diff options
Diffstat (limited to 'tools/lib/bpf/libbpf.c')
| -rw-r--r-- | tools/lib/bpf/libbpf.c | 1855 |
1 files changed, 1523 insertions, 332 deletions
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 151f7ac1882e..ed07789b3e62 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -32,6 +32,9 @@ #include <linux/limits.h> #include <linux/perf_event.h> #include <linux/ring_buffer.h> +#include <sys/epoll.h> +#include <sys/ioctl.h> +#include <sys/mman.h> #include <sys/stat.h> #include <sys/types.h> #include <sys/vfs.h> @@ -188,6 +191,7 @@ struct bpf_program { void *line_info; __u32 line_info_rec_size; __u32 line_info_cnt; + __u32 prog_flags; }; enum libbpf_map_type { @@ -206,7 +210,8 @@ static const char * const libbpf_type_to_btf_name[] = { struct bpf_map { int fd; char *name; - size_t offset; + int sec_idx; + size_t sec_offset; int map_ifindex; int inner_map_fd; struct bpf_map_def def; @@ -233,6 +238,7 @@ struct bpf_object { size_t nr_programs; struct bpf_map *maps; size_t nr_maps; + size_t maps_cap; struct bpf_secdata sections; bool loaded; @@ -259,6 +265,7 @@ struct bpf_object { } *reloc; int nr_reloc; int maps_shndx; + int btf_maps_shndx; int text_shndx; int data_shndx; int rodata_shndx; @@ -348,8 +355,11 @@ static int bpf_program__init(void *data, size_t size, char *section_name, int idx, struct bpf_program *prog) { - if (size < sizeof(struct bpf_insn)) { - pr_warning("corrupted section '%s'\n", section_name); + const size_t bpf_insn_sz = sizeof(struct bpf_insn); + + if (size == 0 || size % bpf_insn_sz) { + pr_warning("corrupted section '%s', size: %zu\n", + section_name, size); return -EINVAL; } @@ -375,9 +385,8 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx, section_name); goto errout; } - prog->insns_cnt = size / sizeof(struct bpf_insn); - memcpy(prog->insns, data, - prog->insns_cnt * sizeof(struct bpf_insn)); + prog->insns_cnt = size / bpf_insn_sz; + memcpy(prog->insns, data, size); prog->idx = idx; prog->instances.fds = NULL; prog->instances.nr = -1; @@ -494,15 +503,14 @@ static struct bpf_object *bpf_object__new(const char *path, strcpy(obj->path, path); /* Using basename() GNU version which doesn't modify arg. */ - strncpy(obj->name, basename((void *)path), - sizeof(obj->name) - 1); + strncpy(obj->name, basename((void *)path), sizeof(obj->name) - 1); end = strchr(obj->name, '.'); if (end) *end = 0; obj->efile.fd = -1; /* - * Caller of this function should also calls + * Caller of this function should also call * bpf_object__elf_finish() after data collection to return * obj_buf to user. If not, we should duplicate the buffer to * avoid user freeing them before elf finish. @@ -510,6 +518,7 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.maps_shndx = -1; + obj->efile.btf_maps_shndx = -1; obj->efile.data_shndx = -1; obj->efile.rodata_shndx = -1; obj->efile.bss_shndx = -1; @@ -562,38 +571,35 @@ static int bpf_object__elf_init(struct bpf_object *obj) } else { obj->efile.fd = open(obj->path, O_RDONLY); if (obj->efile.fd < 0) { - char errmsg[STRERR_BUFSIZE]; - char *cp = libbpf_strerror_r(errno, errmsg, - sizeof(errmsg)); + char errmsg[STRERR_BUFSIZE], *cp; + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warning("failed to open %s: %s\n", obj->path, cp); - return -errno; + return err; } obj->efile.elf = elf_begin(obj->efile.fd, - LIBBPF_ELF_C_READ_MMAP, - NULL); + LIBBPF_ELF_C_READ_MMAP, NULL); } if (!obj->efile.elf) { - pr_warning("failed to open %s as ELF file\n", - obj->path); + pr_warning("failed to open %s as ELF file\n", obj->path); err = -LIBBPF_ERRNO__LIBELF; goto errout; } if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) { - pr_warning("failed to get EHDR from %s\n", - obj->path); + pr_warning("failed to get EHDR from %s\n", obj->path); err = -LIBBPF_ERRNO__FORMAT; goto errout; } ep = &obj->efile.ehdr; /* Old LLVM set e_machine to EM_NONE */ - if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) { - pr_warning("%s is not an eBPF object file\n", - obj->path); + if (ep->e_type != ET_REL || + (ep->e_machine && ep->e_machine != EM_BPF)) { + pr_warning("%s is not an eBPF object file\n", obj->path); err = -LIBBPF_ERRNO__FORMAT; goto errout; } @@ -604,47 +610,31 @@ errout: return err; } -static int -bpf_object__check_endianness(struct bpf_object *obj) +static int bpf_object__check_endianness(struct bpf_object *obj) { - static unsigned int const endian = 1; - - switch (obj->efile.ehdr.e_ident[EI_DATA]) { - case ELFDATA2LSB: - /* We are big endian, BPF obj is little endian. */ - if (*(unsigned char const *)&endian != 1) - goto mismatch; - break; - - case ELFDATA2MSB: - /* We are little endian, BPF obj is big endian. */ - if (*(unsigned char const *)&endian != 0) - goto mismatch; - break; - default: - return -LIBBPF_ERRNO__ENDIAN; - } - - return 0; - -mismatch: - pr_warning("Error: endianness mismatch.\n"); +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB) + return 0; +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB) + return 0; +#else +# error "Unrecognized __BYTE_ORDER__" +#endif + pr_warning("endianness mismatch.\n"); return -LIBBPF_ERRNO__ENDIAN; } static int -bpf_object__init_license(struct bpf_object *obj, - void *data, size_t size) +bpf_object__init_license(struct bpf_object *obj, void *data, size_t size) { - memcpy(obj->license, data, - min(size, sizeof(obj->license) - 1)); + memcpy(obj->license, data, min(size, sizeof(obj->license) - 1)); pr_debug("license of %s is %s\n", obj->path, obj->license); return 0; } static int -bpf_object__init_kversion(struct bpf_object *obj, - void *data, size_t size) +bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size) { __u32 kver; @@ -654,8 +644,7 @@ bpf_object__init_kversion(struct bpf_object *obj, } memcpy(&kver, data, sizeof(kver)); obj->kern_version = kver; - pr_debug("kernel version of %s is %x\n", obj->path, - obj->kern_version); + pr_debug("kernel version of %s is %x\n", obj->path, obj->kern_version); return 0; } @@ -664,7 +653,9 @@ static int compare_bpf_map(const void *_a, const void *_b) const struct bpf_map *a = _a; const struct