, " "); else obj__printf(obj, "%*s ", ANNOTATION__IPC_WIDTH - 1, "IPC"); - if (!notes->options->show_minmax_cycle) { - if (al->cycles) + if (!annotate_opts.show_minmax_cycle) { + if (al->cycles && al->cycles->avg) obj__printf(obj, "%*" PRIu64 " ", - ANNOTATION__CYCLES_WIDTH - 1, al->cycles); + ANNOTATION__CYCLES_WIDTH - 1, al->cycles->avg); else if (!show_title) obj__printf(obj, "%*s", ANNOTATION__CYCLES_WIDTH, " "); @@ -3145,8 +3221,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati scnprintf(str, sizeof(str), "%" PRIu64 "(%" PRIu64 "/%" PRIu64 ")", - al->cycles, al->cycles_min, - al->cycles_max); + al->cycles->avg, al->cycles->min, + al->cycles->max); obj__printf(obj, "%*s ", ANNOTATION__MINMAX_CYCLES_WIDTH - 1, @@ -3172,7 +3248,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati if (!*al->line) obj__printf(obj, "%-*s", width - pcnt_width - cycles_width, " "); else if (al->offset == -1) { - if (al->line_nr && notes->options->show_linenr) + if (al->line_nr && annotate_opts.show_linenr) printed = scnprintf(bf, sizeof(bf), "%-*d ", notes->widths.addr + 1, al->line_nr); else printed = scnprintf(bf, sizeof(bf), "%-*s ", notes->widths.addr, " "); @@ -3182,15 +3258,15 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati u64 addr = al->offset; int color = -1; - if (!notes->options->use_offset) + if (!annotate_opts.use_offset) addr += notes->start; - if (!notes->options->use_offset) { + if (!annotate_opts.use_offset) { printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr); } else { if (al->jump_sources && - notes->options->offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) { - if (notes->options->show_nr_jumps) { + annotate_opts.offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) { + if (annotate_opts.show_nr_jumps) { int prev; printed = scnprintf(bf, sizeof(bf), "%*d ", notes->widths.jumps, @@ -3204,9 +3280,9 @@ print_addr: printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ", notes->widths.target, addr); } else if (ins__is_call(&disasm_line(al)->ins) && - notes->options->offset_level >= ANNOTATION__OFFSET_CALL) { + annotate_opts.offset_level >= ANNOTATION__OFFSET_CALL) { goto print_addr; - } else if (notes->options->offset_level == ANNOTATION__MAX_OFFSET_LEVEL) { + } else if (annotate_opts.offset_level == ANNOTATION__MAX_OFFSET_LEVEL) { goto print_addr; } else { printed = scnprintf(bf, sizeof(bf), "%-*s ", @@ -3228,43 +3304,44 @@ print_addr: } void annotation_line__write(struct annotation_line *al, struct annotation *notes, - struct annotation_write_ops *wops, - struct annotation_options *opts) + struct annotation_write_ops *wops) { __annotation_line__write(al, notes, wops->first_line, wops->current_entry, wops->change_color, wops->width, wops->obj, - opts->percent_type, + annotate_opts.percent_type, wops->set_color, wops->set_percent_color, wops->set_jumps_percent_color, wops->printf, wops->write_graph); } int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, - struct annotation_options *options, struct arch **parch) + struct arch **parch) { struct symbol *sym = ms->sym; struct annotation *notes = symbol__annotation(sym); size_t size = symbol__size(sym); int nr_pcnt = 1, err; - notes->offsets = zalloc(size * sizeof(struct annotation_line *)); - if (notes->offsets == NULL) + notes->src->offsets = zalloc(size * sizeof(struct annotation_line *)); + if (notes->src->offsets == NULL) return ENOMEM; if (evsel__is_group_event(evsel)) nr_pcnt = evsel->core.nr_members; - err = symbol__annotate(ms, evsel, options, parch); + err = symbol__annotate(ms, evsel, parch); if (err) goto out_free_offsets; - notes->options = options; - symbol__calc_percent(sym, evsel); annotation__set_offsets(notes, size); annotation__mark_jump_targets(notes, sym); - annotation__compute_ipc(notes, size); + + err = annotation__compute_ipc(notes, size); + if (err) + goto out_free_offsets; + annotation__init_column_widths(notes, sym); notes->nr_events = nr_pcnt; @@ -3274,7 +3351,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, return 0; out_free_offsets: - zfree(¬es->offsets); + zfree(¬es->src->offsets); return err; } @@ -3337,8 +3414,10 @@ static int annotation__config(const char *var, const char *value, void *data) return 0; } -void annotation_options__init(struct annotation_options *opt) +void annotation_options__init(void) { + struct annotation_options *opt = &annotate_opts; + memset(opt, 0, sizeof(*opt)); /* Default values. */ @@ -3349,16 +3428,15 @@ void annotation_options__init(struct annotation_options *opt) opt->percent_type = PERCENT_PERIOD_LOCAL; } - -void annotation_options__exit(struct annotation_options *opt) +void annotation_options__exit(void) { - zfree(&opt->disassembler_style); - zfree(&opt->objdump_path); + zfree(&annotate_opts.disassembler_style); + zfree(&annotate_opts.objdump_path); } -void annotation_config__init(struct annotation_options *opt) +void annotation_config__init(void) { - perf_config(annotation__config, opt); + perf_config(annotation__config, &annotate_opts); } static unsigned int parse_percent_type(char *str1, char *str2) @@ -3382,10 +3460,9 @@ static unsigned int parse_percent_type(char *str1, char *str2) return type; } -int annotate_parse_percent_type(const struct option *opt, const char *_str, +int annotate_parse_percent_type(const struct option *opt __maybe_unused, const char *_str, int unset __maybe_unused) { - struct annotation_options *opts = opt->value; unsigned int type; char *str1, *str2; int err = -1; @@ -3404,7 +3481,7 @@ int annotate_parse_percent_type(const struct option *opt, const char *_str, if (type == (unsigned int) -1) type = parse_percent_type(str2, str1); if (type != (unsigned int) -1) { - opts->percent_type = type; + annotate_opts.percent_type = type; err = 0; } @@ -3413,8 +3490,10 @@ out: return err; } -int annotate_check_args(struct annotation_options *args) +int annotate_check_args(void) { + struct annotation_options *args = &annotate_opts; + if (args->prefix_strip && !args->prefix) { pr_err("--prefix-strip requires --prefix\n"); return -1; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 962780559176..589f8aaf0236 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -31,8 +31,6 @@ struct ins { struct ins_operands { char *raw; - char *raw_comment; - char *raw_func_start; struct { char *raw; char *name; @@ -41,17 +39,23 @@ struct ins_operands { s64 offset; bool offset_avail; bool outside; + bool multi_regs; } target; union { struct { char *raw; char *name; u64 addr; + bool multi_regs; } source; struct { struct ins ins; struct ins_operands *ops; } locked; + struct { + char *raw_comment; + char *raw_func_start; + } jump; }; }; @@ -101,6 +105,8 @@ struct annotation_options { unsigned int percent_type; }; +extern struct annotation_options annotate_opts; + enum { ANNOTATION__OFFSET_JUMP_TARGETS = 1, ANNOTATION__OFFSET_CALL, @@ -130,6 +136,13 @@ struct annotation_data { struct sym_hist_entry he; }; +struct cycles_info { + float ipc; + u64 avg; + u64 max; + u64 min; +}; + struct annotation_line { struct list_head node; struct rb_node rb_node; @@ -137,12 +150,9 @@ struct annotation_line { char *line; int line_nr; char *fileloc; - int jump_sources; - float ipc; - u64 cycles; - u64 cycles_max; - u64 cycles_min; char *path; + struct cycles_info *cycles; + int jump_sources; u32 idx; int idx_asm; int data_nr; @@ -214,8 +224,7 @@ struct annotation_write_ops { }; void annotation_line__write(struct annotation_line *al, struct annotation *notes, - struct annotation_write_ops *ops, - struct annotation_options *opts); + struct annotation_write_ops *ops); int __annotation__scnprintf_samples_period(struct annotation *notes, char *bf, size_t size, @@ -264,27 +273,29 @@ struct cyc_hist { * returns. */ struct annotated_source { - struct list_head source; - int nr_histograms; - size_t sizeof_sym_hist; - struct cyc_hist *cycles_hist; - struct sym_hist *histograms; + struct list_head source; + size_t sizeof_sym_hist; + struct sym_hist *histograms; + struct annotation_line **offsets; + int nr_histograms; + int nr_entries; + int nr_asm_entries; + u16 max_line_len; }; -struct LOCKABLE annotation { - u64 max_coverage; - u64 start; +struct annotated_branch { u64 hit_cycles; u64 hit_insn; unsigned int total_insn; unsigned int cover_insn; - struct annotation_options *options; - struct annotation_line **offsets; + struct cyc_hist *cycles_hist; + u64 max_coverage; +}; + +struct LOCKABLE annotation { + u64 start; int nr_events; int max_jump_sources; - int nr_entries; - int nr_asm_entries; - u16 max_line_len; struct { u8 addr; u8 jumps; @@ -293,8 +304,8 @@ struct LOCKABLE annotation { u8 max_addr; u8 max_ins_name; } widths; - bool have_cycles; struct annotated_source *src; + struct annotated_branch *branch; }; static inline void annotation__init(struct annotation *notes __maybe_unused) @@ -308,10 +319,10 @@ bool annotation__trylock(struct annotation *notes) EXCLUSIVE_TRYLOCK_FUNCTION(tr static inline int annotation__cycles_width(struct annotation *notes) { - if (notes->have_cycles && notes->options->show_minmax_cycle) + if (notes->branch && annotate_opts.show_minmax_cycle) return ANNOTATION__IPC_WIDTH + ANNOTATION__MINMAX_CYCLES_WIDTH; - return notes->have_cycles ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0; + return notes->branch ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0; } static inline int annotation__pcnt_width(struct annotation *notes) @@ -319,13 +330,12 @@ static inline int annotation__pcnt_width(struct annotation *notes) return (symbol_conf.show_total_period ? 12 : 7) * notes->nr_events; } -static inline bool annotation_line__filter(struct annotation_line *al, struct annotation *notes) +static inline bool annotation_line__filter(struct annotation_line *al) { - return notes->options->hide_src_code && al->offset == -1; + return annotate_opts.hide_src_code && al->offset == -1; } void annotation__set_offsets(struct annotation *notes, s64 size); -void annotation__compute_ipc(struct annotation *notes, size_t size); void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym); void annotation__update_column_widths(struct annotation *notes); void annotation__init_column_widths(struct annotation *notes, struct symbol *sym); @@ -349,6 +359,8 @@ static inline struct annotation *symbol__annotation(struct symbol *sym) int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample, struct evsel *evsel); +struct annotated_branch *annotation__get_branch(struct annotation *notes); + int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, struct addr_map_symbol *start, unsigned cycles); @@ -361,11 +373,9 @@ void symbol__annotate_zero_histograms(struct symbol *sym); int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, - struct annotation_options *options, struct arch **parch); int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, - struct annotation_options *options, struct arch **parch); enum symbol_disassemble_errno { @@ -392,43 +402,39 @@ enum symbol_disassemble_errno { int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen); -int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel, - struct annotation_options *options); +int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel); void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); void annotated_source__purge(struct annotated_source *as); -int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel, - struct annotation_options *opts); +int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel); bool ui__has_annotation(void); -int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts); +int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel); -int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts); +int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel); #ifdef HAVE_SLANG_SUPPORT int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, - struct hist_browser_timer *hbt, - struct annotation_options *opts); + struct hist_browser_timer *hbt); #else static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused, struct evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused, - struct annotation_options *opts __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused) { return 0; } #endif -void annotation_options__init(struct annotation_options *opt); -void annotation_options__exit(struct annotation_options *opt); +void annotation_options__init(void); +void annotation_options__exit(void); -void annotation_config__init(struct annotation_options *opt); +void annotation_config__init(void); int annotate_parse_percent_type(const struct option *opt, const char *_str, int unset); -int annotate_check_args(struct annotation_options *args); +int annotate_check_args(void); #endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index a0368202a746..3684e6009b63 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -174,7 +174,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp, struct evlist *evlist, struct evsel *evsel, int idx) { - bool per_cpu = !perf_cpu_map__empty(evlist->core.user_requested_cpus); + bool per_cpu = !perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus); mp->mmap_needed = evsel->needs_auxtrace_mmap; @@ -648,7 +648,7 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, static int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx) { - bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.user_requested_cpus); + bool per_cpu_mmaps = !perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus); if (per_cpu_mmaps) { struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->core.all_cpus, idx); @@ -1638,6 +1638,9 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts, case 'Z': synth_opts->timeless_decoding = true; break; + case 'T': + synth_opts->use_timestamp = true; + break; case ' ': case ',': break; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 29eb82dff574..55702215a82d 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -99,6 +99,7 @@ enum itrace_period_type { * @remote_access: whether to synthesize remote access events * @mem: whether to synthesize memory events * @timeless_decoding: prefer "timeless" decoding i.e. ignore timestamps + * @use_timestamp: use the timestamp trace as kernel time * @vm_time_correlation: perform VM Time Correlation * @vm_tm_corr_dry_run: VM Time Correlation dry-run * @vm_tm_corr_args: VM Time Correlation implementation-specific arguments @@ -146,6 +147,7 @@ struct itrace_synth_opts { bool remote_access; bool mem; bool timeless_decoding; + bool use_timestamp; bool vm_time_correlation; bool vm_tm_corr_dry_run; char *vm_tm_corr_args; @@ -678,6 +680,7 @@ bool auxtrace__evsel_is_auxtrace(struct perf_session *session, " q: quicker (less detailed) decoding\n" \ " A: approximate IPC\n" \ " Z: prefer to ignore timestamps (so-called \"timeless\" decoding)\n" \ +" T: use the timestamp trace as kernel time\n" \ " PERIOD[ns|us|ms|i|t]: specify period to sample stream\n" \ " concatenate multiple options. Default is iybxwpe or cewp\n" diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c index 591fc1edd385..dec910989701 100644 --- a/tools/perf/util/block-info.c +++ b/tools/perf/util/block-info.c @@ -129,9 +129,9 @@ int block_info__process_sym(struct hist_entry *he, struct block_hist *bh, al.sym = he->ms.sym; notes = symbol__annotation(he->ms.sym); - if (!notes || !notes->src || !notes->src->cycles_hist) + if (!notes || !notes->branch || !notes->branch->cycles_hist) return 0; - ch = notes->src->cycles_hist; + ch = notes->branch->cycles_hist; for (unsigned int i = 0; i < symbol__size(he->ms.sym); i++) { if (ch[i].num_aggr) { struct block_info *bi; @@ -464,8 +464,7 @@ void block_info__free_report(struct block_report *reps, int nr_reps) } int report__browse_block_hists(struct block_hist *bh, float min_percent, - struct evsel *evsel, struct perf_env *env, - struct annotation_options *annotation_opts) + struct evsel *evsel, struct perf_env *env) { int ret; @@ -477,8 +476,7 @@ int report__browse_block_hists(struct block_hist *bh, float min_percent, return 0; case 1: symbol_conf.report_individual_block = true; - ret = block_hists_tui_browse(bh, evsel, min_percent, - env, annotation_opts); + ret = block_hists_tui_browse(bh, evsel, min_percent, env); return ret; default: return -1; diff --git a/tools/perf/util/block-info.h b/tools/perf/util/block-info.h index 42e9dcc4cf0a..96f53e89795e 100644 --- a/tools/perf/util/block-info.h +++ b/tools/perf/util/block-info.h @@ -78,8 +78,7 @@ struct block_report *block_info__create_report(struct evlist *evlist, void block_info__free_report(struct block_report *reps, int nr_reps); int report__browse_block_hists(struct block_hist *bh, float min_percent, - struct evsel *evsel, struct perf_env *env, - struct annotation_options *annotation_opts); + struct evsel *evsel, struct perf_env *env); float block_info__total_cycles_percent(struct hist_entry *he); diff --git a/tools/perf/util/block-range.c b/tools/perf/util/block-range.c index 680e92774d0c..15c42196c24c 100644 --- a/tools/perf/util/block-range.c +++ b/tools/perf/util/block-range.c @@ -311,6 +311,7 @@ done: double block_range__coverage(struct block_range *br) { struct symbol *sym; + struct annotated_branch *branch; if (!br) { if (block_ranges.blocks) @@ -323,5 +324,9 @@ double block_range__coverage(struct block_range *br) if (!sym) return -1; - return (double)br->coverage / symbol__annotation(sym)->max_coverage; + branch = symbol__annotation(sym)->branch; + if (!branch) + return -1; + + return (double)br->coverage / branch->max_coverage; } diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 38fcf3ba5749..830711cae30d 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -386,6 +386,9 @@ int perf_event__synthesize_bpf_events(struct perf_session *session, int err; int fd; + if (opts->no_bpf_event) + return 0; + event = malloc(sizeof(event->bpf) + KSYM_NAME_LEN + machine->id_hdr_size); if (!event) return -1; diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index 7f9b0e46e008..7a8af60e0f51 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -455,7 +455,7 @@ static int bperf__load(struct evsel *evsel, struct target *target) return -1; if (!all_cpu_map) { - all_cpu_map = perf_cpu_map__new(NULL); + all_cpu_map = perf_cpu_map__new_online_cpus(); if (!all_cpu_map) return -1; } diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h index 0cd3369af2a4..b29109cd3609 100644 --- a/tools/perf/util/compress.h +++ b/tools/perf/util/compress.h @@ -3,6 +3,8 @@ #define PERF_COMPRESS_H #include <stdbool.h> +#include <stddef.h> +#include <sys/types.h> #ifdef HAVE_ZSTD_SUPPORT #include <zstd.h> #endif @@ -21,6 +23,7 @@ struct zstd_data { #ifdef HAVE_ZSTD_SUPPORT ZSTD_CStream *cstream; ZSTD_DStream *dstream; + int comp_level; #endif }; @@ -29,7 +32,7 @@ struct zstd_data { int zstd_init(struct zstd_data *data, int level); int zstd_fini(struct zstd_data *data); -size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size, +ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size, void *src, size_t src_size, size_t max_record_size, size_t process_header(void *record, size_t increment)); @@ -48,7 +51,7 @@ static inline int zstd_fini(struct zstd_data *data __maybe_unused) } static inline -size_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused, +ssize_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused, void *dst __maybe_unused, size_t dst_size __maybe_unused, void *src __maybe_unused, size_t src_size __maybe_unused, size_t max_record_size __maybe_unused, diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 0e090e8bc334..0581ee0fa5f2 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -672,7 +672,7 @@ struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */ static struct perf_cpu_map *online; if (!online) - online = perf_cpu_map__new(NULL); /* from /sys/devices/system/cpu/online */ + online = perf_cpu_map__new_online_cpus(); /* from /sys/devices/system/cpu/online */ return online; } diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c index 81cfc85f4668..8bbeb2dc76fd 100644 --- a/tools/perf/util/cputopo.c +++ b/tools/perf/util/cputopo.c @@ -267,7 +267,7 @@ struct cpu_topology *cpu_topology__new(void) ncpus = cpu__max_present_cpu().cpu; /* build online CPU map */ - map = perf_cpu_map__new(NULL); + map = perf_cpu_map__new_online_cpus(); if (map == NULL) { pr_debug("failed to get system cpumap\n"); return NULL; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index a9873d14c632..d65d7485886c 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -3346,12 +3346,27 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, etm->metadata = metadata; etm->auxtrace_type = auxtrace_info->type; - /* Use virtual timestamps if all ETMs report ts_source = 1 */ - etm->has_virtual_ts = cs_etm__has_virtual_ts(metadata, num_cpu); + if (etm->synth_opts.use_timestamp) + /* + * Prior to Armv8.4, Arm CPUs don't support FEAT_TRF feature, + * therefore the decoder cannot know if the timestamp trace is + * same with the kernel time. + * + * If a user has knowledge for the working platform and can + * specify itrace option 'T' to tell decoder to forcely use the + * traced timestamp as the kernel time. + */ + etm->has_virtual_ts = true; + else + /* Use virtual timestamps if all ETMs report ts_source = 1 */ + etm->has_virtual_ts = cs_etm__has_virtual_ts(metadata, num_cpu); if (!etm->has_virtual_ts) ui__warning("Virtual timestamps are not enabled, or not supported by the traced system.\n" - "The time field of the samples will not be set accurately.\n\n"); + "The time field of the samples will not be set accurately.\n" + "For Arm CPUs prior to Armv8.4 or without support FEAT_TRF,\n" + "you can specify the itrace option 'T' for timestamp decoding\n" + "if the Coresight timestamp on the platform is same with the kernel time.\n\n"); etm->auxtrace.process_event = cs_etm__process_event; etm->auxtrace.process_auxtrace_event = cs_etm__process_auxtrace_event; diff --git a/tools/perf/util/debuginfo.c b/tools/perf/util/debuginfo.c new file mode 100644 index 000000000000..19acf4775d35 --- /dev/null +++ b/tools/perf/util/debuginfo.c @@ -0,0 +1,205 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * DWARF debug information handling code. Copied from probe-finder.c. + * + * Written by Masami Hiramatsu <mhiramat@redhat.com> + */ + +#include <errno.h> +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <linux/zalloc.h> + +#include "build-id.h" +#include "dso.h" +#include "debug.h" +#include "debuginfo.h" +#include "symbol.h" + +#ifdef HAVE_DEBUGINFOD_SUPPORT +#include <elfutils/debuginfod.h> +#endif + +/* Dwarf FL wrappers */ +static char *debuginfo_path; /* Currently dummy */ + +static const Dwfl_Callbacks offline_callbacks = { + .find_debuginfo = dwfl_standard_find_debuginfo, + .debuginfo_path = &debuginfo_path, + + .section_address = dwfl_offline_section_address, + + /* We use this table for core files too. */ + .find_elf = dwfl_build_id_find_elf, +}; + +/* Get a Dwarf from offline image */ +static int debuginfo__init_offline_dwarf(struct debuginfo *dbg, + const char *path) +{ + GElf_Addr dummy; + int fd; + + fd = open(path, O_RDONLY); + if (fd < 0) + return fd; + + dbg->dwfl = dwfl_begin(&offline_callbacks); + if (!dbg->dwfl) + goto error; + + dwfl_report_begin(dbg->dwfl); + dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd); + if (!dbg->mod) + goto error; + + dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias); + if (!dbg->dbg) + goto error; + + dwfl_module_build_id(dbg->mod, &dbg->build_id, &dummy); + + dwfl_report_end(dbg->dwfl, NULL, NULL); + + return 0; +error: + if (dbg->dwfl) + dwfl_end(dbg->dwfl); + else + close(fd); + memset(dbg, 0, sizeof(*dbg)); + + return -ENOENT; +} + +static struct debuginfo *__debuginfo__new(const char *path) +{ + struct debuginfo *dbg = zalloc(sizeof(*dbg)); + if (!dbg) + return NULL; + + if (debuginfo__init_offline_dwarf(dbg, path) < 0) + zfree(&dbg); + if (dbg) + pr_debug("Open Debuginfo file: %s\n", path); + return dbg; +} + +enum dso_binary_type distro_dwarf_types[] = { + DSO_BINARY_TYPE__FEDORA_DEBUGINFO, + DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, + DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, + DSO_BINARY_TYPE__BUILDID_DEBUGINFO, + DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO, + DSO_BINARY_TYPE__NOT_FOUND, +}; + +struct debuginfo *debuginfo__new(const char *path) +{ + enum dso_binary_type *type; + char buf[PATH_MAX], nil = '\0'; + struct dso *dso; + struct debuginfo *dinfo = NULL; + struct build_id bid; + + /* Try to open distro debuginfo files */ + dso = dso__new(path); + if (!dso) + goto out; + + /* Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO */ + if (is_regular_file(path) && filename__read_build_id(path, &bid) > 0) + dso__set_build_id(dso, &bid); + + for (type = distro_dwarf_types; + !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND; + type++) { + if (dso__read_binary_type_filename(dso, *type, &nil, + buf, PATH_MAX) < 0) + continue; + dinfo = __debuginfo__new(buf); + } + dso__put(dso); + +out: + /* if failed to open all distro debuginfo, open given binary */ + return dinfo ? : __debuginfo__new(path); +} + +void debuginfo__delete(struct debuginfo *dbg) +{ + if (dbg) { + if (dbg->dwfl) + dwfl_end(dbg->dwfl); + free(dbg); + } +} + +/* For the kernel module, we need a special code to get a DIE */ +int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs, + bool adjust_offset) +{ + int n, i; + Elf32_Word shndx; + Elf_Scn *scn; + Elf *elf; + GElf_Shdr mem, *shdr; + const char *p; + + elf = dwfl_module_getelf(dbg->mod, &dbg->bias); + if (!elf) + return -EINVAL; + + /* Get the number of relocations */ + n = dwfl_module_relocations(dbg->mod); + if (n < 0) + return -ENOENT; + /* Search the relocation related .text section */ + for (i = 0; i < n; i++) { + p = dwfl_module_relocation_info(dbg->mod, i, &shndx); + if (strcmp(p, ".text") == 0) { + /* OK, get the section header */ + scn = elf_getscn(elf, shndx); + if (!scn) + return -ENOENT; + shdr = gelf_getshdr(scn, &mem); + if (!shdr) + return -ENOENT; + *offs = shdr->sh_addr; + if (adjust_offset) + *offs -= shdr->sh_offset; + } + } + return 0; +} + +#ifdef HAVE_DEBUGINFOD_SUPPORT +int get_source_from_debuginfod(const char *raw_path, + const char *sbuild_id, char **new_path) +{ + debuginfod_client *c = debuginfod_begin(); + const char *p = raw_path; + int fd; + + if (!c) + return -ENOMEM; + + fd = debuginfod_find_source(c, (const unsigned char *)sbuild_id, + 0, p, new_path); + pr_debug("Search %s from debuginfod -> %d\n", p, fd); + if (fd >= 0) + close(fd); + debuginfod_end(c); + if (fd < 0) { + pr_debug("Failed to find %s in debuginfod (%s)\n", + raw_path, sbuild_id); + return -ENOENT; + } + pr_debug("Got a source %s\n", *new_path); + + return 0; +} +#endif /* HAVE_DEBUGINFOD_SUPPORT */ diff --git a/tools/perf/util/debuginfo.h b/tools/perf/util/debuginfo.h new file mode 100644 index 000000000000..4d65b8c605fc --- /dev/null +++ b/tools/perf/util/debuginfo.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _PERF_DEBUGINFO_H +#define _PERF_DEBUGINFO_H + +#include <errno.h> +#include <linux/compiler.h> + +#ifdef HAVE_DWARF_SUPPORT + +#include "dwarf-aux.h" + +/* debug information structure */ +struct debuginfo { + Dwarf *dbg; + Dwfl_Module *mod; + Dwfl *dwfl; + Dwarf_Addr bias; + const unsigned char *build_id; +}; + +/* This also tries to open distro debuginfo */ +struct debuginfo *debuginfo__new(const char *path); +void debuginfo__delete(struct debuginfo *dbg); + +int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs, + bool adjust_offset); + +#else /* HAVE_DWARF_SUPPORT */ + +/* dummy debug information structure */ +struct debuginfo { +}; + +static inline struct debuginfo *debuginfo__new(const char *path __maybe_unused) +{ + return NULL; +} + +static inline void debuginfo__delete(struct debuginfo *dbg __maybe_unused) +{ +} + +static inline int debuginfo__get_text_offset(struct debuginfo *dbg __maybe_unused, + Dwarf_Addr *offs __maybe_unused, + bool adjust_offset __maybe_unused) +{ + return -EINVAL; +} + +#endif /* HAVE_DWARF_SUPPORT */ + +#ifdef HAVE_DEBUGINFOD_SUPPORT +int get_source_from_debuginfod(const char *raw_path, const char *sbuild_id, + char **new_path); +#else /* HAVE_DEBUGINFOD_SUPPORT */ +static inline int get_source_from_debuginfod(const char *raw_path __maybe_unused, + const char *sbuild_id __maybe_unused, + char **new_path __maybe_unused) +{ + return -ENOTSUP; +} +#endif /* HAVE_DEBUGINFOD_SUPPORT */ + +#endif /* _PERF_DEBUGINFO_H */ diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 2941d88f2199..edd9e407bc74 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -1090,7 +1090,14 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf) return strbuf_addf(buf, "%s%s", tmp, name ?: ""); } ret = die_get_typename(&type, buf); - return ret ? ret : strbuf_addstr(buf, tmp); + if (ret < 0) { + /* void pointer has no type attribute */ + if (tag == DW_TAG_pointer_type && ret == -ENOENT) + return strbuf_addf(buf, "void*"); + + return ret; + } + return strbuf_addstr(buf, tmp); } /** @@ -1238,12 +1245,151 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf) out: return ret; } -#else -int die_get_var_range(Dwarf_Die *sp_die __maybe_unused, - Dwarf_Die *vr_die __maybe_unused, - struct strbuf *buf __maybe_unused) + +/* Interval parameters for __die_find_var_reg_cb() */ +struct find_var_data { + /* Target instruction address */ + Dwarf_Addr pc; + /* Target memory address (for global data) */ + Dwarf_Addr addr; + /* Target register */ + unsigned reg; + /* Access offset, set for global data */ + int offset; +}; + +/* Max number of registers DW_OP_regN supports */ +#define DWARF_OP_DIRECT_REGS 32 + +/* Only checks direct child DIEs in the given scope. */ +static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg) { - return -ENOTSUP; + struct find_var_data *data = arg; + int tag = dwarf_tag(die_mem); + ptrdiff_t off = 0; + Dwarf_Attribute attr; + Dwarf_Addr base, start, end; + Dwarf_Op *ops; + size_t nops; + + if (tag != DW_TAG_variable && tag != DW_TAG_formal_parameter) + return DIE_FIND_CB_SIBLING; + + if (dwarf_attr(die_mem, DW_AT_location, &attr) == NULL) + return DIE_FIND_CB_SIBLING; + + while ((off = dwarf_getlocations(&attr, off, &base, &start, &end, &ops, &nops)) > 0) { + /* Assuming the location list is sorted by address */ + if (end < data->pc) + continue; + if (start > data->pc) + break; + + /* Only match with a simple case */ + if (data->reg < DWARF_OP_DIRECT_REGS) { + if (ops->atom == (DW_OP_reg0 + data->reg) && nops == 1) + return DIE_FIND_CB_END; + } else { + if (ops->atom == DW_OP_regx && ops->number == data->reg && + nops == 1) + return DIE_FIND_CB_END; + } + } + return DIE_FIND_CB_SIBLING; +} + +/** + * die_find_variable_by_reg - Find a variable saved in a register + * @sc_die: a scope DIE + * @pc: the program address to find + * @reg: the register number to find + * @die_mem: a buffer to save the resulting DIE + * + * Find the variable DIE accessed by the given register. + */ +Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg, + Dwarf_Die *die_mem) +{ + struct find_var_data data = { + .pc = pc, + .reg = reg, + }; + return die_find_child(sc_die, __die_find_var_reg_cb, &data, die_mem); +} + +/* Only checks direct child DIEs in the given scope */ +static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg) +{ + struct find_var_data *data = arg; + int tag = dwarf_tag(die_mem); + ptrdiff_t off = 0; + Dwarf_Attribute attr; + Dwarf_Addr base, start, end; + Dwarf_Word size; + Dwarf_Die type_die; + Dwarf_Op *ops; + size_t nops; + + if (tag != DW_TAG_variable) + return DIE_FIND_CB_SIBLING; + + if (dwarf_attr(die_mem, DW_AT_location, &attr) == NULL) + return DIE_FIND_CB_SIBLING; + + while ((off = dwarf_getlocations(&attr, off, &base, &start, &end, &ops, &nops)) > 0) { + if (ops->atom != DW_OP_addr) + continue; + + if (data->addr < ops->number) + continue; + + if (data->addr == ops->number) { + /* Update offset relative to the start of the variable */ + data->offset = 0; + return DIE_FIND_CB_END; + } + + if (die_get_real_type(die_mem, &type_die) == NULL) + continue; + + if (dwarf_aggregate_size(&type_die, &size) < 0) + continue; + + if (data->addr >= ops->number + size) + continue; + + /* Update offset relative to the start of the variable */ + data->offset = data->addr - ops->number; + return DIE_FIND_CB_END; + } + return DIE_FIND_CB_SIBLING; +} + +/** + * die_find_variable_by_addr - Find variable located at given address + * @sc_die: a scope DIE + * @pc: the program address to find + * @addr: the data address to find + * @die_mem: a buffer to save the resulting DIE + * @offset: the offset in the resulting type + * + * Find the variable DIE located at the given address (in PC-relative mode). + * This is usually for global variables. + */ +Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc, + Dwarf_Addr addr, Dwarf_Die *die_mem, + int *offset) +{ + struct find_var_data data = { + .pc = pc, + .addr = addr, + }; + Dwarf_Die *result; + + result = die_find_child(sc_die, __die_find_var_addr_cb, &data, die_mem); + if (result) + *offset = data.offset; + return result; } #endif @@ -1425,3 +1571,56 @@ void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die, *entrypc = postprologue_addr; } + +/* Internal parameters for __die_find_scope_cb() */ +struct find_scope_data { + /* Target instruction address */ + Dwarf_Addr pc; + /* Number of scopes found [output] */ + int nr; + /* Array of scopes found, 0 for the outermost one. [output] */ + Dwarf_Die *scopes; +}; + +static int __die_find_scope_cb(Dwarf_Die *die_mem, void *arg) +{ + struct find_scope_data *data = arg; + + if (dwarf_haspc(die_mem, data->pc)) { + Dwarf_Die *tmp; + + tmp = realloc(data->scopes, (data->nr + 1) * sizeof(*tmp)); + if (tmp == NULL) + return DIE_FIND_CB_END; + + memcpy(tmp + data->nr, die_mem, sizeof(*die_mem)); + data->scopes = tmp; + data->nr++; + return DIE_FIND_CB_CHILD; + } + return DIE_FIND_CB_SIBLING; +} + +/** + * die_get_scopes - Return a list of scopes including the address + * @cu_die: a compile unit DIE + * @pc: the address to find + * @scopes: the array of DIEs for scopes (result) + * + * This function does the same as the dwarf_getscopes() but doesn't follow + * the origins of inlined functions. It returns the number of scopes saved + * in the @scopes argument. The outer scope will be saved first (index 0) and + * the last one is the innermost scope at the @pc. + */ +int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes) +{ + struct find_scope_data data = { + .pc = pc, + }; + Dwarf_Die die_mem; + + die_find_child(cu_die, __die_find_scope_cb, &data, &die_mem); + + *scopes = data.scopes; + return data.nr; +} diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index 7ec8bc1083bb..0ddf61fd3f8b 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -121,7 +121,6 @@ int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf); /* Get the name and type of given variable DIE, stored as "type\tname" */ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf); -int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf); /* Check if target program is compiled with optimization */ bool die_is_optimized_target(Dwarf_Die *cu_die); @@ -130,4 +129,49 @@ bool die_is_optimized_target(Dwarf_Die *cu_die); void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die, Dwarf_Addr *entrypc); -#endif +/* Get the list of including scopes */ +int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes); + +#ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT + +/* Get byte offset range of given variable DIE */ +int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf); + +/* Find a variable saved in the 'reg' at given address */ +Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg, + Dwarf_Die *die_mem); + +/* Find a (global) variable located in the 'addr' */ +Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc, + Dwarf_Addr addr, Dwarf_Die *die_mem, + int *offset); + +#else /* HAVE_DWARF_GETLOCATIONS_SUPPORT */ + +static inline int die_get_var_range(Dwarf_Die *sp_die __maybe_unused, + Dwarf_Die *vr_die __maybe_unused, + struct strbuf *buf __maybe_unused) +{ + return -ENOTSUP; +} + +static inline Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die __maybe_unused, + Dwarf_Addr pc __maybe_unused, + int reg __maybe_unused, + Dwarf_Die *die_mem __maybe_unused) +{ + return NULL; +} + +static inline Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die __maybe_unused, + Dwarf_Addr pc __maybe_unused, + Dwarf_Addr addr __maybe_unused, + Dwarf_Die *die_mem __maybe_unused, + int *offset __maybe_unused) +{ + return NULL; +} + +#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */ + +#endif /* _DWARF_AUX_H */ diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 44140b7f596a..c68b7a004f29 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -3,6 +3,7 @@ #include "debug.h" #include "env.h" #include "util/header.h" +#include "linux/compiler.h" #include <linux/ctype.h> #include <linux/zalloc.h> #include "cgroup.h" @@ -12,6 +13,7 @@ #include <string.h> #include "pmus.h" #include "strbuf.h" +#include "trace/beauty/beauty.h" struct perf_env perf_env; @@ -453,6 +455,18 @@ const char *perf_env__arch(struct perf_env *env) return normalize_arch(arch_name); } +const char *perf_env__arch_strerrno(struct perf_env *env __maybe_unused, int err __maybe_unused) +{ +#if defined(HAVE_SYSCALL_TABLE_SUPPORT) && defined(HAVE_LIBTRACEEVENT) + if (env->arch_strerrno == NULL) + env->arch_strerrno = arch_syscalls__strerrno_function(perf_env__arch(env)); + + return env->arch_strerrno ? env->arch_strerrno(err) : "no arch specific strerrno function"; +#else + return "!(HAVE_SYSCALL_TABLE_SUPPORT && HAVE_LIBTRACEEVENT)"; +#endif +} + const char *perf_env__cpuid(struct perf_env *env) { int status; @@ -531,6 +545,24 @@ int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu) return cpu.cpu >= 0 && cpu.cpu < env->nr_numa_map ? env->numa_map[cpu.cpu] : -1; } +bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name) +{ + char *pmu_mapping = env->pmu_mappings, *colon; + + for (int i = 0; i < env->nr_pmu_mappings; ++i) { + if (strtoul(pmu_mapping, &colon, 0) == ULONG_MAX || *colon != ':') + goto out_error; + + pmu_mapping = colon + 1; + if (strcmp(pmu_mapping, pmu_name) == 0) + return true; + + pmu_mapping += strlen(pmu_mapping) + 1; + } +out_error: + return false; +} + char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name, const char *cap) { diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 4566c51f2fd9..bf7e3c4c211f 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -46,10 +46,17 @@ struct hybrid_node { struct pmu_caps { int nr_caps; unsigned int max_branches; + unsigned int br_cntr_nr; + unsigned int br_cntr_width; + char **caps; char *pmu_name; }; +typedef const char *(arch_syscalls__strerrno_t)(int err); + +arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch); + struct perf_env { char *hostname; char *os_release; @@ -62,6 +69,8 @@ struct perf_env { unsigned long long total_mem; unsigned int msr_pmu_type; unsigned int max_branches; + unsigned int br_cntr_nr; + unsigned int br_cntr_width; int kernel_is_64_bit; int nr_cmdline; @@ -130,6 +139,7 @@ struct perf_env { */ bool enabled; } clock; + arch_syscalls__strerrno_t *arch_strerrno; }; enum perf_compress_type { @@ -159,6 +169,7 @@ int perf_env__read_cpu_topology_map(struct perf_env *env); void cpu_cache_level__free(struct cpu_cache_level *cache); const char *perf_env__arch(struct perf_env *env); +const char *perf_env__arch_strerrno(struct perf_env *env, int err); const char *perf_env__cpuid(struct perf_env *env); const char *perf_env__raw_arch(struct perf_env *env); int perf_env__nr_cpus_avail(struct perf_env *env); @@ -174,4 +185,6 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id); int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu); char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name, const char *cap); + +bool perf_env__has_pmu_mapping(struct perf_env *env, const char *pmu_name); #endif /* __PERF_ENV_H */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 923c0fb15122..68f45e9e63b6 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -617,13 +617,13 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) { al->level = 'k'; maps = machine__kernel_maps(machine); - load_map = true; + load_map = !symbol_conf.lazy_load_kernel_maps; } else if (cpumode == PERF_RECORD_MISC_USER && perf_host) { al->level = '.'; } else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) { al->level = 'g'; maps = machine__kernel_maps(machine); - load_map = true; + load_map = !symbol_conf.lazy_load_kernel_maps; } else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) { al->level = 'u'; } else { diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index e36da58522ef..95f25e9fb994 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1056,7 +1056,7 @@ int evlist__create_maps(struct evlist *evlist, struct target *target) return -1; if (target__uses_dummy_map(target)) - cpus = perf_cpu_map__dummy_new(); + cpus = perf_cpu_map__new_any_cpu(); else cpus = perf_cpu_map__new(target->cpu_list); @@ -1352,7 +1352,7 @@ static int evlist__create_syswide_maps(struct evlist *evlist) * error, and we may not want to do that fallback to a * default cpu identity map :-\ */ - cpus = perf_cpu_map__new(NULL); + cpus = perf_cpu_map__new_online_cpus(); if (!cpus) goto out; @@ -2518,3 +2518,33 @@ void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_lis } perf_cpu_map__put(user_requested_cpus); } + +void evlist__uniquify_name(struct evlist *evlist) +{ + char *new_name, empty_attributes[2] = ":", *attributes; + struct evsel *pos; + + if (perf_pmus__num_core_pmus() == 1) + return; + + evlist__for_each_entry(evlist, pos) { + if (!evsel__is_hybrid(pos)) + continue; + + if (strchr(pos->name, '/')) + continue; + + attributes = strchr(pos->name, ':'); + if (attributes) + *attributes = '\0'; + else + attributes = empty_attributes; + + if (asprintf(&new_name, "%s/%s/%s", pos->pmu_name, pos->name, attributes + 1)) { + free(pos->name); + pos->name = new_name; + } else { + *attributes = ':'; + } + } +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 98e7ddb2bd30..cb91dc9117a2 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -442,5 +442,6 @@ struct evsel *evlist__find_evsel(struct evlist *evlist, int idx); int evlist__scnprintf_evsels(struct evlist *evlist, size_t size, char *bf); void evlist__check_mem_load_aux(struct evlist *evlist); void evlist__warn_user_requested_cpus(struct evlist *evlist, const char *cpu_list); +void evlist__uniquify_name(struct evlist *evlist); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 72a5dfc38d38..6d7c9c58a9bc 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1801,7 +1801,7 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, if (cpus == NULL) { if (empty_cpu_map == NULL) { - empty_cpu_map = perf_cpu_map__dummy_new(); + empty_cpu_map = perf_cpu_map__new_any_cpu(); if (empty_cpu_map == NULL) return -ENOMEM; } @@ -1832,6 +1832,8 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, static void evsel__disable_missing_features(struct evsel *evsel) { + if (perf_missing_features.branch_counters) + evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_COUNTERS; if (perf_missing_features.read_lost) evsel->core.attr.read_format &= ~PERF_FORMAT_LOST; if (perf_missing_features.weight_struct) { @@ -1885,7 +1887,12 @@ bool evsel__detect_missing_features(struct evsel *evsel) * Must probe features in the order they were added to the * perf_event_attr interface. */ - if (!perf_missing_features.read_lost && + if (!perf_missing_features.branch_counters && + (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) { + perf_missing_features.branch_counters = true; + pr_debug2("switching off branch counters support\n"); + return true; + } else if (!perf_missing_features.read_lost && (evsel->core.attr.read_format & PERF_FORMAT_LOST)) { perf_missing_features.read_lost = true; pr_debug2("switching off PERF_FORMAT_LOST support\n"); @@ -2318,6 +2325,22 @@ u64 evsel__bitfield_swap_branch_flags(u64 value) return new_val; } +static inline bool evsel__has_branch_counters(const struct evsel *evsel) +{ + struct evsel *cur, *leader = evsel__leader(evsel); + + /* The branch counters feature only supports group */ + if (!leader || !evsel->evlist) + return false; + + evlist__for_each_entry(evsel->evlist, cur) { + if ((leader == evsel__leader(cur)) && + (cur->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) + return true; + } + return false; +} + int evsel__parse_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *data) { @@ -2551,6 +2574,16 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, OVERFLOW_CHECK(array, sz, max_size); array = (void *)array + sz; + + if (evsel__has_branch_counters(evsel)) { + OVERFLOW_CHECK_u64(array); + + data->branch_stack_cntr = (u64 *)array; + sz = data->branch_stack->nr * sizeof(u64); + + OVERFLOW_CHECK(array, sz, max_size); + array = (void *)array + sz; + } } if (type & PERF_SAMPLE_REGS_USER) { @@ -2820,7 +2853,8 @@ u64 evsel__intval_common(struct evsel *evsel, struct perf_sample *sample, const #endif -bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize) +bool evsel__fallback(struct evsel *evsel, struct target *target, int err, + char *msg, size_t msgsize) { int paranoid; @@ -2828,18 +2862,19 @@ bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize) evsel->core.attr.type == PERF_TYPE_HARDWARE && evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES) { /* - * If it's cycles then fall back to hrtimer based - * cpu-clock-tick sw counter, which is always available even if - * no PMU support. + * If it's cycles then fall back to hrtimer based cpu-clock sw + * counter, which is always available even if no PMU support. * * PPC returns ENXIO until 2.6.37 (behavior changed with commit * b0a873e). */ - scnprintf(msg, msgsize, "%s", -"The cycles event is not supported, trying to fall back to cpu-clock-ticks"); - evsel->core.attr.type = PERF_TYPE_SOFTWARE; - evsel->core.attr.config = PERF_COUNT_SW_CPU_CLOCK; + evsel->core.attr.config = target__has_cpu(target) + ? PERF_COUNT_SW_CPU_CLOCK + : PERF_COUNT_SW_TASK_CLOCK; + scnprintf(msg, msgsize, + "The cycles event is not supported, trying to fall back to %s", + target__has_cpu(target) ? "cpu-clock" : "task-clock"); zfree(&evsel->name); return true; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d791316a1792..efbb6e848287 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -191,6 +191,7 @@ struct perf_missing_features { bool code_page_size; bool weight_struct; bool read_lost; + bool branch_counters; }; extern struct perf_missing_features perf_missing_features; @@ -459,7 +460,8 @@ static inline bool evsel__is_clock(const struct evsel *evsel) evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK); } -bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize); +bool evsel__fallback(struct evsel *evsel, struct target *target, int err, + char *msg, size_t msgsize); int evsel__open_strerror(struct evsel *evsel, struct target *target, int err, char *msg, size_t size); diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index fefc72066c4e..ac17a3cb59dc 100644 --- a/tools/perf/util/genelf.c +++ b/tools/perf/util/genelf.c @@ -293,9 +293,9 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, */ phdr = elf_newphdr(e, 1); phdr[0].p_type = PT_LOAD; - phdr[0].p_offset = 0; - phdr[0].p_vaddr = 0; - phdr[0].p_paddr = 0; + phdr[0].p_offset = GEN_ELF_TEXT_OFFSET; + phdr[0].p_vaddr = GEN_ELF_TEXT_OFFSET; + phdr[0].p_paddr = GEN_ELF_TEXT_OFFSET; phdr[0].p_filesz = csize; phdr[0].p_memsz = csize; phdr[0].p_flags = PF_X | PF_R; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index e86b9439ffee..a9f71f8343f0 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1444,7 +1444,9 @@ static int build_mem_topology(struct memory_node **nodesp, u64 *cntp) nodes = new_nodes; size += 4; } - ret = memory_node__read(&nodes[cnt++], idx); + ret = memory_node__read(&nodes[cnt], idx); + if (!ret) + cnt += 1; } out: closedir(dir); @@ -2145,6 +2147,14 @@ static void print_pmu_caps(struct feat_fd *ff, FILE *fp) __print_pmu_caps(fp, pmu_caps->nr_caps, pmu_caps->caps, pmu_caps->pmu_name); } + + if (strcmp(perf_env__arch(&ff->ph->env), "x86") == 0 && + perf_env__has_pmu_mapping(&ff->ph->env, "ibs_op")) { + char *max_precise = perf_env__find_pmu_cap(&ff->ph->env, "cpu", "max_precise"); + + if (max_precise != NULL && atoi(max_precise) == 0) + fprintf(fp, "# AMD systems uses ibs_op// PMU for some precise events, e.g.: cycles:p, see the 'perf list' man page for further details.