diff options
Diffstat (limited to 'tools/lib/bpf/libbpf.c')
| -rw-r--r-- | tools/lib/bpf/libbpf.c | 910 |
1 files changed, 664 insertions, 246 deletions
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index a27f6e9ccce7..96ff1aa4bf6a 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -118,6 +118,9 @@ static const char * const attach_type_name[] = { [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", [BPF_STRUCT_OPS] = "struct_ops", [BPF_NETFILTER] = "netfilter", + [BPF_TCX_INGRESS] = "tcx_ingress", + [BPF_TCX_EGRESS] = "tcx_egress", + [BPF_TRACE_UPROBE_MULTI] = "trace_uprobe_multi", }; static const char * const link_type_name[] = { @@ -132,6 +135,8 @@ static const char * const link_type_name[] = { [BPF_LINK_TYPE_KPROBE_MULTI] = "kprobe_multi", [BPF_LINK_TYPE_STRUCT_OPS] = "struct_ops", [BPF_LINK_TYPE_NETFILTER] = "netfilter", + [BPF_LINK_TYPE_TCX] = "tcx", + [BPF_LINK_TYPE_UPROBE_MULTI] = "uprobe_multi", }; static const char * const map_type_name[] = { @@ -362,6 +367,8 @@ enum sec_def_flags { SEC_SLEEPABLE = 8, /* BPF program support non-linear XDP buffer */ SEC_XDP_FRAGS = 16, + /* Setup proper attach type for usdt probes. */ + SEC_USDT = 32, }; struct bpf_sec_def { @@ -547,6 +554,7 @@ struct extern_desc { int btf_id; int sec_btf_id; const char *name; + char *essent_name; bool is_set; bool is_weak; union { @@ -1501,16 +1509,36 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) return map; } -static size_t bpf_map_mmap_sz(const struct bpf_map *map) +static size_t bpf_map_mmap_sz(unsigned int value_sz, unsigned int max_entries) { - long page_sz = sysconf(_SC_PAGE_SIZE); + const long page_sz = sysconf(_SC_PAGE_SIZE); size_t map_sz; - map_sz = (size_t)roundup(map->def.value_size, 8) * map->def.max_entries; + map_sz = (size_t)roundup(value_sz, 8) * max_entries; map_sz = roundup(map_sz, page_sz); return map_sz; } +static int bpf_map_mmap_resize(struct bpf_map *map, size_t old_sz, size_t new_sz) +{ + void *mmaped; + + if (!map->mmaped) + return -EINVAL; + + if (old_sz == new_sz) + return 0; + + mmaped = mmap(NULL, new_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (mmaped == MAP_FAILED) + return -errno; + + memcpy(mmaped, map->mmaped, min(old_sz, new_sz)); + munmap(map->mmaped, old_sz); + map->mmaped = mmaped; + return 0; +} + static char *internal_map_name(struct bpf_object *obj, const char *real_name) { char map_name[BPF_OBJ_NAME_LEN], *p; @@ -1609,6 +1637,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, { struct bpf_map_def *def; struct bpf_map *map; + size_t mmap_sz; int err; map = bpf_object__add_map(obj); @@ -1643,7 +1672,8 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n", map->name, map->sec_idx, map->sec_offset, def->map_flags); - map->mmaped = mmap(NULL, bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE, + mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); + map->mmaped = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); if (map->mmaped == MAP_FAILED) { err = -errno; @@ -1953,9 +1983,9 @@ static int bpf_object__read_kconfig_file(struct bpf_object *obj, void *data) return -ENAMETOOLONG; /* gzopen also accepts uncompressed files. */ - file = gzopen(buf, "r"); + file = gzopen(buf, "re"); if (!file) - file = gzopen("/proc/config.gz", "r"); + file = gzopen("/proc/config.gz", "re"); if (!file) { pr_warn("failed to open system Kconfig\n"); @@ -3745,6 +3775,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj) struct extern_desc *ext; int i, n, off, dummy_var_btf_id; const char *ext_name, *sec_name; + size_t ext_essent_len; Elf_Scn *scn; Elf64_Shdr *sh; @@ -3794,6 +3825,14 @@ static int bpf_object__collect_externs(struct bpf_object *obj) ext->sym_idx = i; ext->is_weak = ELF64_ST_BIND(sym->st_info) == STB_WEAK; + ext_essent_len = bpf_core_essential_name_len(ext->name); + ext->essent_name = NULL; + if (ext_essent_len != strlen(ext->name)) { + ext->essent_name = strndup(ext->name, ext_essent_len); + if (!ext->essent_name) + return -ENOMEM; + } + ext->sec_btf_id = find_extern_sec_btf_id(obj->btf, ext->btf_id); if (ext->sec_btf_id <= 0) { pr_warn("failed to find BTF for extern '%s' [%d] section: %d\n", @@ -4330,7 +4369,7 @@ static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info) snprintf(file, sizeof(file), "/proc/%d/fdinfo/%d", getpid(), fd); memset(info, 0, sizeof(*info)); - fp = fopen(file, "r"); + fp = fopen(file, "re"); if (!fp) { err = -errno; pr_warn("failed to open %s: %d. No procfs support?