bpf_map *b = _b; - return a->offset - b->offset; + if (a->sec_idx != b->sec_idx) + return a->sec_idx - b->sec_idx; + return a->sec_offset - b->sec_offset; } static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) @@ -781,24 +772,55 @@ int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, return -ENOENT; } -static bool bpf_object__has_maps(const struct bpf_object *obj) +static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) { - return obj->efile.maps_shndx >= 0 || - obj->efile.data_shndx >= 0 || - obj->efile.rodata_shndx >= 0 || - obj->efile.bss_shndx >= 0; + struct bpf_map *new_maps; + size_t new_cap; + int i; + + if (obj->nr_maps < obj->maps_cap) + return &obj->maps[obj->nr_maps++]; + + new_cap = max((size_t)4, obj->maps_cap * 3 / 2); + new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps)); + if (!new_maps) { + pr_warning("alloc maps for object failed\n"); + return ERR_PTR(-ENOMEM); + } + + obj->maps_cap = new_cap; + obj->maps = new_maps; + + /* zero out new maps */ + memset(obj->maps + obj->nr_maps, 0, + (obj->maps_cap - obj->nr_maps) * sizeof(*obj->maps)); + /* + * fill all fd with -1 so won't close incorrect fd (fd=0 is stdin) + * when failure (zclose won't close negative fd)). + */ + for (i = obj->nr_maps; i < obj->maps_cap; i++) { + obj->maps[i].fd = -1; + obj->maps[i].inner_map_fd = -1; + } + + return &obj->maps[obj->nr_maps++]; } static int -bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map, - enum libbpf_map_type type, Elf_Data *data, - void **data_buff) +bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, + int sec_idx, Elf_Data *data, void **data_buff) { - struct bpf_map_def *def = &map->def; char map_name[BPF_OBJ_NAME_LEN]; + struct bpf_map_def *def; + struct bpf_map *map; + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); map->libbpf_type = type; - map->offset = ~(typeof(map->offset))0; + map->sec_idx = sec_idx; + map->sec_offset = 0; snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name, libbpf_type_to_btf_name[type]); map->name = strdup(map_name); @@ -806,13 +828,15 @@ bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map, pr_warning("failed to alloc map name\n"); return -ENOMEM; } + pr_debug("map '%s' (global data): at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); + def = &map->def; def->type = BPF_MAP_TYPE_ARRAY; def->key_size = sizeof(int); def->value_size = data->d_size; def->max_entries = 1; - def->map_flags = type == LIBBPF_MAP_RODATA ? - BPF_F_RDONLY_PROG : 0; + def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0; if (data_buff) { *data_buff = malloc(data->d_size); if (!*data_buff) { @@ -827,30 +851,61 @@ bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map, return 0; } -static int -bpf_object__init_maps(struct bpf_object *obj, int flags) +static int bpf_object__init_global_data_maps(struct bpf_object *obj) +{ + int err; + + if (!obj->caps.global_data) + return 0; + /* + * Populate obj->maps with libbpf internal maps. + */ + if (obj->efile.data_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA, + obj->efile.data_shndx, + obj->efile.data, + &obj->sections.data); + if (err) + return err; + } + if (obj->efile.rodata_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA, + obj->efile.rodata_shndx, + obj->efile.rodata, + &obj->sections.rodata); + if (err) + return err; + } + if (obj->efile.bss_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS, + obj->efile.bss_shndx, + obj->efile.bss, NULL); + if (err) + return err; + } + return 0; +} + +static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) { - int i, map_idx, map_def_sz = 0, nr_syms, nr_maps = 0, nr_maps_glob = 0; - bool strict = !(flags & MAPS_RELAX_COMPAT); Elf_Data *symbols = obj->efile.symbols; + int i, map_def_sz = 0, nr_maps = 0, nr_syms; Elf_Data *data = NULL; - int ret = 0; + Elf_Scn *scn; + + if (obj->efile.maps_shndx < 0) + return 0; if (!symbols) return -EINVAL; - nr_syms = symbols->d_size / sizeof(GElf_Sym); - if (obj->efile.maps_shndx >= 0) { - Elf_Scn *scn = elf_getscn(obj->efile.elf, - obj->efile.maps_shndx); - - if (scn) - data = elf_getdata(scn, NULL); - if (!scn || !data) { - pr_warning("failed to get Elf_Data from map section %d\n", - obj->efile.maps_shndx); - return -EINVAL; - } + scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx); + if (scn) + data = elf_getdata(scn, NULL); + if (!scn || !data) { + pr_warning("failed to get Elf_Data from map section %d\n", + obj->efile.maps_shndx); + return -EINVAL; } /* @@ -860,16 +915,8 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) * * TODO: Detect array of map and report error. */ - if (obj->caps.global_data) { - if (obj->efile.data_shndx >= 0) - nr_maps_glob++; - if (obj->efile.rodata_shndx >= 0) - nr_maps_glob++; - if (obj->efile.bss_shndx >= 0) - nr_maps_glob++; - } - - for (i = 0; data && i < nr_syms; i++) { + nr_syms = symbols->d_size / sizeof(GElf_Sym); + for (i = 0; i < nr_syms; i++) { GElf_Sym sym; if (!gelf_getsym(symbols, i, &sym)) @@ -878,74 +925,59 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) continue; nr_maps++; } - - if (!nr_maps && !nr_maps_glob) - return 0; - /* Assume equally sized map definitions */ - if (data) { - pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, - nr_maps, data->d_size); - - map_def_sz = data->d_size / nr_maps; - if (!data->d_size || (data->d_size % nr_maps) != 0) { - pr_warning("unable to determine map definition size " - "section %s, %d maps in %zd bytes\n", - obj->path, nr_maps, data->d_size); - return -EINVAL; - } - } - - nr_maps += nr_maps_glob; - obj->maps = calloc(nr_maps, sizeof(obj->maps[0])); - if (!obj->maps) { - pr_warning("alloc maps for object failed\n"); - return -ENOMEM; - } - obj->nr_maps = nr_maps; - - for (i = 0; i < nr_maps; i++) { - /* - * fill all fd with -1 so won't close incorrect - * fd (fd=0 is stdin) when failure (zclose won't close - * negative fd)). - */ - obj->maps[i].fd = -1; - obj->maps[i].inner_map_fd = -1; + pr_debug("maps in %s: %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + + map_def_sz = data->d_size / nr_maps; + if (!data->d_size || (data->d_size % nr_maps) != 0) { + pr_warning("unable to determine map definition size " + "section %s, %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + return -EINVAL; } - /* - * Fill obj->maps using data in "maps" section. - */ - for (i = 0, map_idx = 0; data && i < nr_syms; i++) { + /* Fill obj->maps using data in "maps" section. */ + for (i = 0; i < nr_syms; i++) { GElf_Sym sym; const char *map_name; struct bpf_map_def *def; + struct bpf_map *map; if (!gelf_getsym(symbols, i, &sym)) continue; if (sym.st_shndx != obj->efile.maps_shndx) continue; - map_name = elf_strptr(obj->efile.elf, - obj->efile.strtabidx, + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + + map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name); + if (!map_name) { + pr_warning("failed to get map #%d name sym string for obj %s\n", + i, obj->path); + return -LIBBPF_ERRNO__FORMAT; + } - obj->maps[map_idx].libbpf_type = LIBBPF_MAP_UNSPEC; - obj->maps[map_idx].offset = sym.st_value; + map->libbpf_type = LIBBPF_MAP_UNSPEC; + map->sec_idx = sym.st_shndx; + map->sec_offset = sym.st_value; + pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); if (sym.st_value + map_def_sz > data->d_size) { pr_warning("corrupted maps section in %s: last map \"%s\" too small\n", obj->path, map_name); return -EINVAL; } - obj->maps[map_idx].name = strdup(map_name); - if (!obj->maps[map_idx].name) { + map->name = strdup(map_name); + if (!map->name) { pr_warning("failed to alloc map name\n"); return -ENOMEM; } - pr_debug("map %d is \"%s\"\n", map_idx, - obj->maps[map_idx].name); + pr_debug("map %d is \"%s\"\n", i, map->name); def = (struct bpf_map_def *)(data->d_buf + sym.st_value); /* * If the definition of the map in the object file fits in @@ -954,7 +986,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) * calloc above. */ if (map_def_sz <= sizeof(struct bpf_map_def)) { - memcpy(&obj->maps[map_idx].def, def, map_def_sz); + memcpy(&map->def, def, map_def_sz); } else { /* * Here the map structure being read is bigger than what @@ -974,37 +1006,338 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) return -EINVAL; } } - memcpy(&obj->maps[map_idx].def, def, - sizeof(struct bpf_map_def)); + memcpy(&map->def, def, sizeof(struct bpf_map_def)); } - map_idx++; } + return 0; +} - if (!obj->caps.global_data) - goto finalize; +static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, + __u32 id) +{ + const struct btf_type *t = btf__type_by_id(btf, id); - /* - * Populate rest of obj->maps with libbpf internal maps. - */ - if (obj->efile.data_shndx >= 0) - ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], - LIBBPF_MAP_DATA, - obj->efile.data, - &obj->sections.data); - if (!ret && obj->efile.rodata_shndx >= 0) - ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], - LIBBPF_MAP_RODATA, - obj->efile.rodata, - &obj->sections.rodata); - if (!ret && obj->efile.bss_shndx >= 0) - ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], - LIBBPF_MAP_BSS, - obj->efile.bss, NULL); -finalize: - if (!ret) + while (true) { + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + t = btf__type_by_id(btf, t->type); + break; + default: + return t; + } + } +} + +/* + * Fetch integer attribute of BTF map definition. Such attributes are + * represented using a pointer to an array, in which dimensionality of array + * encodes specified integer value. E.g., int (*type)[BPF_MAP_TYPE_ARRAY]; + * encodes `type => BPF_MAP_TYPE_ARRAY` key/value pair completely using BTF + * type definition, while using only sizeof(void *) space in ELF data section. + */ +static bool get_map_field_int(const char *map_name, const struct btf *btf, + const struct btf_type *def, + const struct btf_member *m, __u32 *res) { + const struct btf_type *t = skip_mods_and_typedefs(btf, m->type); + const char *name = btf__name_by_offset(btf, m->name_off); + const struct btf_array *arr_info; + const struct btf_type *arr_t; + + if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + pr_warning("map '%s': attr '%s': expected PTR, got %u.\n", + map_name, name, BTF_INFO_KIND(t->info)); + return false; + } + + arr_t = btf__type_by_id(btf, t->type); + if (!arr_t) { + pr_warning("map '%s': attr '%s': type [%u] not found.\n", + map_name, name, t->type); + return false; + } + if (BTF_INFO_KIND(arr_t->info) != BTF_KIND_ARRAY) { + pr_warning("map '%s': attr '%s': expected ARRAY, got %u.\n", + map_name, name, BTF_INFO_KIND(arr_t->info)); + return false; + } + arr_info = (const void *)(arr_t + 1); + *res = arr_info->nelems; + return true; +} + +static int bpf_object__init_user_btf_map(struct bpf_object *obj, + const struct btf_type *sec, + int var_idx, int sec_idx, + const Elf_Data *data, bool strict) +{ + const struct btf_type *var, *def, *t; + const struct btf_var_secinfo *vi; + const struct btf_var *var_extra; + const struct btf_member *m; + const char *map_name; + struct bpf_map *map; + int vlen, i; + + vi = (const struct btf_var_secinfo *)(const void *)(sec + 1) + var_idx; + var = btf__type_by_id(obj->btf, vi->type); + var_extra = (const void *)(var + 1); + map_name = btf__name_by_offset(obj->btf, var->name_off); + vlen = BTF_INFO_VLEN(var->info); + + if (map_name == NULL || map_name[0] == '\0') { + pr_warning("map #%d: empty name.\n", var_idx); + return -EINVAL; + } + if ((__u64)vi->offset + vi->size > data->d_size) { + pr_warning("map '%s' BTF data is corrupted.\n", map_name); + return -EINVAL; + } + if (BTF_INFO_KIND(var->info) != BTF_KIND_VAR) { + pr_warning("map '%s': unexpected var kind %u.\n", + map_name, BTF_INFO_KIND(var->info)); + return -EINVAL; + } + if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && + var_extra->linkage != BTF_VAR_STATIC) { + pr_warning("map '%s': unsupported var linkage %u.\n", + map_name, var_extra->linkage); + return -EOPNOTSUPP; + } + + def = skip_mods_and_typedefs(obj->btf, var->type); + if (BTF_INFO_KIND(def->info) != BTF_KIND_STRUCT) { + pr_warning("map '%s': unexpected def kind %u.\n", + map_name, BTF_INFO_KIND(var->info)); + return -EINVAL; + } + if (def->size > vi->size) { + pr_warning("map '%s': invalid def size.