\n"); + } } static void print_pmu_mappings(struct feat_fd *ff, FILE *fp) @@ -3259,7 +3269,9 @@ static int process_compressed(struct feat_fd *ff, } static int __process_pmu_caps(struct feat_fd *ff, int *nr_caps, - char ***caps, unsigned int *max_branches) + char ***caps, unsigned int *max_branches, + unsigned int *br_cntr_nr, + unsigned int *br_cntr_width) { char *name, *value, *ptr; u32 nr_pmu_caps, i; @@ -3294,6 +3306,12 @@ static int __process_pmu_caps(struct feat_fd *ff, int *nr_caps, if (!strcmp(name, "branches")) *max_branches = atoi(value); + if (!strcmp(name, "branch_counter_nr")) + *br_cntr_nr = atoi(value); + + if (!strcmp(name, "branch_counter_width")) + *br_cntr_width = atoi(value); + free(value); free(name); } @@ -3318,7 +3336,9 @@ static int process_cpu_pmu_caps(struct feat_fd *ff, { int ret = __process_pmu_caps(ff, &ff->ph->env.nr_cpu_pmu_caps, &ff->ph->env.cpu_pmu_caps, - &ff->ph->env.max_branches); + &ff->ph->env.max_branches, + &ff->ph->env.br_cntr_nr, + &ff->ph->env.br_cntr_width); if (!ret && !ff->ph->env.cpu_pmu_caps) pr_debug("cpu pmu capabilities not available\n"); @@ -3347,7 +3367,9 @@ static int process_pmu_caps(struct feat_fd *ff, void *data __maybe_unused) for (i = 0; i < nr_pmu; i++) { ret = __process_pmu_caps(ff, &pmu_caps[i].nr_caps, &pmu_caps[i].caps, - &pmu_caps[i].max_branches); + &pmu_caps[i].max_branches, + &pmu_caps[i].br_cntr_nr, + &pmu_caps[i].br_cntr_width); if (ret) goto err; @@ -4369,9 +4391,10 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) ret += fprintf(fp, "... "); map = cpu_map__new_data(&ev->cpus.cpus); - if (map) + if (map) { ret += cpu_map__fprintf(map, fp); - else + perf_cpu_map__put(map); + } else ret += fprintf(fp, "failed to get cpus\n"); break; default: diff --git a/tools/perf/util/hisi-ptt.c b/tools/perf/util/hisi-ptt.c index 43bd1ca62d58..52d0ce302ca0 100644 --- a/tools/perf/util/hisi-ptt.c +++ b/tools/perf/util/hisi-ptt.c @@ -123,6 +123,7 @@ static int hisi_ptt_process_auxtrace_event(struct perf_session *session, if (dump_trace) hisi_ptt_dump_event(ptt, data, size); + free(data); return 0; } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index afc9f1c7f4dc..5d0db96609df 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -457,7 +457,6 @@ struct hist_browser_timer { int refresh; }; -struct annotation_options; struct res_sample; enum rstype { @@ -473,16 +472,13 @@ struct block_hist; void attr_to_script(char *buf, struct perf_event_attr *attr); int map_symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, - struct hist_browser_timer *hbt, - struct annotation_options *annotation_opts); + struct hist_browser_timer *hbt); int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel, - struct hist_browser_timer *hbt, - struct annotation_options *annotation_opts); + struct hist_browser_timer *hbt); int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, - float min_pcnt, struct perf_env *env, bool warn_lost_event, - struct annotation_options *annotation_options); + float min_pcnt, struct perf_env *env, bool warn_lost_event); int script_browse(const char *script_opt, struct evsel *evsel); @@ -492,8 +488,7 @@ int res_sample_browse(struct res_sample *res_samples, int num_res, void res_sample_init(void); int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel, - float min_percent, struct perf_env *env, - struct annotation_options *annotation_opts); + float min_percent, struct perf_env *env); #else static inline int evlist__tui_browse_hists(struct evlist *evlist __maybe_unused, @@ -501,23 +496,20 @@ int evlist__tui_browse_hists(struct evlist *evlist __maybe_unused, struct hist_browser_timer *hbt __maybe_unused, float min_pcnt __maybe_unused, struct perf_env *env __maybe_unused, - bool warn_lost_event __maybe_unused, - struct annotation_options *annotation_options __maybe_unused) + bool warn_lost_event __maybe_unused) { return 0; } static inline int map_symbol__tui_annotate(struct map_symbol *ms __maybe_unused, struct evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused, - struct annotation_options *annotation_options __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused) { return 0; } static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused, struct evsel *evsel __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused, - struct annotation_options *annotation_opts __maybe_unused) + struct hist_browser_timer *hbt __maybe_unused) { return 0; } @@ -541,8 +533,7 @@ static inline void res_sample_init(void) {} static inline int block_hists_tui_browse(struct block_hist *bh __maybe_unused, struct evsel *evsel __maybe_unused, float min_percent __maybe_unused, - struct perf_env *env __maybe_unused, - struct annotation_options *annotation_opts __maybe_unused) + struct perf_env *env __maybe_unused) { return 0; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 90c750150b19..ca855fc435ac 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1285,33 +1285,46 @@ static u64 find_entry_trampoline(struct dso *dso) #define X86_64_CPU_ENTRY_AREA_SIZE 0x2c000 #define X86_64_ENTRY_TRAMPOLINE 0x6000 +struct machine__map_x86_64_entry_trampolines_args { + struct maps *kmaps; + bool found; +}; + +static int machine__map_x86_64_entry_trampolines_cb(struct map *map, void *data) +{ + struct machine__map_x86_64_entry_trampolines_args *args = data; + struct map *dest_map; + struct kmap *kmap = __map__kmap(map); + + if (!kmap || !is_entry_trampoline(kmap->name)) + return 0; + + dest_map = maps__find(args->kmaps, map__pgoff(map)); + if (dest_map != map) + map__set_pgoff(map, map__map_ip(dest_map, map__pgoff(map))); + + args->found = true; + return 0; +} + /* Map x86_64 PTI entry trampolines */ int machine__map_x86_64_entry_trampolines(struct machine *machine, struct dso *kernel) { - struct maps *kmaps = machine__kernel_maps(machine); + struct machine__map_x86_64_entry_trampolines_args args = { + .kmaps = machine__kernel_maps(machine), + .found = false, + }; int nr_cpus_avail, cpu; - bool found = false; - struct map_rb_node *rb_node; u64 pgoff; /* * In the vmlinux case, pgoff is a virtual address which must now be * mapped to a vmlinux offset. */ - maps__for_each_entry(kmaps, rb_node) { - struct map *dest_map, *map = rb_node->map; - struct kmap *kmap = __map__kmap(map); - - if (!kmap || !is_entry_trampoline(kmap->name)) - continue; + maps__for_each_map(args.kmaps, machine__map_x86_64_entry_trampolines_cb, &args); - dest_map = maps__find(kmaps, map__pgoff(map)); - if (dest_map != map) - map__set_pgoff(map, map__map_ip(dest_map, map__pgoff(map))); - found = true; - } - if (found || machine->trampolines_mapped) + if (args.found || machine->trampolines_mapped) return 0; pgoff = find_entry_trampoline(kernel); @@ -1359,8 +1372,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) if (machine->vmlinux_map == NULL) return -ENOMEM; - map__set_map_ip(machine->vmlinux_map, identity__map_ip); - map__set_unmap_ip(machine->vmlinux_map, identity__map_ip); + map__set_mapping_type(machine->vmlinux_map, MAPPING_TYPE__IDENTITY); return maps__insert(machine__kernel_maps(machine), machine->vmlinux_map); } @@ -2157,9 +2169,13 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event if (dump_trace) perf_event__fprintf_task(event, stdout); - if (thread != NULL) - thread__put(thread); - + if (thread != NULL) { + if (symbol_conf.keep_exited_threads) + thread__set_exited(thread, /*exited=*/true); + else + machine__remove_thread(machine, thread); + } + thread__put(thread); return 0; } @@ -3395,16 +3411,8 @@ int machine__for_each_dso(struct machine *machine, machine__dso_t fn, void *priv int machine__for_each_kernel_map(struct machine *machine, machine__map_t fn, void *priv) { struct maps *maps = machine__kernel_maps(machine); - struct map_rb_node *pos; - int err = 0; - maps__for_each_entry(maps, pos) { - err = fn(pos->map, priv); - if (err != 0) { - break; - } - } - return err; + return maps__for_each_map(maps, fn, priv); } bool machine__is_lock_function(struct machine *machine, u64 addr) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index f64b83004421..54c67cb7ecef 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -109,8 +109,7 @@ void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso) map__set_pgoff(map, pgoff); map__set_reloc(map, 0); map__set_dso(map, dso__get(dso)); - map__set_map_ip(map, map__dso_map_ip); - map__set_unmap_ip(map, map__dso_unmap_ip); + map__set_mapping_type(map, MAPPING_TYPE__DSO); map__set_erange_warned(map, false); refcount_set(map__refcnt(map), 1); } @@ -172,7 +171,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, map__init(result, start, start + len, pgoff, dso); if (anon || no_dso) { - map->map_ip = map->unmap_ip = identity__map_ip; + map->mapping_type = MAPPING_TYPE__IDENTITY; /* * Set memory without DSO as loaded. All map__find_* @@ -630,18 +629,3 @@ struct maps *map__kmaps(struct map *map) } return kmap->kmaps; } - -u64 map__dso_map_ip(const struct map *map, u64 ip) -{ - return ip - map__start(map) + map__pgoff(map); -} - -u64 map__dso_unmap_ip(const struct map *map, u64 ip) -{ - return ip + map__start(map) - map__pgoff(map); -} - -u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip) -{ - return ip; -} diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 1b53d53adc86..49756716cb13 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -16,23 +16,25 @@ struct dso; struct maps; struct machine; +enum mapping_type { + /* map__map_ip/map__unmap_ip are given as offsets in the DSO. */ + MAPPING_TYPE__DSO, + /* map__map_ip/map__unmap_ip are just the given ip value. */ + MAPPING_TYPE__IDENTITY, +}; + DECLARE_RC_STRUCT(map) { u64 start; u64 end; - bool erange_warned:1; - bool priv:1; - u32 prot; u64 pgoff; u64 reloc; - - /* ip -> dso rip */ - u64 (*map_ip)(const struct map *, u64); - /* dso rip -> ip */ - u64 (*unmap_ip)(const struct map *, u64); - struct dso *dso; refcount_t refcnt; + u32 prot; u32 flags; + enum mapping_type mapping_type:8; + bool erange_warned; + bool priv; }; struct kmap; @@ -41,38 +43,11 @@ struct kmap *__map__kmap(struct map *map); struct kmap *map__kmap(struct map *map); struct maps *map__kmaps(struct map *map); -/* ip -> dso rip */ -u64 map__dso_map_ip(const struct map *map, u64 ip); -/* dso rip -> ip */ -u64 map__dso_unmap_ip(const struct map *map, u64 ip); -/* Returns ip */ -u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip); - static inline struct dso *map__dso(const struct map *map) { return RC_CHK_ACCESS(map)->dso; } -static inline u64 map__map_ip(const struct map *map, u64 ip) -{ - return RC_CHK_ACCESS(map)->map_ip(map, ip); -} - -static inline u64 map__unmap_ip(const struct map *map, u64 ip) -{ - return RC_CHK_ACCESS(map)->unmap_ip(map, ip); -} - -static inline void *map__map_ip_ptr(struct map *map) -{ - return RC_CHK_ACCESS(map)->map_ip; -} - -static inline void* map__unmap_ip_ptr(struct map *map) -{ - return RC_CHK_ACCESS(map)->unmap_ip; -} - static inline u64 map__start(const struct map *map) { return RC_CHK_ACCESS(map)->start; @@ -123,6 +98,34 @@ static inline size_t map__size(const struct map *map) return map__end(map) - map__start(map); } +/* ip -> dso rip */ +static inline u64 map__dso_map_ip(const struct map *map, u64 ip) +{ + return ip - map__start(map) + map__pgoff(map); +} + +/* dso rip -> ip */ +static inline u64 map__dso_unmap_ip(const struct map *map, u64 rip) +{ + return rip + map__start(map) - map__pgoff(map); +} + +static inline u64 map__map_ip(const struct map *map, u64 ip_or_rip) +{ + if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO) + return map__dso_map_ip(map, ip_or_rip); + else + return ip_or_rip; +} + +static inline u64 map__unmap_ip(const struct map *map, u64 ip_or_rip) +{ + if ((RC_CHK_ACCESS(map)->mapping_type) == MAPPING_TYPE__DSO) + return map__dso_unmap_ip(map, ip_or_rip); + else + return ip_or_rip; +} + /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */ u64 map__rip_2objdump(struct map *map, u64 rip); @@ -294,13 +297,13 @@ static inline void map__set_dso(struct map *map, struct dso *dso) RC_CHK_ACCESS(map)->dso = dso; } -static inline void map__set_map_ip(struct map *map, u64 (*map_ip)(const struct map *map, u64 ip)) +static inline void map__set_mapping_type(struct map *map, enum mapping_type type) { - RC_CHK_ACCESS(map)->map_ip = map_ip; + RC_CHK_ACCESS(map)->mapping_type = type; } -static inline void map__set_unmap_ip(struct map *map, u64 (*unmap_ip)(const struct map *map, u64 rip)) +static inline enum mapping_type map__mapping_type(struct map *map) { - RC_CHK_ACCESS(map)->unmap_ip = unmap_ip; + return RC_CHK_ACCESS(map)->mapping_type; } #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 233438c95b53..160a6dce54bb 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -196,6 +196,21 @@ void maps__put(struct maps *maps) RC_CHK_PUT(maps); } +int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data), void *data) +{ + struct map_rb_node *pos; + int ret = 0; + + down_read(maps__lock(maps)); + maps__for_each_entry(maps, pos) { + ret = cb(pos->map, data); + if (ret) + break; + } + up_read(maps__lock(maps)); + return ret; +} + struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp) { struct map *map = maps__find(maps, addr); @@ -210,31 +225,40 @@ struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp) return NULL; } -struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp) -{ +struct maps__find_symbol_by_name_args { + struct map **mapp; + const char *name; struct symbol *sym; - struct map_rb_node *pos; +}; - down_read(maps__lock(maps)); +static int maps__find_symbol_by_name_cb(struct map *map, void *data) +{ + struct maps__find_symbol_by_name_args *args = data; - maps__for_each_entry(maps, pos) { - sym = map__find_symbol_by_name(pos->map, name); + args->sym = map__find_symbol_by_name(map, args->name); + if (!args->sym) + return 0; - if (sym == NULL) - continue; - if (!map__contains_symbol(pos->map, sym)) { - sym = NULL; - continue; - } - if (mapp != NULL) - *mapp = pos->map; - goto out; + if (!map__contains_symbol(map, args->sym)) { + args->sym = NULL; + return 0; } - sym = NULL; -out: - up_read(maps__lock(maps)); - return sym; + if (args->mapp != NULL) + *args->mapp = map__get(map); + return 1; +} + +struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp) +{ + struct maps__find_symbol_by_name_args args = { + .mapp = mapp, + .name = name, + .sym = NULL, + }; + + maps__for_each_map(maps, maps__find_symbol_by_name_cb, &args); + return args.sym; } int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams) @@ -253,25 +277,34 @@ int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams) return ams->ms.sym ? 