\n", file, @@ -4393,18 +4432,17 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) if (!new_name) return libbpf_err(-errno); - new_fd = open("/", O_RDONLY | O_CLOEXEC); + /* + * Like dup(), but make sure new FD is >= 3 and has O_CLOEXEC set. + * This is similar to what we do in ensure_good_fd(), but without + * closing original FD. + */ + new_fd = fcntl(fd, F_DUPFD_CLOEXEC, 3); if (new_fd < 0) { err = -errno; goto err_free_new_name; } - new_fd = dup3(fd, new_fd, O_CLOEXEC); - if (new_fd < 0) { - err = -errno; - goto err_close_new_fd; - } - err = zclose(map->fd); if (err) { err = -errno; @@ -4793,6 +4831,39 @@ static int probe_perf_link(void) return link_fd < 0 && err == -EBADF; } +static int probe_uprobe_multi_link(void) +{ + LIBBPF_OPTS(bpf_prog_load_opts, load_opts, + .expected_attach_type = BPF_TRACE_UPROBE_MULTI, + ); + LIBBPF_OPTS(bpf_link_create_opts, link_opts); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int prog_fd, link_fd, err; + unsigned long offset = 0; + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", + insns, ARRAY_SIZE(insns), &load_opts); + if (prog_fd < 0) + return -errno; + + /* Creating uprobe in '/' binary should fail with -EBADF. */ + link_opts.uprobe_multi.path = "/"; + link_opts.uprobe_multi.offsets = &offset; + link_opts.uprobe_multi.cnt = 1; + + link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + + return link_fd < 0 && err == -EBADF; +} + static int probe_kern_bpf_cookie(void) { struct bpf_insn insns[] = { @@ -4889,6 +4960,9 @@ static struct kern_feature_desc { [FEAT_SYSCALL_WRAPPER] = { "Kernel using syscall wrapper", probe_kern_syscall_wrapper, }, + [FEAT_UPROBE_MULTI_LINK] = { + "BPF multi-uprobe link support", probe_uprobe_multi_link, + }, }; bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) @@ -5450,6 +5524,10 @@ static int load_module_btfs(struct bpf_object *obj) err = bpf_btf_get_next_id(id, &id); if (err && errno == ENOENT) return 0; + if (err && errno == EPERM) { + pr_debug("skipping module BTFs loading, missing privileges\n"); + return 0; + } if (err) { err = -errno; pr_warn("failed to iterate BTF objects: %d\n", err); @@ -6136,7 +6214,11 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra if (main_prog == subprog) return 0; relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos)); - if (!relos) + /* if new count is zero, reallocarray can return a valid NULL result; + * in this case the previous pointer will be freed, so we *have to* + * reassign old pointer to the new value (even if it's NULL) + */ + if (!relos && new_cnt) return -ENOMEM; if (subprog->nr_reloc) memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc, @@ -6748,6 +6830,10 @@ static int libbpf_prepare_prog_load(struct bpf_program *prog, if (prog->type == BPF_PROG_TYPE_XDP && (def & SEC_XDP_FRAGS)) opts->prog_flags |= BPF_F_XDP_HAS_FRAGS; + /* special check for usdt to use uprobe_multi link */ + if ((def & SEC_USDT) && kernel_supports(prog->obj, FEAT_UPROBE_MULTI_LINK)) + prog->expected_attach_type = BPF_TRACE_UPROBE_MULTI; + if ((def & SEC_ATTACH_BTF) && !prog->attach_btf_id) { int btf_obj_fd = 0, btf_type_id = 0, err; const char *attach_name; @@ -6816,7 +6902,6 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog if (!insns || !insns_cnt) return -EINVAL; - load_attr.expected_attach_type = prog->expected_attach_type; if (kernel_supports(obj, FEAT_PROG_NAME)) prog_name = prog->name; load_attr.attach_prog_fd = prog->attach_prog_fd; @@ -6852,6 +6937,9 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog insns_cnt = prog->insns_cnt; } + /* allow prog_prepare_load_fn to change expected_attach_type */ + load_attr.expected_attach_type = prog->expected_attach_type; + if (obj->gen_loader) { bpf_gen__prog_load(obj->gen_loader, prog->type, prog->name, license, insns, insns_cnt, &load_attr, @@ -7434,7 +7522,7 @@ int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx) int ret, err = 0; FILE *f; - f = fopen("/proc/kallsyms", "r"); + f = fopen("/proc/kallsyms", "re"); if (!f) { err = -errno; pr_warn("failed to open /proc/kallsyms: %d\n", err); @@ -7592,7 +7680,8 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj, local_func_proto_id = ext->ksym.type_id; - kfunc_id = find_ksym_btf_id(obj, ext->name, BTF_KIND_FUNC, &kern_btf, &mod_btf); + kfunc_id = find_ksym_btf_id(obj, ext->essent_name ?: ext->name, BTF_KIND_FUNC, &kern_btf, + &mod_btf); if (kfunc_id < 0) { if (kfunc_id == -ESRCH && ext->is_weak) return 0; @@ -7607,6 +7696,9 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj, ret = bpf_core_types_are_compat(obj->btf, local_func_proto_id, kern_btf, kfunc_proto_id); if (ret <= 0) { + if (ext->is_weak) + return 0; + pr_warn("extern (func ksym) '%s': func_proto [%d] incompatible with %s [%d]\n", ext->name, local_func_proto_id, mod_btf ? mod_btf->name : "vmlinux", kfunc_proto_id); @@ -8284,6 +8376,21 @@ int bpf_object__pin(struct bpf_object *obj, const char *path) return 0; } +int bpf_object__unpin(struct bpf_object *obj, const char *path) +{ + int err; + + err = bpf_object__unpin_programs(obj, path); + if (err) + return libbpf_err(err); + + err = bpf_object__unpin_maps(obj, path); + if (err) + return libbpf_err(err); + + return 0; +} + static void bpf_map__destroy(struct bpf_map *map) { if (map->inner_map) { @@ -8295,7 +8402,10 @@ static void bpf_map__destroy(struct bpf_map *map) map->init_slots_sz = 0; if (map->mmaped) { - munmap(map->mmaped, bpf_map_mmap_sz(map)); + size_t mmap_sz; + + mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); + munmap(map->mmaped, mmap_sz); map->mmaped = NULL; } @@ -8328,6 +8438,7 @@ void bpf_object__close(struct bpf_object *obj) bpf_object__elf_finish(obj); bpf_object_unload(obj); btf__free(obj->btf); + btf__free(obj->btf_vmlinux); btf_ext__free(obj->btf_ext); for (i = 0; i < obj->nr_maps; i++) @@ -8335,6 +8446,10 @@ void bpf_object__close(struct bpf_object *obj) zfree(&obj->btf_custom_path); zfree(&obj->kconfig); + + for (i = 0; i < obj->nr_extern; i++) + zfree(&obj->externs[i].essent_name); + zfree(&obj->externs); obj->nr_extern = 0; @@ -8504,7 +8619,8 @@ int bpf_program__set_insns(struct bpf_program *prog, return -EBUSY; insns = libbpf_reallocarray(prog->insns, new_insn_cnt, sizeof(*insns)); - if (!insns) { + /* NULL is a valid return from reallocarray if the new count is zero */ + if (!insns && new_insn_cnt) { pr_warn("prog '%s': failed to realloc prog code\n", prog->name); return -ENOMEM; } @@ -8534,13 +8650,31 @@ enum bpf_prog_type bpf_program__type(const struct bpf_program *prog) return prog->type; } +static size_t custom_sec_def_cnt; +static struct bpf_sec_def *custom_sec_defs; +static struct bpf_sec_def custom_fallback_def; +static bool has_custom_fallback_def; +static int last_custom_sec_def_handler_id; + int bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) { if (prog->obj->loaded) return libbpf_err(-EBUSY); + /* if type is not changed, do nothing */ + if (prog->type == type) + return 0; + prog->type = type; - prog->sec_def = NULL; + + /* If a program type was changed, we need to reset associated SEC() + * handler, as it will be invalid now. The only exception is a generic + * fallback handler, which by definition is program type-agnostic and + * is a catch-all custom handler, optionally set by the application, + * so should be able to handle any type of BPF program. + */ + if (prog->sec_def != &custom_fallback_def) + prog->sec_def = NULL; return 0; } @@ -8627,6 +8761,7 @@ static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_lin static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link); @@ -8642,12 +8777,21 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("uretprobe.s+", KPROBE, 0, SEC_SLEEPABLE, attach_uprobe), SEC_DEF("kprobe.multi+", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), SEC_DEF("kretprobe.multi+", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), + SEC_DEF("uprobe.multi+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi), + SEC_DEF("uretprobe.multi+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi), + SEC_DEF("uprobe.multi.s+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_SLEEPABLE, attach_uprobe_multi), + SEC_DEF("uretprobe.multi.s+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_SLEEPABLE, attach_uprobe_multi), SEC_DEF("ksyscall+", KPROBE, 0, SEC_NONE, attach_ksyscall), SEC_DEF("kretsyscall+", KPROBE, 0, SEC_NONE, attach_ksyscall), - SEC_DEF("usdt+", KPROBE, 0, SEC_NONE, attach_usdt), - SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), - SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE), - SEC_DEF("action", SCHED_ACT, 0, SEC_NONE), + SEC_DEF("usdt+", KPROBE, 0, SEC_USDT, attach_usdt), + SEC_DEF("usdt.s+", KPROBE, 0, SEC_USDT | SEC_SLEEPABLE, attach_usdt), + SEC_DEF("tc/ingress", SCHED_CLS, BPF_TCX_INGRESS, SEC_NONE), /* alias for tcx */ + SEC_DEF("tc/egress", SCHED_CLS, BPF_TCX_EGRESS, SEC_NONE), /* alias for tcx */ + SEC_DEF("tcx/ingress", SCHED_CLS, BPF_TCX_INGRESS, SEC_NONE), + SEC_DEF("tcx/egress", SCHED_CLS, BPF_TCX_EGRESS, SEC_NONE), + SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */ + SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */ + SEC_DEF("action", SCHED_ACT, 0, SEC_NONE), /* deprecated / legacy, use tcx */ SEC_DEF("tracepoint+", TRACEPOINT, 0, SEC_NONE, attach_tp), SEC_DEF("tp+", TRACEPOINT, 0, SEC_NONE, attach_tp), SEC_DEF("raw_tracepoint+", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), @@ -8716,13 +8860,6 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("netfilter", NETFILTER, BPF_NETFILTER, SEC_NONE), }; -static size_t custom_sec_def_cnt; -static struct bpf_sec_def *custom_sec_defs; -static struct bpf_sec_def custom_fallback_def; -static bool has_custom_fallback_def; - -static int last_custom_sec_def_handler_id; - int libbpf_register_prog_handler(const char *sec, enum bpf_prog_type prog_type, enum bpf_attach_type exp_attach_type, @@ -8802,7 +8939,11 @@ int libbpf_unregister_prog_handler(int handler_id) /* try to shrink the array, but it's ok if we couldn't */ sec_defs = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt, sizeof(*sec_defs)); - if (sec_defs) + /* if new count is zero, reallocarray can return a