\n", map_name); + return -EINVAL; + } + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + map->name = strdup(map_name); + if (!map->name) { + pr_warning("map '%s': failed to alloc map name.\n", map_name); + return -ENOMEM; + } + map->libbpf_type = LIBBPF_MAP_UNSPEC; + map->def.type = BPF_MAP_TYPE_UNSPEC; + map->sec_idx = sec_idx; + map->sec_offset = vi->offset; + pr_debug("map '%s': at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); + + vlen = BTF_INFO_VLEN(def->info); + m = (const void *)(def + 1); + for (i = 0; i < vlen; i++, m++) { + const char *name = btf__name_by_offset(obj->btf, m->name_off); + + if (!name) { + pr_warning("map '%s': invalid field #%d.\n", + map_name, i); + return -EINVAL; + } + if (strcmp(name, "type") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + &map->def.type)) + return -EINVAL; + pr_debug("map '%s': found type = %u.\n", + map_name, map->def.type); + } else if (strcmp(name, "max_entries") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + &map->def.max_entries)) + return -EINVAL; + pr_debug("map '%s': found max_entries = %u.\n", + map_name, map->def.max_entries); + } else if (strcmp(name, "map_flags") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + &map->def.map_flags)) + return -EINVAL; + pr_debug("map '%s': found map_flags = %u.\n", + map_name, map->def.map_flags); + } else if (strcmp(name, "key_size") == 0) { + __u32 sz; + + if (!get_map_field_int(map_name, obj->btf, def, m, + &sz)) + return -EINVAL; + pr_debug("map '%s': found key_size = %u.\n", + map_name, sz); + if (map->def.key_size && map->def.key_size != sz) { + pr_warning("map '%s': conflicting key size %u != %u.\n", + map_name, map->def.key_size, sz); + return -EINVAL; + } + map->def.key_size = sz; + } else if (strcmp(name, "key") == 0) { + __s64 sz; + + t = btf__type_by_id(obj->btf, m->type); + if (!t) { + pr_warning("map '%s': key type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + pr_warning("map '%s': key spec is not PTR: %u.\n", + map_name, BTF_INFO_KIND(t->info)); + return -EINVAL; + } + sz = btf__resolve_size(obj->btf, t->type); + if (sz < 0) { + pr_warning("map '%s': can't determine key size for type [%u]: %lld.\n", + map_name, t->type, sz); + return sz; + } + pr_debug("map '%s': found key [%u], sz = %lld.\n", + map_name, t->type, sz); + if (map->def.key_size && map->def.key_size != sz) { + pr_warning("map '%s': conflicting key size %u != %lld.\n", + map_name, map->def.key_size, sz); + return -EINVAL; + } + map->def.key_size = sz; + map->btf_key_type_id = t->type; + } else if (strcmp(name, "value_size") == 0) { + __u32 sz; + + if (!get_map_field_int(map_name, obj->btf, def, m, + &sz)) + return -EINVAL; + pr_debug("map '%s': found value_size = %u.\n", + map_name, sz); + if (map->def.value_size && map->def.value_size != sz) { + pr_warning("map '%s': conflicting value size %u != %u.\n", + map_name, map->def.value_size, sz); + return -EINVAL; + } + map->def.value_size = sz; + } else if (strcmp(name, "value") == 0) { + __s64 sz; + + t = btf__type_by_id(obj->btf, m->type); + if (!t) { + pr_warning("map '%s': value type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { + pr_warning("map '%s': value spec is not PTR: %u.\n", + map_name, BTF_INFO_KIND(t->info)); + return -EINVAL; + } + sz = btf__resolve_size(obj->btf, t->type); + if (sz < 0) { + pr_warning("map '%s': can't determine value size for type [%u]: %lld.\n", + map_name, t->type, sz); + return sz; + } + pr_debug("map '%s': found value [%u], sz = %lld.\n", + map_name, t->type, sz); + if (map->def.value_size && map->def.value_size != sz) { + pr_warning("map '%s': conflicting value size %u != %lld.\n", + map_name, map->def.value_size, sz); + return -EINVAL; + } + map->def.value_size = sz; + map->btf_value_type_id = t->type; + } else { + if (strict) { + pr_warning("map '%s': unknown field '%s'.\n", + map_name, name); + return -ENOTSUP; + } + pr_debug("map '%s': ignoring unknown field '%s'.\n", + map_name, name); + } + } + + if (map->def.type == BPF_MAP_TYPE_UNSPEC) { + pr_warning("map '%s': map type isn't specified.\n", map_name); + return -EINVAL; + } + + return 0; +} + +static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict) +{ + const struct btf_type *sec = NULL; + int nr_types, i, vlen, err; + const struct btf_type *t; + const char *name; + Elf_Data *data; + Elf_Scn *scn; + + if (obj->efile.btf_maps_shndx < 0) + return 0; + + scn = elf_getscn(obj->efile.elf, obj->efile.btf_maps_shndx); + if (scn) + data = elf_getdata(scn, NULL); + if (!scn || !data) { + pr_warning("failed to get Elf_Data from map section %d (%s)\n", + obj->efile.maps_shndx, MAPS_ELF_SEC); + return -EINVAL; + } + + nr_types = btf__get_nr_types(obj->btf); + for (i = 1; i <= nr_types; i++) { + t = btf__type_by_id(obj->btf, i); + if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC) + continue; + name = btf__name_by_offset(obj->btf, t->name_off); + if (strcmp(name, MAPS_ELF_SEC) == 0) { + sec = t; + break; + } + } + + if (!sec) { + pr_warning("DATASEC '%s' not found.\n", MAPS_ELF_SEC); + return -ENOENT; + } + + vlen = BTF_INFO_VLEN(sec->info); + for (i = 0; i < vlen; i++) { + err = bpf_object__init_user_btf_map(obj, sec, i, + obj->efile.btf_maps_shndx, + data, strict); + if (err) + return err; + } + + return 0; +} + +static int bpf_object__init_maps(struct bpf_object *obj, int flags) +{ + bool strict = !(flags & MAPS_RELAX_COMPAT); + int err; + + err = bpf_object__init_user_maps(obj, strict); + if (err) + return err; + + err = bpf_object__init_user_btf_maps(obj, strict); + if (err) + return err; + + err = bpf_object__init_global_data_maps(obj); + if (err) + return err; + + if (obj->nr_maps) { qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map); - return ret; + } + return 0; } static bool section_have_execinstr(struct bpf_object *obj, int idx) @@ -1093,6 +1426,86 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) } } +static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj) +{ + return obj->efile.btf_maps_shndx >= 0; +} + +static int bpf_object__init_btf(struct bpf_object *obj, + Elf_Data *btf_data, + Elf_Data *btf_ext_data) +{ + bool btf_required = bpf_object__is_btf_mandatory(obj); + int err = 0; + + if (btf_data) { + obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); + if (IS_ERR(obj->btf)) { + pr_warning("Error loading ELF section %s: %d.