0 : -1; } -size_t maps__fprintf(struct maps *maps, FILE *fp) -{ - size_t printed = 0; - struct map_rb_node *pos; +struct maps__fprintf_args { + FILE *fp; + size_t printed; +}; - down_read(maps__lock(maps)); +static int maps__fprintf_cb(struct map *map, void *data) +{ + struct maps__fprintf_args *args = data; - maps__for_each_entry(maps, pos) { - printed += fprintf(fp, "Map:"); - printed += map__fprintf(pos->map, fp); - if (verbose > 2) { - printed += dso__fprintf(map__dso(pos->map), fp); - printed += fprintf(fp, "--\n"); - } + args->printed += fprintf(args->fp, "Map:"); + args->printed += map__fprintf(map, args->fp); + if (verbose > 2) { + args->printed += dso__fprintf(map__dso(map), args->fp); + args->printed += fprintf(args->fp, "--\n"); } + return 0; +} - up_read(maps__lock(maps)); +size_t maps__fprintf(struct maps *maps, FILE *fp) +{ + struct maps__fprintf_args args = { + .fp = fp, + .printed = 0, + }; + + maps__for_each_map(maps, maps__fprintf_cb, &args); - return printed; + return args.printed; } int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) @@ -475,3 +508,241 @@ struct map_rb_node *map_rb_node__next(struct map_rb_node *node) return rb_entry(next, struct map_rb_node, rb_node); } + +static int map__strcmp(const void *a, const void *b) +{ + const struct map *map_a = *(const struct map **)a; + const struct map *map_b = *(const struct map **)b; + const struct dso *dso_a = map__dso(map_a); + const struct dso *dso_b = map__dso(map_b); + int ret = strcmp(dso_a->short_name, dso_b->short_name); + + if (ret == 0 && map_a != map_b) { + /* + * Ensure distinct but name equal maps have an order in part to + * aid reference counting. + */ + ret = (int)map__start(map_a) - (int)map__start(map_b); + if (ret == 0) + ret = (int)((intptr_t)map_a - (intptr_t)map_b); + } + + return ret; +} + +static int map__strcmp_name(const void *name, const void *b) +{ + const struct dso *dso = map__dso(*(const struct map **)b); + + return strcmp(name, dso->short_name); +} + +void __maps__sort_by_name(struct maps *maps) +{ + qsort(maps__maps_by_name(maps), maps__nr_maps(maps), sizeof(struct map *), map__strcmp); +} + +static int map__groups__sort_by_name_from_rbtree(struct maps *maps) +{ + struct map_rb_node *rb_node; + struct map **maps_by_name = realloc(maps__maps_by_name(maps), + maps__nr_maps(maps) * sizeof(struct map *)); + int i = 0; + + if (maps_by_name == NULL) + return -1; + + up_read(maps__lock(maps)); + down_write(maps__lock(maps)); + + RC_CHK_ACCESS(maps)->maps_by_name = maps_by_name; + RC_CHK_ACCESS(maps)->nr_maps_allocated = maps__nr_maps(maps); + + maps__for_each_entry(maps, rb_node) + maps_by_name[i++] = map__get(rb_node->map); + + __maps__sort_by_name(maps); + + up_write(maps__lock(maps)); + down_read(maps__lock(maps)); + + return 0; +} + +static struct map *__maps__find_by_name(struct maps *maps, const char *name) +{ + struct map **mapp; + + if (maps__maps_by_name(maps) == NULL && + map__groups__sort_by_name_from_rbtree(maps)) + return NULL; + + mapp = bsearch(name, maps__maps_by_name(maps), maps__nr_maps(maps), + sizeof(*mapp), map__strcmp_name); + if (mapp) + return *mapp; + return NULL; +} + +struct map *maps__find_by_name(struct maps *maps, const char *name) +{ + struct map_rb_node *rb_node; + struct map *map; + + down_read(maps__lock(maps)); + + + if (RC_CHK_ACCESS(maps)->last_search_by_name) { + const struct dso *dso = map__dso(RC_CHK_ACCESS(maps)->last_search_by_name); + + if (strcmp(dso->short_name, name) == 0) { + map = RC_CHK_ACCESS(maps)->last_search_by_name; + goto out_unlock; + } + } + /* + * If we have maps->maps_by_name, then the name isn't in the rbtree, + * as maps->maps_by_name mirrors the rbtree when lookups by name are + * made. + */ + map = __maps__find_by_name(maps, name); + if (map || maps__maps_by_name(maps) != NULL) + goto out_unlock; + + /* Fallback to traversing the rbtree... */ + maps__for_each_entry(maps, rb_node) { + struct dso *dso; + + map = rb_node->map; + dso = map__dso(map); + if (strcmp(dso->short_name, name) == 0) { + RC_CHK_ACCESS(maps)->last_search_by_name = map; + goto out_unlock; + } + } + map = NULL; + +out_unlock: + up_read(maps__lock(maps)); + return map; +} + +void maps__fixup_end(struct maps *maps) +{ + struct map_rb_node *prev = NULL, *curr; + + down_write(maps__lock(maps)); + + maps__for_each_entry(maps, curr) { + if (prev != NULL && !map__end(prev->map)) + map__set_end(prev->map, map__start(curr->map)); + + prev = curr; + } + + /* + * We still haven't the actual symbols, so guess the + * last map final address. + */ + if (curr && !map__end(curr->map)) + map__set_end(curr->map, ~0ULL); + + up_write(maps__lock(maps)); +} + +/* + * Merges map into maps by splitting the new map within the existing map + * regions. + */ +int maps__merge_in(struct maps *kmaps, struct map *new_map) +{ + struct map_rb_node *rb_node; + LIST_HEAD(merged); + int err = 0; + + maps__for_each_entry(kmaps, rb_node) { + struct map *old_map = rb_node->map; + + /* no overload with this one */ + if (map__end(new_map) < map__start(old_map) || + map__start(new_map) >= map__end(old_map)) + continue; + + if (map__start(new_map) < map__start(old_map)) { + /* + * |new...... + * |old.... + */ + if (map__end(new_map) < map__end(old_map)) { + /* + * |new......| -> |new..| + * |old....| -> |old....| + */ + map__set_end(new_map, map__start(old_map)); + } else { + /* + * |new.............| -> |new..| |new..| + * |old....| -> |old....| + */ + struct map_list_node *m = map_list_node__new(); + + if (!m) { + err = -ENOMEM; + goto out; + } + + m->map = map__clone(new_map); + if (!m->map) { + free(m); + err = -ENOMEM; + goto out; + } + + map__set_end(m->map, map__start(old_map)); + list_add_tail(&m->node, &merged); + map__add_pgoff(new_map, map__end(old_map) - map__start(new_map)); + map__set_start(new_map, map__end(old_map)); + } + } else { + /* + * |new...... + * |old.... + */ + if (map__end(new_map) < map__end(old_map)) { + /* + * |new..| -> x + * |old.........| -> |old.........| + */ + map__put(new_map); + new_map = NULL; + break; + } else { + /* + * |new......| -> |new...| + * |old....| -> |old....| + */ + map__add_pgoff(new_map, map__end(old_map) - map__start(new_map)); + map__set_start(new_map, map__end(old_map)); + } + } + } + +out: + while (!list_empty(&merged)) { + struct map_list_node *old_node; + + old_node = list_entry(merged.next, struct map_list_node, node); + list_del_init(&old_node->node); + if (!err) + err = maps__insert(kmaps, old_node->map); + map__put(old_node->map); + free(old_node); + } + + if (new_map) { + if (!err) + err = maps__insert(kmaps, new_map); + map__put(new_map); + } + return err; +} diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h index 83144e0645ed..14ad95979257 100644 --- a/tools/perf/util/maps.h +++ b/tools/perf/util/maps.h @@ -21,6 +21,16 @@ struct map_rb_node { struct map *map; }; +struct map_list_node { + struct list_head node; + struct map *map; +}; + +static inline struct map_list_node *map_list_node__new(void) +{ + return malloc(sizeof(struct map_list_node)); +} + struct map_rb_node *maps__first(struct maps *maps); struct map_rb_node *map_rb_node__next(struct map_rb_node *node); struct map_rb_node *maps__find_node(struct maps *maps, struct map *map); @@ -71,6 +81,9 @@ static inline void __maps__zput(struct maps **map) #define maps__zput(map) __maps__zput(&map) +/* Iterate over map calling cb for each entry. */ +int maps__for_each_map(struct maps *maps, int (*cb)(struct map *map, void *data), void *data); + static inline struct rb_root *maps__entries(struct maps *maps) { return &RC_CHK_ACCESS(maps)->entries; @@ -133,4 +146,6 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map); void __maps__sort_by_name(struct maps *maps); +void maps__fixup_end(struct maps *maps); + #endif // __PERF_MAPS_H diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 954b235e12e5..3a2e3687878c 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -100,11 +100,14 @@ int perf_mem_events__parse(const char *str) return -1; } -static bool perf_mem_event__supported(const char *mnt, char *sysfs_name) +static bool perf_mem_event__supported(const char *mnt, struct perf_pmu *pmu, + struct perf_mem_event *e) { + char sysfs_name[100]; char path[PATH_MAX]; struct stat st; + scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name, pmu->name); scnprintf(path, PATH_MAX, "%s/devices/%s", mnt, sysfs_name); return !stat(path, &st); } @@ -120,7 +123,6 @@ int perf_mem_events__init(void) for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { struct perf_mem_event *e = perf_mem_events__ptr(j); - char sysfs_name[100]; struct perf_pmu *pmu = NULL; /* @@ -136,12 +138,12 @@ int perf_mem_events__init(void) * of core PMU. */ while ((pmu = perf_pmus__scan(pmu)) != NULL) { - scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name, pmu->name); - e->supported |= perf_mem_event__supported(mnt, sysfs_name); + e->supported |= perf_mem_event__supported(mnt, pmu, e); + if (e->supported) { + found = true; + break; + } } - - if (e->supported) - found = true; } return found ? 0 : -ENOENT; @@ -167,13 +169,10 @@ static void perf_mem_events__print_unsupport_hybrid(struct perf_mem_event *e, int idx) { const char *mnt = sysfs__mount(); - char sysfs_name[100]; struct perf_pmu *pmu = NULL; while ((pmu = perf_pmus__scan(pmu)) != NULL) { - scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name, - pmu->name); - if (!perf_mem_event__supported(mnt, sysfs_name)) { + if (!perf_mem_event__supported(mnt, pmu, e)) { pr_err("failed: event '%s' not supported\n", perf_mem_events__name(idx, pmu->name)); } @@ -183,6 +182,7 @@ static void perf_mem_events__print_unsupport_hybrid(struct perf_mem_event *e, int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, char **rec_tmp, int *tmp_nr) { + const char *mnt = sysfs__mount(); int i = *argv_nr, k = 0; struct perf_mem_event *e; @@ -211,6 +211,9 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, while ((pmu = perf_pmus__scan(pmu)) != NULL) { const char *s = perf_mem_events__name(j, pmu->name); + if (!perf_mem_event__supported(mnt, pmu, e)) + continue; + rec_argv[i++] = "-e"; if (s) { char *copy = strdup(s); diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 49093b21ee2d..122ee198a86e 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -295,15 +295,14 @@ int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu map->core.flush = mp->flush; - map->comp_level = mp->comp_level; #ifndef PYTHON_PERF - if (zstd_init(&map->zstd_data, map->comp_level)) { + if (zstd_init(&map->zstd_data, mp->comp_level)) { pr_debug2("failed to init mmap compressor, error %d\n", errno); return -1; } #endif - if (map->comp_level && !perf_mmap__aio_enabled(map)) { + if (mp->comp_level && !perf_mmap__aio_enabled(map)) { map->data = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, 0, 0); if (map->data == MAP_FAILED) { diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index f944c3cd5efa..0df6e1621c7e 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -39,7 +39,6 @@ struct mmap { #endif struct mmap_cpu_mask affinity_mask; void *data; - int comp_level; struct perf_data_file *file; struct zstd_data zstd_data; }; diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c index fd67d204d720..f7f7aff3d85a 100644 --- a/tools/perf/util/parse-branch-options.c +++ b/tools/perf/util/parse-branch-options.c @@ -36,6 +36,7 @@ static const struct branch_mode branch_modes[] = { BRANCH_OPT("stack", PERF_SAMPLE_BRANCH_CALL_STACK), BRANCH_OPT("hw_index", PERF_SAMPLE_BRANCH_HW_INDEX), BRANCH_OPT("priv", PERF_SAMPLE_BRANCH_PRIV_SAVE), + BRANCH_OPT("counter", PERF_SAMPLE_BRANCH_COUNTERS), BRANCH_END }; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index aa2f5c6fc7fc..66eabcea4242 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -976,7 +976,7 @@ static int config_term_pmu(struct perf_event_attr *attr, struct parse_events_error *err) { if (term->type_term == PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE) { - const struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type); + struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type); if (!pmu) { char *err_str; @@ -986,15 +986,23 @@ static int config_term_pmu(struct perf_event_attr *attr, err_str, /*help=*/NULL); return -EINVAL; } - if (perf_pmu__supports_legacy_cache(pmu)) { + /* + * Rewrite the PMU event to a legacy cache one unless the PMU + * doesn't support legacy cache events or the event is present + * within the PMU. + */ + if (perf_pmu__supports_legacy_cache(pmu) && + !perf_pmu__have_event(pmu, term->config)) { attr->type = PERF_TYPE_HW_CACHE; return parse_events__decode_legacy_cache(term->config, pmu->type, &attr->config); - } else + } else { term->type_term = PARSE_EVENTS__TERM_TYPE_USER; + term->no_value = true; + } } if (term->type_term == PARSE_EVENTS__TERM_TYPE_HARDWARE) { - const struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type); + struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type); if (!pmu) { char *err_str; @@ -1004,10 +1012,19 @@ static int config_term_pmu(struct perf_event_attr *attr, err_str, /*help=*/NULL); return -EINVAL; } - attr->type = PERF_TYPE_HARDWARE; - attr->config = term->val.num; - if (perf_pmus__supports_extended_type()) - attr->config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT; + /* + * If the PMU has a sysfs or json event prefer it over + * legacy. ARM requires this. + */ + if (perf_pmu__have_event(pmu, term->config)) { + term->type_term = PARSE_EVENTS__TERM_TYPE_USER; + term->no_value = true; + } else { + attr->type = PERF_TYPE_HARDWARE; + attr->config = term->val.num; + if (perf_pmus__supports_extended_type()) + attr->config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT; + } return 0; } if (term->type_term == PARSE_EVENTS__TERM_TYPE_USER || @@ -1381,6 +1398,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, YYLTYPE *loc = loc_; LIST_HEAD(config_terms); struct parse_events_terms parsed_terms; + bool alias_rewrote_terms = false; pmu = parse_state->fake_pmu ?: perf_pmus__find(name); @@ -1433,7 +1451,15 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, return evsel ? 0 : -ENOMEM; } - if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, &parsed_terms, &info, err)) { + /* Configure attr/terms with a known PMU, this will set hardcoded terms. */ + if (config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) { + parse_events_terms__exit(&parsed_terms); + return -EINVAL; + } + + /* Look for event names in the terms and rewrite into format based terms. */ + if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, &parsed_terms, + &info, &alias_rewrote_terms, err)) { parse_events_terms__exit(&parsed_terms); return -EINVAL; } @@ -1447,11 +1473,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, strbuf_release(&sb); } - /* - * Configure hardcoded terms first, no need to check - * return value when called with fail == 0 ;) - */ - if (config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) { + /* Configure attr/terms again if an alias was expanded. */ + if (alias_rewrote_terms && + config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) { parse_events_terms__exit(&parsed_terms); return -EINVAL; } diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c index e1e2d701599c..1de3b69cdf4a 100644 --- a/tools/perf/util/perf_api_probe.c +++ b/tools/perf/util/perf_api_probe.c @@ -64,7 +64,7 @@ static bool perf_probe_api(setup_probe_fn_t fn) struct perf_cpu cpu; int ret, i = 0; - cpus = perf_cpu_map__new(NULL); + cpus = perf_cpu_map__new_online_cpus(); if (!cpus) return false; cpu = perf_cpu_map__cpu(cpus, 0); @@ -140,7 +140,7 @@ bool perf_can_record_cpu_wide(void) struct perf_cpu cpu; int fd; - cpus = perf_cpu_map__new(NULL); + cpus = perf_cpu_map__new_online_cpus(); if (!cpus) return false; diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index 2247991451f3..8f04d3b7f3ec 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -55,6 +55,7 @@ static void __p_branch_sample_type(char *buf, size_t size, u64 value) bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP), bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES), bit_name(TYPE_SAVE), bit_name(HW_INDEX), bit_name(PRIV_SAVE), + bit_name(COUNTERS), { .name = NULL, } }; #undef bit_name diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index d3c9aa4326be..3c9609944a2f 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1494,12 +1494,14 @@ static int check_info_data(struct perf_pmu *pmu, * defined for the alias */ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms, - struct perf_pmu_info *info, struct parse_events_error *err) + struct perf_pmu_info *info, bool *rewrote_terms, + struct parse_events_error *err) { struct parse_events_term *term, *h; struct perf_pmu_alias *alias; int ret; + *rewrote_terms = false; info->per_pkg = false; /* @@ -1521,7 +1523,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_ NULL); return ret; } - + *rewrote_terms = true; ret = check_info_data(pmu, alias, info, err, term->err_term); if (ret) return ret; @@ -1615,6 +1617,8 @@ bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu) bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name) { + if (!name) + return false; if (perf_pmu__find_alias(pmu, name, /*load=*/ true) != NULL) return true; if (pmu->cpu_aliases_added || !pmu->events_table) diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index d2895d415f08..424c3fee0949 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -201,7 +201,8 @@ int perf_pmu__config_terms(const struct perf_pmu *pmu, __u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name); int perf_pmu__format_type(struct perf_pmu *pmu, const char *name); int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms, - struct perf_pmu_info *info, struct parse_events_error *err); + struct perf_pmu_info *info, bool *rewrote_terms, + struct parse_events_error *err); int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb); int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load); diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 1a5b7fa459b2..a1a796043691 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -149,10 +149,32 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr, return 0; } +struct kernel_get_module_map_cb_args { + const char *module; + struct map *result; +}; + +static int kernel_get_module_map_cb(struct map *map, void *data) +{ + struct kernel_get_module_map_cb_args *args = data; + struct dso *dso = map__dso(map); + const char *short_name = dso->short_name; /* short_name is "[module]" */ + u16 short_name_len = dso->short_name_len; + + if (strncmp(short_name + 1, args->module, short_name_len - 2) == 0 && + args->module[short_name_len - 2] == '\0') { + args->result = map__get(map); + return 1; + } + return 0; +} + static struct map *kernel_get_module_map(const char *module) { - struct maps *maps = machine__kernel_maps(host_machine); - struct map_rb_node *pos; + struct kernel_get_module_map_cb_args args = { + .module = module, + .result = NULL, + }; /* A file path -- this is an offline module */ if (module && strchr(module, '/')) @@ -164,19 +186,9 @@ static struct map *kernel_get_module_map(const char *module) return map__get(map); } - maps__for_each_entry(maps, pos) { - /* short_name is "[module]" */ - struct dso *dso = map__dso(pos->map); - const char *short_name = dso->short_name; - u16 short_name_len = dso->short_name_len; + maps__for_each_map(machine__kernel_maps(host_machine), kernel_get_module_map_cb, &args); - if (strncmp(short_name + 1, module, - short_name_len - 2) == 0 && - module[short_name_len - 2] == '\0') { - return map__get(pos->map); - } - } - return NULL; + return args.result; } struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user) diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index f171360b0ef4..c8923375e30d 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -23,6 +23,7 @@ #include "event.h" #include "dso.h" #include "debug.h" +#include "debuginfo.h" #include "intlist.h" #include "strbuf.h" #include "strlist.h" @@ -31,128 +32,9 @@ #include "probe-file.h" #include "string2.h" -#ifdef HAVE_DEBUGINFOD_SUPPORT -#include <elfutils/debuginfod.h> -#endif - /* Kprobe tracer basic type is up to u64 */ #define MAX_BASIC_TYPE_BITS 64 -/* Dwarf FL wrappers */ -static char *debuginfo_path; /* Currently dummy */ - -static const Dwfl_Callbacks offline_callbacks = { - .find_debuginfo = dwfl_standard_find_debuginfo, - .debuginfo_path = &debuginfo_path, - - .section_address = dwfl_offline_section_address, - - /* We use this table for core files too. */ - .find_elf = dwfl_build_id_find_elf, -}; - -/* Get a Dwarf from offline image */ -static int debuginfo__init_offline_dwarf(struct debuginfo *dbg, - const char *path) -{ - GElf_Addr dummy; - int fd; - - fd = open(path, O_RDONLY); - if (fd < 0) - return fd; - - dbg->dwfl = dwfl_begin(&offline_callbacks); - if (!dbg->dwfl) - goto error; - - dwfl_report_begin(dbg->dwfl); - dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd); - if (!dbg->mod) - goto error; - - dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias); - if (!dbg->dbg) - goto error; - - dwfl_module_build_id(dbg->mod, &dbg->build_id, &dummy); - - dwfl_report_end(dbg->dwfl, NULL, NULL); - - return 0; -error: - if (dbg->dwfl) - dwfl_end(dbg->dwfl); - else - close(fd); - memset(dbg, 0, sizeof(*dbg)); - - return -ENOENT; -} - -static struct debuginfo *__debuginfo__new(const char *path) -{ - struct debuginfo *dbg = zalloc(sizeof(*dbg)); - if (!dbg) - return NULL; - - if (debuginfo__init_offline_dwarf(dbg, path) < 0) - zfree(&dbg); - if (dbg) - pr_debug("Open Debuginfo file: %s\n", path); - return dbg; -} - -enum dso_binary_type distro_dwarf_types[] = { - DSO_BINARY_TYPE__FEDORA_DEBUGINFO, - DSO_BINARY_TYPE__UBUNTU_DEBUGINFO, - DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO, - DSO_BINARY_TYPE__BUILDID_DEBUGINFO, - DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO, - DSO_BINARY_TYPE__NOT_FOUND, -}; - -struct debuginfo *debuginfo__new(const char *path) -{ - enum dso_binary_type *type; - char buf[PATH_MAX], nil = '\0'; - struct dso *dso; - struct debuginfo *dinfo = NULL; - struct build_id bid; - - /* Try to open distro debuginfo files */ - dso = dso__new(path); - if (!dso) - goto out; - - /* Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO */ - if (is_regular_file(path) && filename__read_build_id(path, &bid) > 0) - dso__set_build_id(dso, &bid); - - for (type = distro_dwarf_types; - !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND; - type++) { - if (dso__read_binary_type_filename(dso, *type, &nil, - buf, PATH_MAX) < 0) - continue; - dinfo = __debuginfo__new(buf); - } - dso__put(dso); - -out: - /* if failed to open all distro debuginfo, open given binary */ - return dinfo ? : __debuginfo__new(path); -} - -void debuginfo__delete(struct debuginfo *dbg) -{ - if (dbg) { - if (dbg->dwfl) - dwfl_end(dbg->dwfl); - free(dbg); - } -} - /* * Probe finder related functions */ @@ -722,7 +604,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) ret = dwarf_getlocation_addr(&fb_attr, pf->addr, &pf->fb_ops, &nops, 1); if (ret <= 0 || nops == 0) { pf->fb_ops = NULL; -#if _ELFUTILS_PREREQ(0, 142) +#ifdef HAVE_DWARF_CFI_SUPPORT } else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa && (pf->cfi_eh != NULL || pf->cfi_dbg != NULL)) { if ((dwarf_cfi_addrframe(pf->cfi_eh, pf->addr, &frame) != 0 && @@ -733,7 +615,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) free(frame); return -ENOENT; } -#endif +#endif /* HAVE_DWARF_CFI_SUPPORT */ } /* Call finder's callback handler */ @@ -1258,7 +1140,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg, pf->machine = ehdr.e_machine; -#if _ELFUTILS_PREREQ(0, 142) +#ifdef HAVE_DWARF_CFI_SUPPORT do { GElf_Shdr shdr; @@ -1268,7 +1150,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg, pf->cfi_dbg = dwarf_getcfi(dbg->dbg); } while (0); -#endif +#endif /* HAVE_DWARF_CFI_SUPPORT */ ret = debuginfo__find_probe_location(dbg, pf); return ret; @@ -1677,44 +1559,6 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg, return (ret < 0) ? ret : af.nvls; } -/* For the kernel module, we need a special code to get a DIE */ -int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs, - bool adjust_offset) -{ - int n, i; - Elf32_Word shndx; - Elf_Scn *scn; - Elf *elf; - GElf_Shdr mem, *shdr; - const char *p; - - elf = dwfl_module_getelf(dbg->mod, &dbg->bias); - if (!elf) - return -EINVAL; - - /* Get the number of relocations */ - n = dwfl_module_relocations(dbg->mod); - if (n < 0) - return -ENOENT; - /* Search the relocation related .text section */ - for (i = 0; i < n; i++) { - p = dwfl_module_relocation_info(dbg->mod, i, &shndx); - if (strcmp(p, ".text") == 0) { - /* OK, get the section header */ - scn = elf_getscn(elf, shndx); - if (!scn) - return -ENOENT; - shdr = gelf_getshdr(scn, &mem); - if (!shdr) - return -ENOENT; - *offs = shdr->sh_addr; - if (adjust_offset) - *offs -= shdr->sh_offset; - } - } - return 0; -} - /* Reverse search */ int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr, struct perf_probe_point *ppt) @@ -2009,41 +1853,6 @@ found: return (ret < 0) ? ret : lf.found; } -#ifdef HAVE_DEBUGINFOD_SUPPORT -/* debuginfod doesn't require the comp_dir but buildid is required */ -static int get_source_from_debuginfod(const char *raw_path, - const char *sbuild_id, char **new_path) -{ - debuginfod_client *c = debuginfod_begin(); - const char *p = raw_path; - int fd; - - if (!c) - return -ENOMEM; - - fd = debuginfod_find_source(c, (const unsigned char *)sbuild_id, - 0, p, new_path); - pr_debug("Search %s from debuginfod -> %d\n", p, fd); - if (fd >= 0) - close(fd); - debuginfod_end(c); - if (fd < 0) { - pr_debug("Failed to find %s in debuginfod (%s)\n", - raw_path, sbuild_id); - return -ENOENT; - } - pr_debug("Got a source %s\n", *new_path); - - return 0; -} -#else -static inline int get_source_from_debuginfod(const char *raw_path __maybe_unused, - const char *sbuild_id __maybe_unused, - char **new_path __maybe_unused) -{ - return -ENOTSUP; -} -#endif /* * Find a src file from a DWARF tag path. Prepend optional source path prefix * and chop off leading directories that do not exist. Result is passed back as diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 8bc1c80d3c1c..3add5ff516e1 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -24,21 +24,7 @@ static inline int is_c_varname(const char *name) #ifdef HAVE_DWARF_SUPPORT #include "dwarf-aux.h" - -/* TODO: export debuginfo data structure even if no dwarf support */ - -/* debug information structure */ -struct debuginfo { - Dwarf *dbg; - Dwfl_Module *mod; - Dwfl *dwfl; - Dwarf_Addr bias; - const unsigned char *build_id; -}; - -/* This also tries to open distro debuginfo */ -struct debuginfo *debuginfo__new(const char *path); -void debuginfo__delete(struct debuginfo *dbg); +#include "debuginfo.h" /* Find probe_trace_events specified by perf_probe_event from debuginfo */ int debuginfo__find_trace_events(struct debuginfo *dbg, @@ -49,9 +35,6 @@ int debuginfo__find_trace_events(struct debuginfo *dbg, int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr, struct perf_probe_point *ppt); -int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs, - bool adjust_offset); - /* Find a line range */ int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr); diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 9eb5c6a08999..87e817b3cf7e 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -237,8 +237,8 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str) evsel = evlist__last(temp_evlist); - if (!evlist || perf_cpu_map__empty(evlist->core.user_requested_cpus)) { - struct perf_cpu_map *cpus = perf_cpu_map__new(NULL); + if (!evlist || perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus)) { + struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus(); if (cpus) cpu = perf_cpu_map__cpu(cpus, 0); diff --git a/tools/perf/util/s390-cpumcf-kernel.h b/tools/perf/util/s390-cpumcf-kernel.h index f55ca07f3ca1..74b36644e384 100644 --- a/tools/perf/util/s390-cpumcf-kernel.h +++ b/tools/perf/util/s390-cpumcf-kernel.h @@ -12,6 +12,8 @@ #define S390_CPUMCF_DIAG_DEF 0xfeef /* Counter diagnostic entry ID */ #define PERF_EVENT_CPUM_CF_DIAG 0xBC000 /* Event: Counter sets */ #define PERF_EVENT_CPUM_SF_DIAG 0xBD000 /* Event: Combined-sampling */ +#define PERF_EVENT_PAI_CRYPTO_ALL 0x1000 /* Event: CRYPTO_ALL */ +#define PERF_EVENT_PAI_NNPA_ALL 0x1800 /* Event: NNPA_ALL */ struct cf_ctrset_entry { /* CPU-M CF counter set entry (8 byte) */ unsigned int def:16; /* 0-15 Data Entry Format */ diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c index 115b16edb451..53383e97ec9d 100644 --- a/tools/perf/util/s390-sample-raw.c +++ b/tools/perf/util/s390-sample-raw.c @@ -51,8 +51,6 @@ static bool s390_cpumcfdg_testctr(struct perf_sample *sample) struct cf_trailer_entry *te; struct cf_ctrset_entry *cep, ce; - if (!len) - return false; while (offset < len) { cep = (struct cf_ctrset_entry *)(buf + offset); ce.def = be16_to_cpu(cep->def); @@ -125,6 +123,9 @@ static int get_counterset_start(int setnr) return 128; case CPUMF_CTR_SET_MT_DIAG: /* Diagnostic counter set */ return 448; + case PERF_EVENT_PAI_NNPA_ALL: /* PAI NNPA counter set */ + case PERF_EVENT_PAI_CRYPTO_ALL: /* PAI CRYPTO counter set */ + return setnr; default: return -1; } @@ -212,27 +213,120 @@ static void s390_cpumcfdg_dump(struct perf_pmu *pmu, struct perf_sample *sample) } } +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wpacked" +#pragma GCC diagnostic ignored "-Wattributes" +/* + * Check for consistency of PAI_CRYPTO/PAI_NNPA raw data. + */ +struct pai_data { /* Event number and value */ + u16 event_nr; + u64 event_val; +} __packed; + +#pragma GCC diagnostic pop + +/* + * Test for valid raw data. At least one PAI event should be in the raw + * data section. + */ +static bool s390_pai_all_test(struct perf_sample *sample) +{ + size_t len = sample->raw_size; + + if (len < 0xa) + return false; + return true; +} + +static void s390_pai_all_dump(struct evsel *evsel, struct perf_sample *sample) +{ + size_t len = sample->raw_size, offset = 0; + unsigned char *p = sample->raw_data; + const char *color = PERF_COLOR_BLUE; + struct pai_data pai_data; + char *ev_name; + + while (offset < len) { + memcpy(&pai_data.event_nr, p, sizeof(pai_data.event_nr)); + pai_data.event_nr = be16_to_cpu(pai_data.event_nr); + p += sizeof(pai_data.event_nr); + offset += sizeof(pai_data.event_nr); + + memcpy(&pai_data.event_val, p, sizeof(pai_data.event_val)); + pai_data.event_val = be64_to_cpu(pai_data.event_val); + p += sizeof(pai_data.event_val); + offset += sizeof(pai_data.event_val); + + ev_name = get_counter_name(evsel->core.attr.config, + pai_data.event_nr, evsel->pmu); + color_fprintf(stdout, color, "\tCounter:%03d %s Value:%#018lx\n", + pai_data.event_nr, ev_name ?: "<unknown>", + pai_data.event_val); + free(ev_name); + + if (offset + 0xa > len) + break; + } + color_fprintf(stdout, color, "\n"); +} + /* S390 specific trace event function. Check for PERF_RECORD_SAMPLE events - * and if the event was triggered by a counter set diagnostic event display - * its raw data. + * and if the event was triggered by a + * - counter set diagnostic event + * - processor activity assist (PAI) crypto counter event + * - processor activity assist (PAI) neural network processor assist (NNPA) + * counter event + * display its raw data. * The function is only invoked when the dump flag -D is set. + * + * Function evlist__s390_sample_raw() is defined as call back after it has + * been verified that the perf.data file was created on s390 platform. */ -void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) +void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, + struct perf_sample *sample) { + const char *pai_name; struct evsel *evsel; if (event->header.type != PERF_RECORD_SAMPLE) return; evsel = evlist__event2evsel(evlist, event); - if (evsel == NULL || - evsel->core.attr.config != PERF_EVENT_CPUM_CF_DIAG) + if (!evsel) + return; + + /* Check for raw data in sample */ + if (!sample->raw_size || !sample->raw_data) return; /* Display raw data on screen */ - if (!s390_cpumcfdg_testctr(sample)) { - pr_err("Invalid counter set data encountered\n"); + if (evsel->core.attr.config == PERF_EVENT_CPUM_CF_DIAG) { + if (!evsel->pmu) + evsel->pmu = perf_pmus__find("cpum_cf"); + if (!s390_cpumcfdg_testctr(sample)) + pr_err("Invalid counter set data encountered\n"); + else + s390_cpumcfdg_dump(evsel->pmu, sample); + return; + } + + switch (evsel->core.attr.config) { + case PERF_EVENT_PAI_NNPA_ALL: + pai_name = "NNPA_ALL"; + break; + case PERF_EVENT_PAI_CRYPTO_ALL: + pai_name = "CRYPTO_ALL"; + break; + default: return; } - s390_cpumcfdg_dump(evsel->pmu, sample); + + if (!s390_pai_all_test(sample)) { + pr_err("Invalid %s raw data encountered\n", pai_name); + } else { + if (!evsel->pmu) + evsel->pmu = perf_pmus__find_by_type(evsel->core.attr.type); + s390_pai_all_dump(evsel, sample); + } } diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h