valid NULL result; + * in this case the previous pointer will be freed, so we *have to* + * reassign old pointer to the new value (even if it's NULL) + */ + if (sec_defs || custom_sec_def_cnt == 0) custom_sec_defs = sec_defs; return 0; @@ -9413,10 +9554,103 @@ __u32 bpf_map__value_size(const struct bpf_map *map) return map->def.value_size; } +static int map_btf_datasec_resize(struct bpf_map *map, __u32 size) +{ + struct btf *btf; + struct btf_type *datasec_type, *var_type; + struct btf_var_secinfo *var; + const struct btf_type *array_type; + const struct btf_array *array; + int vlen, element_sz, new_array_id; + __u32 nr_elements; + + /* check btf existence */ + btf = bpf_object__btf(map->obj); + if (!btf) + return -ENOENT; + + /* verify map is datasec */ + datasec_type = btf_type_by_id(btf, bpf_map__btf_value_type_id(map)); + if (!btf_is_datasec(datasec_type)) { + pr_warn("map '%s': cannot be resized, map value type is not a datasec\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify datasec has at least one var */ + vlen = btf_vlen(datasec_type); + if (vlen == 0) { + pr_warn("map '%s': cannot be resized, map value datasec is empty\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify last var in the datasec is an array */ + var = &btf_var_secinfos(datasec_type)[vlen - 1]; + var_type = btf_type_by_id(btf, var->type); + array_type = skip_mods_and_typedefs(btf, var_type->type, NULL); + if (!btf_is_array(array_type)) { + pr_warn("map '%s': cannot be resized, last var must be an array\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify request size aligns with array */ + array = btf_array(array_type); + element_sz = btf__resolve_size(btf, array->type); + if (element_sz <= 0 || (size - var->offset) % element_sz != 0) { + pr_warn("map '%s': cannot be resized, element size (%d) doesn't align with new total size (%u)\n", + bpf_map__name(map), element_sz, size); + return -EINVAL; + } + + /* create a new array based on the existing array, but with new length */ + nr_elements = (size - var->offset) / element_sz; + new_array_id = btf__add_array(btf, array->index_type, array->type, nr_elements); + if (new_array_id < 0) + return new_array_id; + + /* adding a new btf type invalidates existing pointers to btf objects, + * so refresh pointers before proceeding + */ + datasec_type = btf_type_by_id(btf, map->btf_value_type_id); + var = &btf_var_secinfos(datasec_type)[vlen - 1]; + var_type = btf_type_by_id(btf, var->type); + + /* finally update btf info */ + datasec_type->size = size; + var->size = size - var->offset; + var_type->type = new_array_id; + + return 0; +} + int bpf_map__set_value_size(struct bpf_map *map, __u32 size) { if (map->fd >= 0) return libbpf_err(-EBUSY); + + if (map->mmaped) { + int err; + size_t mmap_old_sz, mmap_new_sz; + + mmap_old_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); + mmap_new_sz = bpf_map_mmap_sz(size, map->def.max_entries); + err = bpf_map_mmap_resize(map, mmap_old_sz, mmap_new_sz); + if (err) { + pr_warn("map '%s': failed to resize memory-mapped region: %d\n", + bpf_map__name(map), err); + return err; + } + err = map_btf_datasec_resize(map, size); + if (err && err != -ENOENT) { + pr_warn("map '%s': failed to adjust resized BTF, clearing BTF key/value info: %d\n", + bpf_map__name(map), err); + map->btf_value_type_id = 0; + map->btf_key_type_id = 0; + } + } + map->def.value_size = size; return 0; } @@ -9442,7 +9676,7 @@ int bpf_map__set_initial_value(struct bpf_map *map, return 0; } -const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) +void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) { if (!map->mmaped) return NULL; @@ -9958,7 +10192,7 @@ static int parse_uint_from_file(const char *file, const char *fmt) int err, ret; FILE *f; - f = fopen(file, "r"); + f = fopen(file, "re"); if (!f) { err = -errno; pr_debug("failed to open '%s': %s\n", file, @@ -10107,6 +10341,18 @@ static const char *tracefs_uprobe_events(void) return use_debugfs() ? DEBUGFS"/uprobe_events" : TRACEFS"/uprobe_events"; } +static const char *tracefs_available_filter_functions(void) +{ + return use_debugfs() ? DEBUGFS"/available_filter_functions" + : TRACEFS"/available_filter_functions"; +} + +static const char *tracefs_available_filter_functions_addrs(void) +{ + return use_debugfs() ? DEBUGFS"/available_filter_functions_addrs" + : TRACEFS"/available_filter_functions_addrs"; +} + static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz, const char *kfunc_name, size_t offset) { @@ -10389,7 +10635,7 @@ struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog, } /* Adapted from perf/util/string.c */ -static bool glob_match(const char *str, const char *pat) +bool glob_match(const char *str, const char *pat) { while (*str && *pat && *pat != '*') { if (*pat == '?') { /* Matches any single character */ @@ -10422,25 +10668,158 @@ struct