\n", + BTF_ELF_SEC, err); + goto out; + } + err = btf__finalize_data(obj, obj->btf); + if (err) { + pr_warning("Error finalizing %s: %d.\n", + BTF_ELF_SEC, err); + goto out; + } + } + if (btf_ext_data) { + if (!obj->btf) { + pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", + BTF_EXT_ELF_SEC, BTF_ELF_SEC); + goto out; + } + obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, + btf_ext_data->d_size); + if (IS_ERR(obj->btf_ext)) { + pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", + BTF_EXT_ELF_SEC, PTR_ERR(obj->btf_ext)); + obj->btf_ext = NULL; + goto out; + } + } +out: + if (err || IS_ERR(obj->btf)) { + if (btf_required) + err = err ? : PTR_ERR(obj->btf); + else + err = 0; + if (!IS_ERR_OR_NULL(obj->btf)) + btf__free(obj->btf); + obj->btf = NULL; + } + if (btf_required && !obj->btf) { + pr_warning("BTF is required, but is missing or corrupted.\n"); + return err == 0 ? -ENOENT : err; + } + return 0; +} + +static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) +{ + int err = 0; + + if (!obj->btf) + return 0; + + bpf_object__sanitize_btf(obj); + bpf_object__sanitize_btf_ext(obj); + + err = btf__load(obj->btf); + if (err) { + pr_warning("Error loading %s into kernel: %d.\n", + BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + if (bpf_object__is_btf_mandatory(obj)) + return err; + } + return 0; +} + static int bpf_object__elf_collect(struct bpf_object *obj, int flags) { Elf *elf = obj->efile.elf; @@ -1104,8 +1517,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) /* Elf is corrupted/truncated, avoid calling elf_strptr. */ if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) { - pr_warning("failed to get e_shstrndx from %s\n", - obj->path); + pr_warning("failed to get e_shstrndx from %s\n", obj->path); return -LIBBPF_ERRNO__FORMAT; } @@ -1118,24 +1530,21 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) if (gelf_getshdr(scn, &sh) != &sh) { pr_warning("failed to get section(%d) header from %s\n", idx, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + return -LIBBPF_ERRNO__FORMAT; } name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); if (!name) { pr_warning("failed to get section(%d) name from %s\n", idx, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + return -LIBBPF_ERRNO__FORMAT; } data = elf_getdata(scn, 0); if (!data) { pr_warning("failed to get section(%d) data from %s(%s)\n", idx, name, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + return -LIBBPF_ERRNO__FORMAT; } pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n", idx, name, (unsigned long)data->d_size, @@ -1146,12 +1555,18 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) err = bpf_object__init_license(obj, data->d_buf, data->d_size); + if (err) + return err; } else if (strcmp(name, "version") == 0) { err = bpf_object__init_kversion(obj, data->d_buf, data->d_size); + if (err) + return err; } else if (strcmp(name, "maps") == 0) { obj->efile.maps_shndx = idx; + } else if (strcmp(name, MAPS_ELF_SEC) == 0) { + obj->efile.btf_maps_shndx = idx; } else if (strcmp(name, BTF_ELF_SEC) == 0) { btf_data = data; } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { @@ -1160,11 +1575,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) if (obj->efile.symbols) { pr_warning("bpf: multiple SYMTAB in %s\n", obj->path); - err = -LIBBPF_ERRNO__FORMAT; - } else { - obj->efile.symbols = data; - obj->efile.strtabidx = sh.sh_link; + return -LIBBPF_ERRNO__FORMAT; } + obj->efile.symbols = data; + obj->efile.strtabidx = sh.sh_link; } else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) { if (sh.sh_flags & SHF_EXECINSTR) { if (strcmp(name, ".text") == 0) @@ -1178,6 +1592,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) pr_warning("failed to alloc program %s (%s): %s", name, obj->path, cp); + return err; } } else if (strcmp(name, ".data") == 0) { obj->efile.data = data; @@ -1189,8 +1604,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) pr_debug("skip section(%d) %s\n", idx, name); } } else if (sh.sh_type == SHT_REL) { + int nr_reloc = obj->efile.nr_reloc; void *reloc = obj->efile.reloc; - int nr_reloc = obj->efile.nr_reloc + 1; int sec = sh.sh_info; /* points to other section */ /* Only do relo for section with exec instructions */ @@ -1200,79 +1615,37 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) continue; } - reloc = reallocarray(reloc, nr_reloc, + reloc = reallocarray(reloc, nr_reloc + 1, sizeof(*obj->efile.reloc)); if (!reloc) { pr_warning("realloc failed\n"); - err = -ENOMEM; - } else { - int n = nr_reloc - 1; + return -ENOMEM; + } - obj->efile.reloc = reloc; - obj->efile.nr_reloc = nr_reloc; + obj->efile.reloc = reloc; + obj->efile.nr_reloc++; - obj->efile.reloc[n].shdr = sh; - obj->efile.reloc[n].data = data; - } + obj->efile.reloc[nr_reloc].shdr = sh; + obj->efile.reloc[nr_reloc].data = data; } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) { obj->efile.bss = data; obj->efile.bss_shndx = idx; } else { pr_debug("skip section(%d) %s\n", idx, name); } - if (err) - goto out; } if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) { pr_warning("Corrupted ELF file: index of strtab invalid\n"); - return LIBBPF_ERRNO__FORMAT; - } - if (btf_data) { - obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); - if (IS_ERR(obj->btf)) { - pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", - BTF_ELF_SEC, PTR_ERR(obj->btf)); - obj->btf = NULL; - } else { - err = btf__finalize_data(obj, obj->btf); - if (!err) { - bpf_object__sanitize_btf(obj); - err = btf__load(obj->btf); - } - if (err) { - pr_warning("Error finalizing and loading %s into kernel: %d. Ignored and continue.