index c92ad0f51ecd..70b2c3135555 100644 --- a/tools/perf/util/sample.h +++ b/tools/perf/util/sample.h @@ -113,6 +113,7 @@ struct perf_sample { void *raw_data; struct ip_callchain *callchain; struct branch_stack *branch_stack; + u64 *branch_stack_cntr; struct regs_dump user_regs; struct regs_dump intr_regs; struct stack_dump user_stack; diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 603091317bed..b072ac5d3bc2 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -490,6 +490,9 @@ static int perl_start_script(const char *script, int argc, const char **argv, scripting_context->session = session; command_line = malloc((argc + 2) * sizeof(const char *)); + if (!command_line) + return -ENOMEM; + command_line[0] = ""; command_line[1] = script; for (i = 2; i < argc + 2; i++) diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 94312741443a..860e1837ba96 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -353,6 +353,8 @@ static PyObject *get_field_numeric_entry(struct tep_event *event, if (is_array) { list = PyList_New(field->arraylen); + if (!list) + Py_FatalError("couldn't create Python list"); item_size = field->size / field->arraylen; n_items = field->arraylen; } else { @@ -754,7 +756,7 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, ch } } -static void set_regs_in_dict(PyObject *dict, +static int set_regs_in_dict(PyObject *dict, struct perf_sample *sample, struct evsel *evsel) { @@ -770,6 +772,8 @@ static void set_regs_in_dict(PyObject *dict, */ int size = __sw_hweight64(attr->sample_regs_intr) * 28; char *bf = malloc(size); + if (!bf) + return -1; regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, size); @@ -781,6 +785,8 @@ static void set_regs_in_dict(PyObject *dict, pydict_set_item_string_decref(dict, "uregs", _PyUnicode_FromString(bf)); free(bf); + + return 0; } static void set_sym_in_dict(PyObject *dict, struct addr_location *al, @@ -920,7 +926,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, PyLong_FromUnsignedLongLong(sample->cyc_cnt)); } - set_regs_in_dict(dict, sample, evsel); + if (set_regs_in_dict(dict, sample, evsel)) + Py_FatalError("Failed to setting regs in dict"); return dict; } @@ -1918,12 +1925,18 @@ static int python_start_script(const char *script, int argc, const char **argv, scripting_context->session = session; #if PY_MAJOR_VERSION < 3 command_line = malloc((argc + 1) * sizeof(const char *)); + if (!command_line) + return -1; + command_line[0] = script; for (i = 1; i < argc + 1; i++) command_line[i] = argv[i - 1]; PyImport_AppendInittab(name, initperf_trace_context); #else command_line = malloc((argc + 1) * sizeof(wchar_t *)); + if (!command_line) + return -1; + command_line[0] = Py_DecodeLocale(script, NULL); for (i = 1; i < argc + 1; i++) command_line[i] = Py_DecodeLocale(argv[i - 1], NULL); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 1e9aa8ed15b6..199d3e8df315 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -115,6 +115,11 @@ static int perf_session__open(struct perf_session *session, int repipe_fd) return -1; } + if (perf_header__has_feat(&session->header, HEADER_AUXTRACE)) { + /* Auxiliary events may reference exited threads, hold onto dead ones. */ + symbol_conf.keep_exited_threads = true; + } + if (perf_data__is_pipe(data)) return 0; @@ -1150,9 +1155,13 @@ static void callchain__printf(struct evsel *evsel, i, callchain->ips[i]); } -static void branch_stack__printf(struct perf_sample *sample, bool callstack) +static void branch_stack__printf(struct perf_sample *sample, + struct evsel *evsel) { struct branch_entry *entries = perf_sample__branch_entries(sample); + bool callstack = evsel__has_branch_callstack(evsel); + u64 *branch_stack_cntr = sample->branch_stack_cntr; + struct perf_env *env = evsel__env(evsel); uint64_t i; if (!callstack) { @@ -1194,6 +1203,13 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack) } } } + + if (branch_stack_cntr) { + printf("... branch stack counters: nr:%" PRIu64 " (counter width: %u max counter nr:%u)\n", + sample->branch_stack->nr, env->br_cntr_width, env->br_cntr_nr); + for (i = 0; i < sample->branch_stack->nr; i++) + printf("..... %2"PRIu64": %016" PRIx64 "\n", i, branch_stack_cntr[i]); + } } static void regs_dump__printf(u64 mask, u64 *regs, const char *arch) @@ -1355,7 +1371,7 @@ static void dump_sample(struct evsel *evsel, union perf_event *event, callchain__printf(evsel, sample); if (evsel__has_br_stack(evsel)) - branch_stack__printf(sample, evsel__has_branch_callstack(evsel)); + branch_stack__printf(sample, evsel); if (sample_type & PERF_SAMPLE_REGS_USER) regs_user__printf(sample, arch); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 80e4f6132740..27b123ccd2d1 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -583,21 +583,21 @@ static int hist_entry__sym_ipc_snprintf(struct hist_entry *he, char *bf, { struct symbol *sym = he->ms.sym; - struct annotation *notes; + struct annotated_branch *branch; double ipc = 0.0, coverage = 0.0; char tmp[64]; if (!sym) return repsep_snprintf(bf, size, "%-*s", width, "-"); - notes = symbol__annotation(sym); + branch = symbol__annotation(sym)->branch; - if (notes->hit_cycles) - ipc = notes->hit_insn / ((double)notes->hit_cycles); + if (branch && branch->hit_cycles) + ipc = branch->hit_insn / ((double)branch->hit_cycles); - if (notes->total_insn) { - coverage = notes->cover_insn * 100.0 / - ((double)notes->total_insn); + if (branch && branch->total_insn) { + coverage = branch->cover_insn * 100.0 / + ((double)branch->total_insn); } snprintf(tmp, sizeof(tmp), "%-5.2f [%5.1f%%]", ipc, coverage); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index afe6db8e7bf4..8c61f8627ebc 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -898,7 +898,7 @@ static bool hybrid_uniquify(struct evsel *evsel, struct perf_stat_config *config static void uniquify_counter(struct perf_stat_config *config, struct evsel *counter) { - if (config->no_merge || hybrid_uniquify(counter, config)) + if (config->aggr_mode == AGGR_NONE || hybrid_uniquify(counter, config)) uniquify_event_name(counter); } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index ec3506042217..b0bcf92f0f9c 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -315,7 +315,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals, if (!counter->per_pkg) return 0; - if (perf_cpu_map__empty(cpus)) + if (perf_cpu_map__has_any_cpu_or_is_empty(cpus)) return 0; if (!mask) { @@ -592,7 +592,7 @@ void perf_stat_merge_counters(struct perf_stat_config *config, struct evlist *ev { struct evsel *evsel; - if (config->no_merge) + if (config->aggr_mode == AGGR_NONE) return; evlist__for_each_entry(evlist, evsel) diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 325d0fad1842..4357ba114822 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -76,7 +76,6 @@ struct perf_stat_config { bool null_run; bool ru_display; bool big_num; - bool no_merge; bool hybrid_merge; bool walltime_run_table; bool all_kernel; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 9e7eeaf616b8..4b934ed3bfd1 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1392,8 +1392,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, map__set_start(map, shdr->sh_addr + ref_reloc(kmap)); map__set_end(map, map__start(map) + shdr->sh_size); map__set_pgoff(map, shdr->sh_offset); - map__set_map_ip(map, map__dso_map_ip); - map__set_unmap_ip(map, map__dso_unmap_ip); + map__set_mapping_type(map, MAPPING_TYPE__DSO); /* Ensure maps are correctly ordered */ if (kmaps) { int err; @@ -1455,8 +1454,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, map__set_end(curr_map, map__start(curr_map) + shdr->sh_size); map__set_pgoff(curr_map, shdr->sh_offset); } else { - map__set_map_ip(curr_map, identity__map_ip); - map__set_unmap_ip(curr_map, identity__map_ip); + map__set_mapping_type(curr_map, MAPPING_TYPE__IDENTITY); } curr_dso->symtab_type = dso->symtab_type; if (maps__insert(kmaps, curr_map)) diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index a81a14769bd1..1da8b713509c 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -159,9 +159,10 @@ int filename__read_build_id(const char *filename, struct build_id *bid) goto out_free; ret = read_build_id(buf, buf_size, bid, need_swap); - if (ret == 0) + if (ret == 0) { ret = bid->size; - break; + break; + } } } else { Elf64_Ehdr ehdr; @@ -210,9 +211,10 @@ int filename__read_build_id(const char *filename, struct build_id *bid) goto out_free; ret = read_build_id(buf, buf_size, bid, need_swap); - if (ret == 0) + if (ret == 0) { ret = bid->size; - break; + break; + } } } out_free: diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 82cc74b9358e..72f03b875478 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -48,11 +48,6 @@ static bool symbol__is_idle(const char *name); int vmlinux_path__nr_entries; char **vmlinux_path; -struct map_list_node { - struct list_head node; - struct map *map; -}; - struct symbol_conf symbol_conf = { .nanosecs = false, .use_modules = true, @@ -90,11 +85,6 @@ static enum dso_binary_type binary_type_symtab[] = { #define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab) -static struct map_list_node *map_list_node__new(void) -{ - return malloc(sizeof(struct map_list_node)); -} - static bool symbol_type__filter(char symbol_type) { symbol_type = toupper(symbol_type); @@ -270,29 +260,6 @@ void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms) curr->end = roundup(curr->start, 4096) + 4096; } -void maps__fixup_end(struct maps *maps) -{ - struct map_rb_node *prev = NULL, *curr; - - down_write(maps__lock(maps)); - - maps__for_each_entry(maps, curr) { - if (prev != NULL && !map__end(prev->map)) - map__set_end(prev->map, map__start(curr->map)); - - prev = curr; - } - - /* - * We still haven't the actual symbols, so guess the - * last map final address. - */ - if (curr && !map__end(curr->map)) - map__set_end(curr->map, ~0ULL); - - up_write(maps__lock(maps)); -} - struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name) { size_t namelen = strlen(name) + 1; @@ -956,8 +923,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, return -1; } - map__set_map_ip(curr_map, identity__map_ip); - map__set_unmap_ip(curr_map, identity__map_ip); + map__set_mapping_type(curr_map, MAPPING_TYPE__IDENTITY); if (maps__insert(kmaps, curr_map)) { dso__put(ndso); return -1; @@ -1148,33 +1114,35 @@ out_delete_from: return ret; } +static int do_validate_kcore_modules_cb(struct map *old_map, void *data) +{ + struct rb_root *modules = data; + struct module_info *mi; + struct dso *dso; + + if (!__map__is_kmodule(old_map)) + return 0; + + dso = map__dso(old_map); + /* Module must be in memory at the same address */ + mi = find_module(dso->short_name, modules); + if (!mi || mi->start != map__start(old_map)) + return -EINVAL; + + return 0; +} + static int do_validate_kcore_modules(const char *filename, struct maps *kmaps) { struct rb_root modules = RB_ROOT; - struct map_rb_node *old_node; int err; err = read_proc_modules(filename, &modules); if (err) return err; - maps__for_each_entry(kmaps, old_node) { - struct map *old_map = old_node->map; - struct module_info *mi; - struct dso *dso; + err = maps__for_each_map(kmaps, do_validate_kcore_modules_cb, &modules); - if (!__map__is_kmodule(old_map)) { - continue; - } - dso = map__dso(old_map); - /* Module must be in memory at the same address */ - mi = find_module(dso->short_name, &modules); - if (!mi || mi->start != map__start(old_map)) { - err = -EINVAL; - goto out; - } - } -out: delete_modules(&modules); return err; } @@ -1271,103 +1239,6 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data) return 0; } -/* - * Merges map into maps by splitting the new map within the existing map - * regions. - */ -int maps__merge_in(struct maps *kmaps, struct map *new_map) -{ - struct map_rb_node *rb_node; - LIST_HEAD(merged); - int err = 0; - - maps__for_each_entry(kmaps, rb_node) { - struct map *old_map = rb_node->map; - - /* no overload with this one */ - if (map__end(new_map) < map__start(old_map) || - map__start(new_map) >= map__end(old_map)) - continue; - - if (map__start(new_map) < map__start(old_map)) { - /* - * |new...... - * |old.... - */ - if (map__end(new_map) < map__end(old_map)) { - /* - * |new......| -> |new..| - * |old....| -> |old....| - */ - map__set_end(new_map, map__start(old_map)); - } else { - /* - * |new.............| -> |new..| |new..| - * |old....| -> |old....| - */ - struct map_list_node *m = map_list_node__new(); - - if (!m) { - err = -ENOMEM; - goto out; - } - - m->map = map__clone(new_map); - if (!m->map) { - free(m); - err = -ENOMEM; - goto out; - } - - map__set_end(m->map, map__start(old_map)); - list_add_tail(&m->node, &merged); - map__add_pgoff(new_map, map__end(old_map) - map__start(new_map)); - map__set_start(new_map, map__end(old_map)); - } - } else { - /* - * |new...... - * |old.... - */ - if (map__end(new_map) < map__end(old_map)) { - /* - * |new..| -> x - * |old.........| -> |old.........| - */ - map__put(new_map); - new_map = NULL; - break; - } else { - /* - * |new......| -> |new...| - * |old....| -> |old....| - */ - map__add_pgoff(new_map, map__end(old_map) - map__start(new_map)); - map__set_start(new_map, map__end(old_map)); - } - } - } - -out: - while (!list_empty(&merged)) { - struct map_list_node *old_node; - - old_node = list_entry(merged.next, struct map_list_node, node); - list_del_init(&old_node->node); - if (!err) - err = maps__insert(kmaps, old_node->map); - map__put(old_node->map); - free(old_node); - } - - if (new_map) { - if (!err) - err = maps__insert(kmaps, new_map); - map__put(new_map); - } - return err; -} - static int dso__load_kcore(struct dso *dso, struct map *map, const char *kallsyms_filename) { @@ -1475,8 +1346,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, map__set_start(map, map__start(new_map)); map__set_end(map, map__end(new_map)); map__set_pgoff(map, map__pgoff(new_map)); - map__set_map_ip(map, map__map_ip_ptr(new_map)); - map__set_unmap_ip(map, map__unmap_ip_ptr(new_map)); + map__set_mapping_type(map, map__mapping_type(new_map)); /* Ensure maps are correctly ordered */ map_ref = map__get(map); maps__remove(kmaps, map_ref); @@ -2067,124 +1937,6 @@ out: return ret; } -static int map__strcmp(const void *a, const void *b) -{ - const struct map *map_a = *(const struct map **)a; - const struct map *map_b = *(const struct map **)b; - const struct dso *dso_a = map__dso(map_a); - const struct dso *dso_b = map__dso(map_b); - int ret = strcmp(dso_a->short_name, dso_b->short_name); - - if (ret == 0 && map_a != map_b) { - /* - * Ensure distinct but name equal maps have an order in part to - * aid reference counting. - */ - ret = (int)map__start(map_a) - (int)map__start(map_b); - if (ret == 0) - ret = (int)((intptr_t)map_a - (intptr_t)map_b); - } - - return ret; -} - -static int map__strcmp_name(const void *name, const void *b) -{ - const struct dso *dso = map__dso(*(const struct map **)b); - - return strcmp(name, dso->short_name); -} - -void __maps__sort_by_name(struct maps *maps) -{ - qsort(maps__maps_by_name(maps), maps__nr_maps(maps), sizeof(struct map *), map__strcmp); -} - -static int map__groups__sort_by_name_from_rbtree(struct maps *maps) -{ - struct map_rb_node *rb_node; - struct map **maps_by_name = realloc(maps__maps_by_name(maps), - maps__nr_maps(maps) * sizeof(struct map *)); - int i = 0; - - if (maps_by_name == NULL) - return -1; - - up_read(maps__lock(maps)); - down_write(maps__lock(maps)); - - RC_CHK_ACCESS(maps)->maps_by_name = maps_by_name; - RC_CHK_ACCESS(maps)->nr_maps_allocated = maps__nr_maps(maps); - - maps__for_each_entry(maps, rb_node) - maps_by_name[i++] = map__get(rb_node->map); - - __maps__sort_by_name(maps); - - up_write(maps__lock(maps)); - down_read(maps__lock(maps)); - - return 0; -} - -static struct map *__maps__find_by_name(struct maps *maps, const char *name) -{ - struct map **mapp; - - if (maps__maps_by_name(maps) == NULL && - map__groups__sort_by_name_from_rbtree(maps)) - return NULL; - - mapp = bsearch(name, maps__maps_by_name(maps), maps__nr_maps(maps), - sizeof(*mapp), map__strcmp_name); - if (mapp) - return *mapp; - return NULL; -} - -struct map *maps__find_by_name(struct maps *maps, const char *name) -{ - struct map_rb_node *rb_node; - struct map *map; - - down_read(maps__lock(maps)); - - - if (RC_CHK_ACCESS(maps)->last_search_by_name) { - const struct dso *dso = map__dso(RC_CHK_ACCESS(maps)->last_search_by_name); - - if (strcmp(dso->short_name, name) == 0) { - map = RC_CHK_ACCESS(maps)->last_search_by_name; - goto out_unlock; - } - } - /* - * If we have maps->maps_by_name, then the name isn't in the rbtree, - * as maps->maps_by_name mirrors the rbtree when lookups by name are - * made. - */ - map = __maps__find_by_name(maps, name); - if (map || maps__maps_by_name(maps) != NULL) - goto out_unlock; - - /* Fallback to traversing the rbtree... */ - maps__for_each_entry(maps, rb_node) { - struct dso *dso; - - map = rb_node->map; - dso = map__dso(map); - if (strcmp(dso->short_name, name) == 0) { - RC_CHK_ACCESS(maps)->last_search_by_name = map; - goto out_unlock; - } - } - map = NULL; - -out_unlock: - up_read(maps__lock(maps)); - return map; -} - int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) { diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index af87c46b3f89..071837ddce2a 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -189,7 +189,6 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym, void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root_cached *symbols); void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms); -void maps__fixup_end(struct maps *maps); typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data); int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data, diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index 0b589570d1d0..6040286e07a6 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -42,7 +42,9 @@ struct symbol_conf { inline_name, disable_add2line_warn, buildid_mmap2, - guest_code; + guest_code, + lazy_load_kernel_maps, + keep_exited_threads; const char *vmlinux_name, *kallsyms_name, *source_prefix, diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index a0579c7d7b9e..3712186353fb 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -665,18 +665,74 @@ int perf_event__synthesize_cgroups(struct perf_tool *tool __maybe_unused, } #endif +struct perf_event__synthesize_modules_maps_cb_args { + struct perf_tool *tool; + perf_event__handler_t process; + struct machine *machine; + union perf_event *event; +}; + +static int perf_event__synthesize_modules_maps_cb(struct map *map, void *data) +{ + struct perf_event__synthesize_modules_maps_cb_args *args = data; + union perf_event *event = args->event; + struct dso *dso; + size_t size; + + if (!__map__is_kmodule(map)) + return 0; + + dso = map__dso(map); + if (symbol_conf.buildid_mmap2) { + size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64)); + event->mmap2.header.type = PERF_RECORD_MMAP2; + event->mmap2.header.size = (sizeof(event->mmap2) - + (sizeof(event->mmap2.filename) - size)); + memset(event->mmap2.filename + size, 0, args->machine->id_hdr_size); + event->mmap2.header.size += args->machine->id_hdr_size; + event->mmap2.start = map__start(map); + event->mmap2.len = map__size(map); + event->mmap2.pid = args->machine->pid; + + memcpy(event->mmap2.filename, dso->long_name, dso->long_name_len + 1); + + perf_record_mmap2__read_build_id(&event->mmap2, args->machine, false); + } else { + size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64)); + event->mmap.header.type = PERF_RECORD_MMAP; + event->mmap.header.size = (sizeof(event->mmap) - + (sizeof(event->mmap.filename) - size)); + memset(event->mmap.filename + size, 0, args->machine->id_hdr_size); + event->mmap.header.size += args->machine->id_hdr_size; + event->mmap.start = map__start(map); + event->mmap.len = map__size(map); + event->mmap.pid = args->machine->pid; + + memcpy(event->mmap.filename, dso->long_name, dso->long_name_len + 1); + } + + if (perf_tool__process_synth_event(args->tool, event, args->machine, args->process) != 0) + return -1; + + return 0; +} + int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine) { - int rc = 0; - struct map_rb_node *pos; + int rc; struct maps *maps = machine__kernel_maps(machine); - union perf_event *event; - size_t size = symbol_conf.buildid_mmap2 ? - sizeof(event->mmap2) : sizeof(event->mmap); + struct perf_event__synthesize_modules_maps_cb_args args = { + .tool = tool, + .process = process, + .machine = machine, + }; + size_t size = symbol_conf.buildid_mmap2 + ? sizeof(args.event->mmap2) + : sizeof(args.event->mmap); - event = zalloc(size + machine->id_hdr_size); - if (event == NULL) { + args.event = zalloc(size + machine->id_hdr_size); + if (args.event == NULL) { pr_debug("Not enough memory synthesizing mmap event " "for kernel modules\n"); return -1; @@ -687,53 +743,13 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t * __perf_event_mmap */ if (machine__is_host(machine)) - event->header.misc = PERF_RECORD_MISC_KERNEL; + args.event->header.misc = PERF_RECORD_MISC_KERNEL; else - event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; - - maps__for_each_entry(maps, pos) { - struct map *map = pos->map; - struct dso *dso; + args.event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; - if (!__map__is_kmodule(map)) - continue; + rc = maps__for_each_map(maps, perf_event__synthesize_modules_maps_cb, &args); - dso = map__dso(map); - if (symbol_conf.buildid_mmap2) { - size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64)); - event->mmap2.header.type = PERF_RECORD_MMAP2; - event->mmap2.header.size = (sizeof(event->mmap2) - - (sizeof(event->mmap2.filename) - size)); - memset(event->mmap2.filename + size, 0, machine->id_hdr_size); - event->mmap2.header.size += machine->id_hdr_size; - event->mmap2.start = map__start(map); - event->mmap2.len = map__size(map); - event->mmap2.pid = machine->pid; - - memcpy(event->mmap2.filename, dso->long_name, dso->long_name_len + 1); - - perf_record_mmap2__read_build_id(&event->mmap2, machine, false); - } else { - size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64)); - event->mmap.header.type = PERF_RECORD_MMAP; - event->mmap.header.size = (sizeof(event->mmap) - - (sizeof(event->mmap.filename) - size)); - memset(event->mmap.filename + size, 0, machine->id_hdr_size); - event->mmap.header.size += machine->id_hdr_size; - event->mmap.start = map__start(map); - event->mmap.len = map__size(map); - event->mmap.pid = machine->pid; - - memcpy(event->mmap.filename, dso->long_name, dso->long_name_len + 1); - } - - if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { - rc = -1; - break; - } - } - - free(event); + free(args.event); return rc; } diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index fe5e6991ae4b..b6986a81aa6d 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -349,34 +349,33 @@ int thread__insert_map(struct thread *thread, struct map *map) return maps__insert(thread__maps(thread), map); } -static int __thread__prepare_access(struct thread *thread) +struct thread__prepare_access_maps_cb_args { + int err; + struct maps *maps; +}; + +static int thread__prepare_access_maps_cb(struct map *map, void *data) { bool initialized = false; - int err = 0; - struct maps *maps = thread__maps(thread); - struct map_rb_node *rb_node; - - down_read(maps__lock(maps)); - - maps__for_each_entry(maps, rb_node) { - err = unwind__prepare_access(thread__maps(thread), rb_node->map, &initialized); - if (err || initialized) - break; - } + struct thread__prepare_access_maps_cb_args *args = data; - up_read(maps__lock(maps)); + args->err = unwind__prepare_access(args->maps, map, &initialized); - return err; + return (args->err || initialized) ? 1 : 0; } static int thread__prepare_access(struct thread *thread) { - int err = 0; + struct thread__prepare_access_maps_cb_args args = { + .err = 0, + }; - if (dwarf_callchain_users) - err = __thread__prepare_access(thread); + if (dwarf_callchain_users) { + args.maps = thread__maps(thread); + maps__for_each_map(thread__maps(thread), thread__prepare_access_maps_cb, &args); + } - return err; + return args.err; } static int thread__clone_maps(struct thread *thread, struct thread *parent, bool do_maps_clone) @@ -385,7 +384,7 @@ static int thread__clone_maps(struct thread *thread, struct thread *parent, bool if (thread__pid(thread) == thread__pid(parent)) return thread__prepare_access(thread); - if (thread__maps(thread) == thread__maps(parent)) { + if (RC_CHK_EQUAL(thread__maps(thread), thread__maps(parent))) { pr_debug("broken map groups on thread %d/%d parent %d/%d\n", thread__pid(thread), thread__tid(thread), thread__pid(parent), thread__tid(parent)); diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index e79225a0ea46..0df775b5c110 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -36,13 +36,22 @@ struct thread_rb_node { }; DECLARE_RC_STRUCT(thread) { + /** @maps: mmaps associated with this thread. */ struct maps *maps; pid_t pid_; /* Not all tools update this */ + /** @tid: thread ID number unique to a machine. */ pid_t tid; + /** @ppid: parent process of the process this thread belongs to. */ pid_t ppid; int cpu; int guest_cpu; /* For QEMU thread */ refcount_t refcnt; + /** + * @exited: Has the thread had an exit event. Such threads are usually + * removed from the machine's threads but some events/tools require + * access to dead threads. + */ + bool exited; bool comm_set; int comm_len; struct list_head namespaces_list; @@ -189,6 +198,11 @@ static inline refcount_t *thread__refcnt(struct thread *thread) return &RC_CHK_ACCESS(thread)->refcnt; } +static inline void thread__set_exited(struct thread *thread, bool exited) +{ + RC_CHK_ACCESS(thread)->exited = exited; +} + static inline bool thread__comm_set(const struct thread *thread) { return RC_CHK_ACCESS(thread)->comm_set; diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index be7157de0451..4db3d1bd686c 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -28,6 +28,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) struct record_opts *opts = &top->record_opts; struct target *target = &opts->target; size_t ret = 0; + int nr_cpus; if (top->samples) { samples_per_sec = top->samples / top->delay_secs; @@ -93,19 +94,17 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) else ret += SNPRINTF(bf + ret, size - ret, " (all"); + nr_cpus = perf_cpu_map__nr(top->evlist->core.user_requested_cpus); if (target->cpu_list) ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)", - perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1 - ? "s" : "", + nr_cpus > 1 ? "s" : "", target->cpu_list); else { if (target->tid) ret += SNPRINTF(bf + ret, size - ret, ")"); else ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)", - perf_cpu_map__nr(top->evlist->core.user_requested_cpus), - perf_cpu_map__nr(top->evlist->core.user_requested_cpus) > 1 - ? "s" : ""); + nr_cpus, nr_cpus > 1 ? "s" : ""); } perf_top__reset_sample_counters(top); diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index a8b0d79bd96c..4c5588dbb131 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -21,7 +21,6 @@ struct perf_top { struct perf_tool tool; struct evlist *evlist, *sb_evlist; struct record_opts record_opts; - struct annotation_options annotation_opts; struct evswitch evswitch; /* * Symbols will be added here in perf_event__process_sample and will diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 8554db3fc0d7..6013335a8dae 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -46,6 +46,7 @@ static int __report_module(struct addr_location *al, u64 ip, { Dwfl_Module *mod; struct dso *dso = NULL; + Dwarf_Addr base; /* * Some callers will use al->sym, so we can't just use the * cheaper thread__find_map() here. @@ -58,13 +59,25 @@ static int __report_module(struct addr_location *al, u64 ip, if (!dso) return 0; + /* + * The generated JIT DSO files only map the code segment without + * ELF headers. Since JIT codes used to be packed in a memory + * segment, calculating the base address using pgoff falls into + * a different code in another DSO. So just use the map->start + * directly to pick the correct one. + */ + if (!strncmp(dso->long_name, "/tmp/jitted-", 12)) + base = map__start(al->map); + else + base = map__start(al->map) - map__pgoff(al->map); + mod = dwfl_addrmodule(ui->dwfl, ip); if (mod) { Dwarf_Addr s; dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL); - if (s != map__start(al->map) - map__pgoff(al->map)) - mod = 0; + if (s != base) + mod = NULL; } if (!mod) { @@ -72,14 +85,14 @@ static int __report_module(struct addr_location *al, u64 ip, __symbol__join_symfs(filename, sizeof(filename), dso->long_name); mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1, - map__start(al->map) - map__pgoff(al->map), false); + base, false); } if (!mod) { char filename[PATH_MAX]; if (dso__build_id_filename(dso, filename, sizeof(filename), false)) mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1, - map__start(al->map) - map__pgoff(al->map), false); + base, false); } if (mod) { diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index c0641882fd2f..5e5c3395a499 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -327,7 +327,7 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui, maps__for_each_entry(thread__maps(ui->thread), map_node) { struct map *map = map_node->map; - u64 start = map__start(map); + u64 start = map__start(map) - map__pgoff(map); if (map__dso(map) == dso && start < base_addr) base_addr = start; diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c index 48dd2b018c47..57027e0ac7b6 100644 --- a/tools/perf/util/zstd.c +++ b/tools/perf/util/zstd.c @@ -7,35 +7,9 @@ int zstd_init(struct zstd_data *data, int level) { - size_t ret; - - data->dstream = ZSTD_createDStream(); - if (data->dstream == NULL) { - pr_err("Couldn't create decompression stream.\n"); - return -1; - } - - ret = ZSTD_initDStream(data->dstream); - if (ZSTD_isError(ret)) { - pr_err("Failed to initialize decompression stream: %s\n", ZSTD_getErrorName(ret)); - return -1; - } - - if (!level) - return 0; - - data->cstream = ZSTD_createCStream(); - if (data->cstream == NULL) { - pr_err("Couldn't create compression stream.\n"); - return -1; - } - - ret = ZSTD_initCStream(data->cstream, level); - if (ZSTD_isError(ret)) { - pr_err("Failed to initialize compression stream: %s\n", ZSTD_getErrorName(ret)); - return -1; - } - + data->comp_level = level; + data->dstream = NULL; + data->cstream = NULL; return 0; } @@ -54,7 +28,7 @@ int zstd_fini(struct zstd_data *data) return 0; } -size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size, +ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size, void *src, size_t src_size, size_t max_record_size, size_t process_header(void *record, size_t increment)) { @@ -63,6 +37,21 @@ size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t ZSTD_outBuffer output; void *record; + if (!data->cstream) { + data->cstream = ZSTD_createCStream(); + if (data->cstream == NULL) { + pr_err("Couldn't create compression stream.\n"); + return -1; + } + + ret = ZSTD_initCStream(data->cstream, data->comp_level); + if (ZSTD_isError(ret)) { + pr_err("Failed to initialize compression stream: %s\n", + ZSTD_getErrorName(ret)); + return -1; + } + } + while (input.pos < input.size) { record = dst; size = process_header(record, 0); @@ -96,6 +85,20 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size ZSTD_inBuffer input = { src, src_size, 0 }; ZSTD_outBuffer output = { dst, dst_size, 0 }; + if (!data->dstream) { + data->dstream = ZSTD_createDStream(); + if (data->dstream == NULL) { + pr_err("Couldn't create decompression stream.\n"); + return 0; + } + + ret = ZSTD_initDStream(data->dstream); + if (ZSTD_isError(ret)) { + pr_err("Failed to initialize decompression stream: %s\n", + ZSTD_getErrorName(ret)); + return 0; + } + } while (input.pos < input.size) { ret = ZSTD_decompressStream(data->dstream, &output, &input); if (ZSTD_isError(ret)) { |