kprobe_multi_resolve { size_t cnt; }; -static int -resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type, - const char *sym_name, void *ctx) +struct avail_kallsyms_data { + char **syms; + size_t cnt; + struct kprobe_multi_resolve *res; +}; + +static int avail_func_cmp(const void *a, const void *b) +{ + return strcmp(*(const char **)a, *(const char **)b); +} + +static int avail_kallsyms_cb(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx) { - struct kprobe_multi_resolve *res = ctx; + struct avail_kallsyms_data *data = ctx; + struct kprobe_multi_resolve *res = data->res; int err; - if (!glob_match(sym_name, res->pattern)) + if (!bsearch(&sym_name, data->syms, data->cnt, sizeof(*data->syms), avail_func_cmp)) return 0; - err = libbpf_ensure_mem((void **) &res->addrs, &res->cap, sizeof(unsigned long), - res->cnt + 1); + err = libbpf_ensure_mem((void **)&res->addrs, &res->cap, sizeof(*res->addrs), res->cnt + 1); if (err) return err; - res->addrs[res->cnt++] = (unsigned long) sym_addr; + res->addrs[res->cnt++] = (unsigned long)sym_addr; return 0; } +static int libbpf_available_kallsyms_parse(struct kprobe_multi_resolve *res) +{ + const char *available_functions_file = tracefs_available_filter_functions(); + struct avail_kallsyms_data data; + char sym_name[500]; + FILE *f; + int err = 0, ret, i; + char **syms = NULL; + size_t cap = 0, cnt = 0; + + f = fopen(available_functions_file, "re"); + if (!f) { + err = -errno; + pr_warn("failed to open %s: %d\n", available_functions_file, err); + return err; + } + + while (true) { + char *name; + + ret = fscanf(f, "%499s%*[^\n]\n", sym_name); + if (ret == EOF && feof(f)) + break; + + if (ret != 1) { + pr_warn("failed to parse available_filter_functions entry: %d\n", ret); + err = -EINVAL; + goto cleanup; + } + + if (!glob_match(sym_name, res->pattern)) + continue; + + err = libbpf_ensure_mem((void **)&syms, &cap, sizeof(*syms), cnt + 1); + if (err) + goto cleanup; + + name = strdup(sym_name); + if (!name) { + err = -errno; + goto cleanup; + } + + syms[cnt++] = name; + } + + /* no entries found, bail out */ + if (cnt == 0) { + err = -ENOENT; + goto cleanup; + } + + /* sort available functions */ + qsort(syms, cnt, sizeof(*syms), avail_func_cmp); + + data.syms = syms; + data.res = res; + data.cnt = cnt; + libbpf_kallsyms_parse(avail_kallsyms_cb, &data); + + if (res->cnt == 0) + err = -ENOENT; + +cleanup: + for (i = 0; i < cnt; i++) + free((char *)syms[i]); + free(syms); + + fclose(f); + return err; +} + +static bool has_available_filter_functions_addrs(void) +{ + return access(tracefs_available_filter_functions_addrs(), R_OK) != -1; +} + +static int libbpf_available_kprobes_parse(struct kprobe_multi_resolve *res) +{ + const char *available_path = tracefs_available_filter_functions_addrs(); + char sym_name[500]; + FILE *f; + int ret, err = 0; + unsigned long long sym_addr; + + f = fopen(available_path, "re"); + if (!f) { + err = -errno; + pr_warn("failed to open %s: %d\n", available_path, err); + return err; + } + + while (true) { + ret = fscanf(f, "%llx %499s%*[^\n]\n", &sym_addr, sym_name); + if (ret == EOF && feof(f)) + break; + + if (ret != 2) { + pr_warn("failed to parse available_filter_functions_addrs entry: %d\n", + ret); + err = -EINVAL; + goto cleanup; + } + + if (!glob_match(sym_name, res->pattern)) + continue; + + err = libbpf_ensure_mem((void **)&res->addrs, &res->cap, + sizeof(*res->addrs), res->cnt + 1); + if (err) + goto cleanup; + + res->addrs[res->cnt++] = (unsigned long)sym_addr; + } + + if (res->cnt == 0) + err = -ENOENT; + +cleanup: + fclose(f); + return err; +} + struct bpf_link * bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, const char *pattern, @@ -10477,13 +10856,12 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, return libbpf_err_ptr(-EINVAL); if (pattern) { - err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res); + if (has_available_filter_functions_addrs()) + err = libbpf_available_kprobes_parse(&res); + else + err = libbpf_available_kallsyms_parse(&res); if (err) goto error; - if (!res.cnt) { - err = -ENOENT; - goto error; - } addrs = res.addrs; cnt = res.cnt; } @@ -10610,6 +10988,37 @@ static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, stru return libbpf_get_error(*link); } +static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + char *probe_type = NULL, *binary_path = NULL, *func_name = NULL; + LIBBPF_OPTS(bpf_uprobe_multi_opts, opts); + int n, ret = -EINVAL; + + *link = NULL; + + n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%ms", + &probe_type, &binary_path, &func_name); + switch (n) { + case 1: + /* handle SEC("u[ret]probe") - format is valid, but auto-attach is impossible. */ + ret = 0; + break; + case 3: + opts.retprobe = strcmp(probe_type, "uretprobe.multi") == 0; + *link = bpf_program__attach_uprobe_multi(prog, -1, binary_path, func_name, &opts); + ret = libbpf_get_error(*link); + break; + default: + pr_warn("prog '%s': invalid format of section definition '%s'\n", prog->name, + prog->sec_name); + break; + } + free(probe_type); + free(binary_path); + free(func_name); + return ret; +} + static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz, const char *binary_path, uint64_t offset) { @@ -10692,191 +11101,6 @@ err_clean_legacy: return err; } -/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */ -static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn) -{ - while ((scn = elf_nextscn(elf, scn)) != NULL) { - GElf_Shdr sh; - - if (!gelf_getshdr(scn, &sh)) - continue; - if (sh.sh_type == sh_type) - return scn; - } - return NULL; -} - -/* Find offset of function name in the provided ELF object. "binary_path" is - * the path to the ELF binary represented by "elf", and only used for error - * reporting matters. "name" matches symbol name or name@@LIB for library - * functions. - */ -static long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name) -{ - int i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB }; - bool is_shared_lib, is_name_qualified; - long ret = -ENOENT; - size_t name_len; - GElf_Ehdr ehdr; - - if (!gelf_getehdr(elf, &ehdr)) { - pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1)); - ret = -LIBBPF_ERRNO__FORMAT; - goto out; - } - /* for shared lib case, we do not need to calculate relative offset */ - is_shared_lib = ehdr.e_type == ET_DYN; - - name_len = strlen(name); - /* Does name specify "@@LIB"? */ - is_name_qualified = strstr(name, "@@") != NULL; - - /* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if - * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically - * linked binary may not have SHT_DYMSYM, so absence of a section should not be - * reported as a warning/error. - */ - for (i = 0; i < ARRAY_SIZE(sh_types); i++) { - size_t nr_syms, strtabidx, idx; - Elf_Data *symbols = NULL; - Elf_Scn *scn = NULL; - int last_bind = -1; - const char *sname; - GElf_Shdr sh; - - scn = elf_find_next_scn_by_type(elf, sh_types[i], NULL); - if (!scn) { - pr_debug("elf: failed to find symbol table ELF sections in '%s'\n", - binary_path); - continue; - } - if (!gelf_getshdr(scn, &sh)) - continue; - strtabidx = sh.sh_link; - symbols = elf_getdata(scn, 0); - if (!symbols) { - pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n", - binary_path, elf_errmsg(-1)); - ret = -LIBBPF_ERRNO__FORMAT; - goto out; - } - nr_syms = symbols->d_size / sh.sh_entsize; - - for (idx = 0; idx < nr_syms; idx++) { - int curr_bind; - GElf_Sym sym; - Elf_Scn *sym_scn; - GElf_Shdr sym_sh; - - if (!gelf_getsym(symbols, idx, &sym)) - continue; - - if (GELF_ST_TYPE(sym.st_info) != STT_FUNC) - continue; - - sname = elf_strptr(elf, strtabidx, sym.st_name); - if (!sname) - continue; - - curr_bind = GELF_ST_BIND(sym.st_info); - - /* User can specify func, func@@LIB or func@@LIB_VERSION. */ - if (strncmp(sname, name, name_len) != 0) - continue; - /* ...but we don't want a search for "foo" to match 'foo2" also, so any - * additional characters in sname should be of the form "@@LIB". - */ - if (!is_name_qualified && sname[name_len] != '\0' && sname[name_len] != '@') - continue; - - if (ret >= 0) { - /* handle multiple matches */ - if (last_bind != STB_WEAK && curr_bind != STB_WEAK) { - /* Only accept one non-weak bind. */ - pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n", - sname, name, binary_path); - ret = -LIBBPF_ERRNO__FORMAT; - goto out; - } else if (curr_bind == STB_WEAK) { - /* already have a non-weak bind, and - * this is a weak bind, so ignore. - */ - continue; - } - } - - /* Transform symbol's virtual address (absolute for - * binaries and relative for shared libs) into file - * offset, which is what kernel is expecting for - * uprobe/uretprobe attachment. - * See Documentation/trace/uprobetracer.rst for more - * details. - * This is done by looking up symbol's containing - * section's header and using it's virtual address - * (sh_addr) and corresponding file offset (sh_offset) - * to transform sym.st_value (virtual address) into - * desired final file offset. - */ - sym_scn = elf_getscn(elf, sym.st_shndx); - if (!sym_scn) - continue; - if (!gelf_getshdr(sym_scn, &sym_sh)) - continue; - - ret = sym.st_value - sym_sh.sh_addr + sym_sh.sh_offset; - last_bind = curr_bind; - } - if (ret > 0) - break; - } - - if (ret > 0) { - pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path, - ret); - } else { - if (ret == 0) { - pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path, - is_shared_lib ? "should not be 0 in a shared library" : - "try using shared library path instead"); - ret = -ENOENT; - } else { - pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path); - } - } -out: - return ret; -} - -/* Find offset of function name in ELF object specified by path. "name" matches - * symbol