diff options
Diffstat (limited to '')
-rw-r--r-- | tools/lib/api/fs/fs.c | 80 | ||||
-rw-r--r-- | tools/lib/api/io.h | 12 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.c | 142 | ||||
-rw-r--r-- | tools/lib/perf/Documentation/examples/sampling.c | 2 | ||||
-rw-r--r-- | tools/lib/perf/Documentation/libperf-sampling.txt | 2 | ||||
-rw-r--r-- | tools/lib/perf/Documentation/libperf.txt | 4 | ||||
-rw-r--r-- | tools/lib/perf/cpumap.c | 65 | ||||
-rw-r--r-- | tools/lib/perf/evlist.c | 6 | ||||
-rw-r--r-- | tools/lib/perf/evsel.c | 2 | ||||
-rw-r--r-- | tools/lib/perf/include/internal/mmap.h | 3 | ||||
-rw-r--r-- | tools/lib/perf/include/perf/cpumap.h | 40 | ||||
-rw-r--r-- | tools/lib/perf/libperf.map | 6 | ||||
-rw-r--r-- | tools/lib/perf/mmap.c | 20 | ||||
-rw-r--r-- | tools/lib/perf/tests/test-cpumap.c | 4 | ||||
-rw-r--r-- | tools/lib/perf/tests/test-evlist.c | 6 | ||||
-rw-r--r-- | tools/lib/perf/tests/test-evsel.c | 2 | ||||
-rw-r--r-- | tools/lib/subcmd/help.c | 18 |
17 files changed, 294 insertions, 120 deletions
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/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index c5a42ac309fd..afd09571c482 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -6695,6 +6695,67 @@ static struct { /* all other program types don't have "named" context structs */ }; +static bool need_func_arg_type_fixup(const struct btf *btf, const struct bpf_program *prog, + const char *subprog_name, int arg_idx, + int arg_type_id, const char *ctx_name) +{ + const struct btf_type *t; + const char *tname; + + /* check if existing parameter already matches verifier expectations */ + t = skip_mods_and_typedefs(btf, arg_type_id, NULL); + if (!btf_is_ptr(t)) + goto out_warn; + + /* typedef bpf_user_pt_regs_t is a special PITA case, valid for kprobe + * and perf_event programs, so check this case early on and forget + * about it for subsequent checks + */ + while (btf_is_mod(t)) + t = btf__type_by_id(btf, t->type); + if (btf_is_typedef(t) && + (prog->type == BPF_PROG_TYPE_KPROBE || prog->type == BPF_PROG_TYPE_PERF_EVENT)) { + tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>"; + if (strcmp(tname, "bpf_user_pt_regs_t") == 0) + return false; /* canonical type for kprobe/perf_event */ + } + + /* now we can ignore typedefs moving forward */ + t = skip_mods_and_typedefs(btf, t->type, NULL); + + /* if it's `void *`, definitely fix up BTF info */ + if (btf_is_void(t)) + return true; + + /* if it's already proper canonical type, no need to fix up */ + tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>"; + if (btf_is_struct(t) && strcmp(tname, ctx_name) == 0) + return false; + + /* special cases */ + switch (prog->type) { + case BPF_PROG_TYPE_KPROBE: + case BPF_PROG_TYPE_PERF_EVENT: + /* `struct pt_regs *` is expected, but we need to fix up */ + if (btf_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return true; + break; + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return true; + break; + default: + break; + } + +out_warn: + pr_warn("prog '%s': subprog '%s' arg#%d is expected to be of `struct %s *` type\n", + prog->name, subprog_name, arg_idx, ctx_name); + return false; +} + static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_program *prog) { int fn_id, fn_proto_id, ret_type_id, orig_proto_id; @@ -6757,6 +6818,69 @@ static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_progr return fn_id; } +static int probe_kern_arg_ctx_tag(void) +{ + /* To minimize merge conflicts with BPF token series that refactors + * feature detection code a lot, we don't integrate + * probe_kern_arg_ctx_tag() into kernel_supports() feature-detection + * framework yet, doing our own caching internally. + * This will be cleaned up a bit later when bpf/bpf-next trees settle. + */ + static int cached_result = -1; + static const char strs[] = "\0a\0b\0arg:ctx\0"; + const __u32 types[] = { + /* [1] INT */ + BTF_TYPE_INT_ENC(1 /* "a" */, BTF_INT_SIGNED, 0, 32, 4), + /* [2] PTR -> VOID */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0), + /* [3] FUNC_PROTO `int(void *a)` */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1), + BTF_PARAM_ENC(1 /* "a" */, 2), + /* [4] FUNC 'a' -> FUNC_PROTO (main prog) */ + BTF_TYPE_ENC(1 /* "a" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 3), + /* [5] FUNC_PROTO `int(void *b __arg_ctx)` */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1), + BTF_PARAM_ENC(3 /* "b" */, 2), + /* [6] FUNC 'b' -> FUNC_PROTO (subprog) */ + BTF_TYPE_ENC(3 /* "b" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 5), + /* [7] DECL_TAG 'arg:ctx' -> func 'b' arg 'b' */ + BTF_TYPE_DECL_TAG_ENC(5 /* "arg:ctx" */, 6, 0), + }; + const struct bpf_insn insns[] = { + /* main prog */ + BPF_CALL_REL(+1), + BPF_EXIT_INSN(), + /* global subprog */ + BPF_EMIT_CALL(BPF_FUNC_get_func_ip), /* needs PTR_TO_CTX */ + BPF_EXIT_INSN(), + }; + const struct bpf_func_info_min func_infos[] = { + { 0, 4 }, /* main prog -> FUNC 'a' */ + { 2, 6 }, /* subprog -> FUNC 'b' */ + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts); + int prog_fd, btf_fd, insn_cnt = ARRAY_SIZE(insns); + + if (cached_result >= 0) + return cached_result; + + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs)); + if (btf_fd < 0) + return 0; + + opts.prog_btf_fd = btf_fd; + opts.func_info = &func_infos; + opts.func_info_cnt = ARRAY_SIZE(func_infos); + opts.func_info_rec_size = sizeof(func_infos[0]); + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, "det_arg_ctx", + "GPL", insns, insn_cnt, &opts); + close(btf_fd); + + cached_result = probe_fd(prog_fd); + return cached_result; +} + /* Check if main program or global subprog's function prototype has `arg:ctx` * argument tags, and, if necessary, substitute correct type to match what BPF * verifier would expect, taking into account specific program type. This @@ -6766,7 +6890,7 @@ static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_progr */ static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_program *prog) { - const char *ctx_name = NULL, *ctx_tag = "arg:ctx"; + const char *ctx_name = NULL, *ctx_tag = "arg:ctx", *fn_name; struct bpf_func_info_min *func_rec; struct btf_type *fn_t, *fn_proto_t; struct btf *btf = obj->btf; @@ -6780,6 +6904,10 @@ static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_progra if (!obj->btf_ext || !prog->func_info) return 0; + /* don't do any fix ups if kernel natively supports __arg_ctx */ + if (probe_kern_arg_ctx_tag() > 0) + return 0; + /* some BPF program types just don't have named context structs, so * this fallback mechanism doesn't work for them */ @@ -6842,15 +6970,11 @@ static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_progra if (arg_idx < 0 || arg_idx >= arg_cnt) continue; - /* check if existing parameter already matches verifier expectations */ + /* check if we should fix up argument type */ p = &btf_params(fn_proto_t)[arg_idx]; - t = skip_mods_and_typedefs(btf, p->type, NULL); - if (btf_is_ptr(t) && - (t = skip_mods_and_typedefs(btf, t->type, NULL)) && - btf_is_struct(t) && - strcmp(btf__str_by_offset(btf, t->name_off), ctx_name) == 0) { - continue; /* no need for fix up */ - } + fn_name = btf__str_by_offset(btf, fn_t->name_off) ?: "<anon>"; + if (!need_func_arg_type_fixup(btf, prog, fn_name, arg_idx, p->type, ctx_name)) + continue; /* clone fn/fn_proto, unless we already did it for another arg */ if (func_rec->type_id == orig_fn_id) { 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/lib/subcmd/help.c b/tools/lib/subcmd/help.c index adfbae27dc36..8561b0f01a24 100644 --- a/tools/lib/subcmd/help.c +++ b/tools/lib/subcmd/help.c @@ -52,11 +52,21 @@ void uniq(struct cmdnames *cmds) if (!cmds->cnt) return; - for (i = j = 1; i < cmds->cnt; i++) - if (strcmp(cmds->names[i]->name, cmds->names[i-1]->name)) - cmds->names[j++] = cmds->names[i]; - + for (i = 1; i < cmds->cnt; i++) { + if (!strcmp(cmds->names[i]->name, cmds->names[i-1]->name)) + zfree(&cmds->names[i - 1]); + } + for (i = 0, j = 0; i < cmds->cnt; i++) { + if (cmds->names[i]) { + if (i == j) + j++; + else + cmds->names[j++] = cmds->names[i]; + } + } cmds->cnt = j; + while (j < i) + cmds->names[j++] = NULL; } void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes) |