name or name@@LIB for library functions. - */ -static long elf_find_func_offset_from_file(const char *binary_path, const char *name) -{ - char errmsg[STRERR_BUFSIZE]; - long ret = -ENOENT; - Elf *elf; - int fd; - - fd = open(binary_path, O_RDONLY | O_CLOEXEC); - if (fd < 0) { - ret = -errno; - pr_warn("failed to open %s: %s\n", binary_path, - libbpf_strerror_r(ret, errmsg, sizeof(errmsg))); - return ret; - } - elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); - if (!elf) { - pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1)); - close(fd); - return -LIBBPF_ERRNO__FORMAT; - } - - ret = elf_find_func_offset(elf, binary_path, name); - elf_end(elf); - close(fd); - return ret; -} - /* Find offset of function name in archive specified by path. Currently * supported are .zip files that do not compress their contents, as used on * Android in the form of APKs, for example. "file_name" is the name of the ELF @@ -11019,6 +11243,120 @@ static int resolve_full_path(const char *file, char *result, size_t result_sz) return -ENOENT; } +struct bpf_link * +bpf_program__attach_uprobe_multi(const struct bpf_program *prog, + pid_t pid, + const char *path, + const char *func_pattern, + const struct bpf_uprobe_multi_opts *opts) +{ + const unsigned long *ref_ctr_offsets = NULL, *offsets = NULL; + LIBBPF_OPTS(bpf_link_create_opts, lopts); + unsigned long *resolved_offsets = NULL; + int err = 0, link_fd, prog_fd; + struct bpf_link *link = NULL; + char errmsg[STRERR_BUFSIZE]; + char full_path[PATH_MAX]; + const __u64 *cookies; + const char **syms; + size_t cnt; + + if (!OPTS_VALID(opts, bpf_uprobe_multi_opts)) + return libbpf_err_ptr(-EINVAL); + + syms = OPTS_GET(opts, syms, NULL); + offsets = OPTS_GET(opts, offsets, NULL); + ref_ctr_offsets = OPTS_GET(opts, ref_ctr_offsets, NULL); + cookies = OPTS_GET(opts, cookies, NULL); + cnt = OPTS_GET(opts, cnt, 0); + + /* + * User can specify 2 mutually exclusive set of inputs: + * + * 1) use only path/func_pattern/pid arguments + * + * 2) use path/pid with allowed combinations of: + * syms/offsets/ref_ctr_offsets/cookies/cnt + * + * - syms and offsets are mutually exclusive + * - ref_ctr_offsets and cookies are optional + * + * Any other usage results in error. + */ + + if (!path) + return libbpf_err_ptr(-EINVAL); + if (!func_pattern && cnt == 0) + return libbpf_err_ptr(-EINVAL); + + if (func_pattern) { + if (syms || offsets || ref_ctr_offsets || cookies || cnt) + return libbpf_err_ptr(-EINVAL); + } else { + if (!!syms == !!offsets) + return libbpf_err_ptr(-EINVAL); + } + + if (func_pattern) { + if (!strchr(path, '/')) { + err = resolve_full_path(path, full_path, sizeof(full_path)); + if (err) { + pr_warn("prog '%s': failed to resolve full path for '%s': %d\n", + prog->name, path, err); + return libbpf_err_ptr(err); + } + path = full_path; + } + + err = elf_resolve_pattern_offsets(path, func_pattern, + &resolved_offsets, &cnt); + if (err < 0) + return libbpf_err_ptr(err); + offsets = resolved_offsets; + } else if (syms) { + err = elf_resolve_syms_offsets(path, cnt, syms, &resolved_offsets); + if (err < 0) + return libbpf_err_ptr(err); + offsets = resolved_offsets; + } + + lopts.uprobe_multi.path = path; + lopts.uprobe_multi.offsets = offsets; + lopts.uprobe_multi.ref_ctr_offsets = ref_ctr_offsets; + lopts.uprobe_multi.cookies = cookies; + lopts.uprobe_multi.cnt = cnt; + lopts.uprobe_multi.flags = OPTS_GET(opts, retprobe, false) ? BPF_F_UPROBE_MULTI_RETURN : 0; + + if (pid == 0) + pid = getpid(); + if (pid > 0) + lopts.uprobe_multi.pid = pid; + + link = calloc(1, sizeof(*link)); + if (!link) { + err = -ENOMEM; + goto error; + } + link->detach = &bpf_link__detach_fd; + + prog_fd = bpf_program__fd(prog); + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &lopts); + if (link_fd < 0) { + err = -errno; + pr_warn("prog '%s': failed to attach multi-uprobe: %s\n", + prog->name, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto error; + } + link->fd = link_fd; + free(resolved_offsets); + return link; + +error: + free(resolved_offsets); + free(link); + return libbpf_err_ptr(err); +} + LIBBPF_API struct bpf_link * bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const char *binary_path, size_t func_offset, @@ -11563,11 +11901,10 @@ static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_li } static struct bpf_link * -bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id, - const char *target_name) +bpf_program_attach_fd(const struct bpf_program *prog, + int target_fd, const char *target_name, + const struct bpf_link_create_opts *opts) { - DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts, - .target_btf_id = btf_id); enum bpf_attach_type attach_type; char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; @@ -11585,7 +11922,7 @@ bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id link->detach = &bpf_link__detach_fd; attach_type = bpf_program__expected_attach_type(prog); - link_fd = bpf_link_create(prog_fd, target_fd, attach_type, &opts); + link_fd = bpf_link_create(prog_fd, target_fd, attach_type, opts); if (link_fd < 0) { link_fd = -errno; free(link); @@ -11601,19 +11938,54 @@ bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id struct bpf_link * bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd) { - return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup"); + return bpf_program_attach_fd(prog, cgroup_fd, "cgroup", NULL); } struct bpf_link * bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd) { - return bpf_program__attach_fd(prog, netns_fd, 0, "netns"); + return bpf_program_attach_fd(prog, netns_fd, "netns", NULL); } struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex) { /* target_fd/target_ifindex use the same field in LINK_CREATE */ - return bpf_program__attach_fd(prog, ifindex, 0, "xdp"); + return bpf_program_attach_fd(prog, ifindex, "xdp", NULL); +} + +struct bpf_link * +bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex, + const struct bpf_tcx_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, link_create_opts); + __u32 relative_id; + int relative_fd; + + if (!OPTS_VALID(opts, bpf_tcx_opts)) + return libbpf_err_ptr(-EINVAL); + + relative_id = OPTS_GET(opts, relative_id, 0); + relative_fd = OPTS_GET(opts, relative_fd, 0); + + /* validate we don't have unexpected combinations of non-zero fields */ + if (!ifindex) { + pr_warn("prog '%s': target netdevice ifindex cannot be zero\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + if (relative_fd && relative_id) { + pr_warn("prog '%s': relative_fd and relative_id cannot be set at the same time\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link_create_opts.tcx.expected_revision = OPTS_GET(opts, expected_revision, 0); + link_create_opts.tcx.relative_fd = relative_fd; + link_create_opts.tcx.relative_id = relative_id; + link_create_opts.flags = OPTS_GET(opts, flags, 0); + + /* target_fd/target_ifindex use the same field in LINK_CREATE */ + return bpf_program_attach_fd(prog, ifindex, "tcx", &link_create_opts); } struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, @@ -11635,11 +12007,16 @@ struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, } if (target_fd) { + LIBBPF_OPTS(bpf_link_create_opts, target_opts); + btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd); if (btf_id < 0) return libbpf_err_ptr(btf_id); - return bpf_program__attach_fd(prog, target_fd, btf_id, "freplace"); + target_opts.target_btf_id = btf_id; + + return bpf_program_attach_fd(prog, target_fd, "freplace", + &target_opts); } else { /* no target, so use raw_tracepoint_open for compatibility * with old kernels @@ -11694,6 +12071,48 @@ static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_l return libbpf_get_error(*link); } +struct bpf_link *bpf_program__attach_netfilter(const struct bpf_program *prog, + const struct bpf_netfilter_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, lopts); + struct bpf_link *link; + int prog_fd, link_fd; + + if (!OPTS_VALID(opts, bpf_netfilter_opts)) + return libbpf_err_ptr(-EINVAL); + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("prog '%s': can't attach before loaded\n", prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link = calloc(1, sizeof(*link)); + if (!link) + return libbpf_err_ptr(-ENOMEM); + + link->detach = &bpf_link__detach_fd; + + lopts.netfilter.pf = OPTS_GET(opts, pf, 0); + lopts.netfilter.hooknum = OPTS_GET(opts, hooknum, 0); + lopts.netfilter.priority = OPTS_GET(opts, priority, 0); + lopts.netfilter.flags = OPTS_GET(opts, flags, 0); + + link_fd = bpf_link_create(prog_fd, 0, BPF_NETFILTER, &lopts); + if (link_fd < 0) { + char errmsg[STRERR_BUFSIZE]; + + link_fd = -errno; + free(link); + pr_warn("prog '%s': failed to attach to netfilter: %s\n", + prog->name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); + return libbpf_err_ptr(link_fd); + } + link->fd = link_fd; + + return link; +} + struct bpf_link *bpf_program__attach(const struct bpf_program *prog) { struct bpf_link *link = NULL; @@ -12694,7 +13113,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) for (i = 0; i < s->map_cnt; i++) { struct bpf_map *map = *s->maps[i].map; - size_t mmap_sz = bpf_map_mmap_sz(map); + size_t mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); int prot, map_fd = bpf_map__fd(map); void **mmaped = s->maps[i].mmaped; @@ -12721,8 +13140,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) * as per normal clean up procedure, so we don't need to worry * about it from skeleton's clean up perspective. */ - *mmaped = mmap(map->mmaped, mmap_sz, prot, - MAP_SHARED | MAP_FIXED, map_fd, 0); + *mmaped = mmap(map->mmaped, mmap_sz, prot, MAP_SHARED | MAP_FIXED, map_fd, 0); if (*mmaped == MAP_FAILED) { err = -errno; *mmaped = NULL; |