\n", - BTF_ELF_SEC, err); - btf__free(obj->btf); - obj->btf = NULL; - err = 0; - } - } - } - if (btf_ext_data) { - if (!obj->btf) { - pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", - BTF_EXT_ELF_SEC, BTF_ELF_SEC); - } else { - obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, - btf_ext_data->d_size); - if (IS_ERR(obj->btf_ext)) { - pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", - BTF_EXT_ELF_SEC, - PTR_ERR(obj->btf_ext)); - obj->btf_ext = NULL; - } else { - bpf_object__sanitize_btf_ext(obj); - } - } + return -LIBBPF_ERRNO__FORMAT; } - if (bpf_object__has_maps(obj)) { + err = bpf_object__init_btf(obj, btf_data, btf_ext_data); + if (!err) err = bpf_object__init_maps(obj, flags); - if (err) - goto out; - } - err = bpf_object__init_prog_names(obj); -out: + if (!err) + err = bpf_object__sanitize_and_load_btf(obj); + if (!err) + err = bpf_object__init_prog_names(obj); return err; } @@ -1291,7 +1664,8 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx) } struct bpf_program * -bpf_object__find_program_by_title(struct bpf_object *obj, const char *title) +bpf_object__find_program_by_title(const struct bpf_object *obj, + const char *title) { struct bpf_program *pos; @@ -1313,7 +1687,8 @@ static bool bpf_object__shndx_is_data(const struct bpf_object *obj, static bool bpf_object__shndx_is_maps(const struct bpf_object *obj, int shndx) { - return shndx == obj->efile.maps_shndx; + return shndx == obj->efile.maps_shndx || + shndx == obj->efile.btf_maps_shndx; } static bool bpf_object__relo_in_known_section(const struct bpf_object *obj, @@ -1346,8 +1721,7 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, size_t nr_maps = obj->nr_maps; int i, nrels; - pr_debug("collecting relocating info for: '%s'\n", - prog->section_name); + pr_debug("collecting relocating info for: '%s'\n", prog->section_name); nrels = shdr->sh_size / shdr->sh_entsize; prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels); @@ -1358,23 +1732,21 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, prog->nr_reloc = nrels; for (i = 0; i < nrels; i++) { - GElf_Sym sym; - GElf_Rel rel; - unsigned int insn_idx; - unsigned int shdr_idx; struct bpf_insn *insns = prog->insns; enum libbpf_map_type type; + unsigned int insn_idx; + unsigned int shdr_idx; const char *name; size_t map_idx; + GElf_Sym sym; + GElf_Rel rel; if (!gelf_getrel(data, i, &rel)) { pr_warning("relocation: failed to get %d reloc\n", i); return -LIBBPF_ERRNO__FORMAT; } - if (!gelf_getsym(symbols, - GELF_R_SYM(rel.r_info), - &sym)) { + if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { pr_warning("relocation: symbol %"PRIx64" not found\n", GELF_R_SYM(rel.r_info)); return -LIBBPF_ERRNO__FORMAT; @@ -1435,16 +1807,19 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, if (maps[map_idx].libbpf_type != type) continue; if (type != LIBBPF_MAP_UNSPEC || - (type == LIBBPF_MAP_UNSPEC && - maps[map_idx].offset == sym.st_value)) { - pr_debug("relocation: find map %zd (%s) for insn %u\n", - map_idx, maps[map_idx].name, insn_idx); + (maps[map_idx].sec_idx == sym.st_shndx && + maps[map_idx].sec_offset == sym.st_value)) { + pr_debug("relocation: found map %zd (%s, sec_idx %d, offset %zu) for insn %u\n", + map_idx, maps[map_idx].name, + maps[map_idx].sec_idx, + maps[map_idx].sec_offset, + insn_idx); break; } } if (map_idx >= nr_maps) { - pr_warning("bpf relocation: map_idx %d large than %d\n", + pr_warning("bpf relocation: map_idx %d larger than %d\n", (int)map_idx, (int)nr_maps - 1); return -LIBBPF_ERRNO__RELOC; } @@ -1458,14 +1833,18 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, return 0; } -static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) +static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) { struct bpf_map_def *def = &map->def; __u32 key_type_id = 0, value_type_id = 0; int ret; + /* if it's BTF-defined map, we don't need to search for type IDs */ + if (map->sec_idx == obj->efile.btf_maps_shndx) + return 0; + if (!bpf_map__is_internal(map)) { - ret = btf__get_map_kv_tids(btf, map->name, def->key_size, + ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size, def->value_size, &key_type_id, &value_type_id); } else { @@ -1473,7 +1852,7 @@ static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) * LLVM annotates global data differently in BTF, that is, * only as '.data', '.bss' or '.rodata'. */ - ret = btf__find_by_name(btf, + ret = btf__find_by_name(obj->btf, libbpf_type_to_btf_name[map->libbpf_type]); } if (ret < 0) @@ -1737,6 +2116,7 @@ static int bpf_object__create_maps(struct bpf_object *obj) { struct bpf_create_map_attr create_attr = {}; + int nr_cpus = 0; unsigned int i; int err; @@ -1759,7 +2139,22 @@ bpf_object__create_maps(struct bpf_object *obj) create_attr.map_flags = def->map_flags; create_attr.key_size = def->key_size; create_attr.value_size = def->value_size; - create_attr.max_entries = def->max_entries; + if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && + !def->max_entries) { + if (!nr_cpus) + nr_cpus = libbpf_num_possible_cpus(); + if (nr_cpus < 0) { + pr_warning("failed to determine number of system CPUs: %d\n", + nr_cpus); + err = nr_cpus; + goto err_out; + } + pr_debug("map '%s': setting size to %d\n", + map->name, nr_cpus); + create_attr.max_entries = nr_cpus; + } else { + create_attr.max_entries = def->max_entries; + } create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; @@ -1767,17 +2162,19 @@ bpf_object__create_maps(struct bpf_object *obj) map->inner_map_fd >= 0) create_attr.inner_map_fd = map->inner_map_fd; - if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) { + if (obj->btf && !bpf_map_find_btf_info(obj, map)) { create_attr.btf_fd = btf__fd(obj->btf); create_attr.btf_key_type_id = map->btf_key_type_id; create_attr.btf_value_type_id = map->btf_value_type_id; } *pfd = bpf_create_map_xattr(&create_attr); - if (*pfd < 0 && create_attr.btf_key_type_id) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + if (*pfd < 0 && (create_attr.btf_key_type_id || + create_attr.btf_value_type_id)) { + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", - map->name, cp, errno); + map->name, cp, err); create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; @@ -1789,11 +2186,11 @@ bpf_object__create_maps(struct bpf_object *obj) if (*pfd < 0) { size_t j; - err = *pfd; + err = -errno; err_out: - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("failed to create map (name: '%s'): %s\n", - map->name, cp); + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warning("failed to create map (name: '%s'): %s(%d)\n", + map->name, cp, err); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); return err; @@ -1807,7 +2204,7 @@ err_out: } } - pr_debug("create map %s: fd=%d\n", map->name, *pfd); + pr_debug("created map %s: fd=%d\n", map->name, *pfd); } return 0; @@ -1828,18 +2225,14 @@ check_btf_ext_reloc_err(struct bpf_program *prog, int err, if (btf_prog_info) { /* * Some info has already been found but has problem - * in the last btf_ext reloc. Must have to error - * out. + * in the last btf_ext reloc. Must have to error out. */ pr_warning("Error in relocating %s for sec %s.\n", info_name, prog->section_name); return err; } - /* - * Have problem loading the very first info. Ignore - * the rest. - */ + /* Have problem loading the very first info. Ignore the rest. */ pr_warning("Cannot find %s for main program sec %s. Ignore all %s.\n", info_name, prog->section_name, info_name); return 0; @@ -2043,9 +2436,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) return -LIBBPF_ERRNO__RELOC; } - err = bpf_program__collect_reloc(prog, - shdr, data, - obj); + err = bpf_program__collect_reloc(prog, shdr, data, obj); if (err) return err; } @@ -2062,6 +2453,9 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, char *log_buf; int ret; + if (!insns || !insns_cnt) + return -EINVAL; + memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); load_attr.prog_type = prog->type; load_attr.expected_attach_type = prog->expected_attach_type; @@ -2080,8 +2474,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.line_info_rec_size = prog->line_info_rec_size; load_attr.line_info_cnt = prog->line_info_cnt; load_attr.log_level = prog->log_level; - if (!load_attr.insns || !load_attr.insns_cnt) - return -EINVAL; + load_attr.prog_flags = prog->prog_flags; retry_load: log_buf = malloc(log_buf_size); @@ -2219,14 +2612,14 @@ out: return err; } -static bool bpf_program__is_function_storage(struct bpf_program *prog, - struct bpf_object *obj) +static bool bpf_program__is_function_storage(const struct bpf_program *prog, + const struct bpf_object *obj) { return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls; } static int -bpf_object__load_progs(struct bpf_object *obj) +bpf_object__load_progs(struct bpf_object *obj, int log_level) { size_t i; int err; @@ -2234,6 +2627,7 @@ bpf_object__load_progs(struct bpf_object *obj) for (i = 0; i < obj->nr_programs; i++) { if (bpf_program__is_function_storage(&obj->programs[i], obj)) continue; + obj->programs[i].log_level |= log_level; err = bpf_program__load(&obj->programs[i], obj->license, obj->kern_version); @@ -2270,6 +2664,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type) case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: return false; case BPF_PROG_TYPE_KPROBE: default: @@ -2360,11 +2755,9 @@ struct bpf_object *bpf_object__open_buffer(void *obj_buf, snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx", (unsigned long)obj_buf, (unsigned long)obj_buf_sz); - tmp_name[sizeof(tmp_name) - 1] = '\0'; name = tmp_name; } - pr_debug("loading object '%s' from buffer\n", - name); + pr_debug("loading object '%s' from buffer\n", name); return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true); } @@ -2385,10 +2778,14 @@ int bpf_object__unload(struct bpf_object *obj) return 0; } -int bpf_object__load(struct bpf_object *obj) +int bpf_object__load_xattr(struct bpf_object_load_attr *attr) { + struct bpf_object *obj; int err; + if (!attr) + return -EINVAL; + obj = attr->obj; if (!obj) return -EINVAL; @@ -2401,7 +2798,7 @@ int bpf_object__load(struct bpf_object *obj) CHECK_ERR(bpf_object__create_maps(obj), err, out); CHECK_ERR(bpf_object__relocate(obj), err, out); - CHECK_ERR(bpf_object__load_progs(obj), err, out); + CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out); return 0; out: @@ -2410,6 +2807,15 @@ out: return err; } +int bpf_object__load(struct bpf_object *obj) +{ + struct bpf_object_load_attr attr = { + .obj = obj, + }; + + return bpf_object__load_xattr(&attr); +} + static int check_path(const char *path) { char *cp, errmsg[STRERR_BUFSIZE]; @@ -2914,17 +3320,17 @@ bpf_object__next(struct bpf_object *prev) return next; } -const char *bpf_object__name(struct bpf_object *obj) +const char *bpf_object__name(const struct bpf_object *obj) { return obj ? obj->path : ERR_PTR(-EINVAL); } -unsigned int bpf_object__kversion(struct bpf_object *obj) +unsigned int bpf_object__kversion(const struct bpf_object *obj) { return obj ? obj->kern_version : 0; } -struct btf *bpf_object__btf(struct bpf_object *obj) +struct btf *bpf_object__btf(const struct bpf_object *obj) { return obj ? obj->btf : NULL; } @@ -2945,13 +3351,14 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv, return 0; } -void *bpf_object__priv(struct bpf_object *obj) +void *bpf_object__priv(const struct bpf_object *obj) { return obj ? obj->priv : ERR_PTR(-EINVAL); } static struct bpf_program * -__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward) +__bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj, + bool forward) { size_t nr_programs = obj->nr_programs; ssize_t idx; @@ -2976,7 +3383,7 @@ __bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward) } struct bpf_program * -bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) +bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj) { struct bpf_program *prog = prev; @@ -2988,7 +3395,7 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) } struct bpf_program * -bpf_program__prev(struct bpf_program *next, struct bpf_object *obj) +bpf_program__prev(struct bpf_program *next, const struct bpf_object *obj) { struct bpf_program *prog = next; @@ -3010,7 +3417,7 @@ int bpf_program__set_priv(struct bpf_program *prog, void *priv, return 0; } -void *bpf_program__priv(struct bpf_program *prog) +void *bpf_program__priv(const struct bpf_program *prog) { return prog ? prog->priv : ERR_PTR(-EINVAL); } @@ -3020,7 +3427,7 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex) prog->prog_ifindex = ifindex; } -const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) +const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy) { const char *title; @@ -3036,7 +3443,7 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) return title; } -int bpf_program__fd(struct bpf_program *prog) +int bpf_program__fd(const struct bpf_program *prog) { return bpf_program__nth_fd(prog, 0); } @@ -3069,7 +3476,7 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, return 0; } -int bpf_program__nth_fd(struct bpf_program *prog, int n) +int bpf_program__nth_fd(const struct bpf_program *prog, int n) { int fd; @@ -3097,25 +3504,25 @@ void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) prog->type = type; } -static bool bpf_program__is_type(struct bpf_program *prog, +static bool bpf_program__is_type(const struct bpf_program *prog, enum bpf_prog_type type) { return prog ? (prog->type == type) : false; } -#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ -int bpf_program__set_##NAME(struct bpf_program *prog) \ -{ \ - if (!prog) \ - return -EINVAL; \ - bpf_program__set_type(prog, TYPE); \ - return 0; \ -} \ - \ -bool bpf_program__is_##NAME(struct bpf_program *prog) \ -{ \ - return bpf_program__is_type(prog, TYPE); \ -} \ +#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ +int bpf_program__set_##NAME(struct bpf_program *prog) \ +{ \ + if (!prog) \ + return -EINVAL; \ + bpf_program__set_type(prog, TYPE); \ + return 0; \ +} \ + \ +bool bpf_program__is_##NAME(const struct bpf_program *prog) \ +{ \ + return bpf_program__is_type(prog, TYPE); \ +} \ BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER); BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); @@ -3216,6 +3623,10 @@ static const struct { BPF_CGROUP_UDP6_RECVMSG), BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_CGROUP_SYSCTL), + BPF_EAPROG_SEC("cgroup/getsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, + BPF_CGROUP_GETSOCKOPT), + BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, + BPF_CGROUP_SETSOCKOPT), }; #undef BPF_PROG_SEC_IMPL @@ -3314,17 +3725,17 @@ bpf_program__identify_section(struct bpf_program *prog, expected_attach_type); } -int bpf_map__fd(struct bpf_map *map) +int bpf_map__fd(const struct bpf_map *map) { return map ? map->fd : -EINVAL; } -const struct bpf_map_def *bpf_map__def(struct bpf_map *map) +const struct bpf_map_def *bpf_map__def(const struct bpf_map *map) { return map ? &map->def : ERR_PTR(-EINVAL); } -const char *bpf_map__name(struct bpf_map *map) +const char *bpf_map__name(const struct bpf_map *map) { return map ? map->name : NULL; } @@ -3355,17 +3766,17 @@ int bpf_map__set_priv(struct bpf_map *map, void *priv, return 0; } -void *bpf_map__priv(struct bpf_map *map) +void *bpf_map__priv(const struct bpf_map *map) { return map ? map->priv : ERR_PTR(-EINVAL); } -bool bpf_map__is_offload_neutral(struct bpf_map *map) +bool bpf_map__is_offload_neutral(const struct bpf_map *map) { return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; } -bool bpf_map__is_internal(struct bpf_map *map) +bool bpf_map__is_internal(const struct bpf_map *map) { return map->libbpf_type != LIBBPF_MAP_UNSPEC; } @@ -3390,7 +3801,7 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) } static struct bpf_map * -__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i) +__bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) { ssize_t idx; struct bpf_map *s, *e; @@ -3414,7 +3825,7 @@ __bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i) } struct bpf_map * -bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) +bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj) { if (prev == NULL) return obj->maps; @@ -3423,7 +3834,7 @@ bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) } struct bpf_map * -bpf_map__prev(struct bpf_map *next, struct bpf_object *obj) +bpf_map__prev(const struct bpf_map *next, const struct bpf_object *obj) { if (next == NULL) { if (!obj->nr_maps) @@ -3435,7 +3846,7 @@ bpf_map__prev(struct bpf_map *next, struct bpf_object *obj) } struct bpf_map * -bpf_object__find_map_by_name(struct bpf_object *obj, const char *name) +bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name) { struct bpf_map *pos; @@ -3447,7 +3858,7 @@ bpf_object__find_map_by_name(struct bpf_object *obj, const char *name) } int -bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name) +bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name) { return bpf_map__fd(bpf_object__find_map_by_name(obj, name)); } @@ -3455,20 +3866,12 @@ bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name) struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset) { - int i; - - for (i = 0; i < obj->nr_maps; i++) { - if (obj->maps[i].offset == offset) - return &obj->maps[i]; - } - return ERR_PTR(-ENOENT); + return ERR_PTR(-ENOTSUP); } long libbpf_get_error(const void *ptr) { - if (IS_ERR(ptr)) - return PTR_ERR(ptr); - return 0; + return PTR_ERR_OR_ZERO(ptr); } int bpf_prog_load(const char *file, enum bpf_prog_type type, @@ -3487,10 +3890,7 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type, int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, struct bpf_object **pobj, int *prog_fd) { - struct bpf_object_open_attr open_attr = { - .file = attr->file, - .prog_type = attr->prog_type, - }; + struct bpf_object_open_attr open_attr = {}; struct bpf_program *prog, *first_prog = NULL; enum bpf_attach_type expected_attach_type; enum bpf_prog_type prog_type; @@ -3503,6 +3903,9 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, if (!attr->file) return -EINVAL; + open_attr.file = attr->file; + open_attr.prog_type = attr->prog_type; + obj = bpf_object__open_xattr(&open_attr); if (IS_ERR_OR_NULL(obj)) return -ENOENT; @@ -3529,6 +3932,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, expected_attach_type); prog->log_level = attr->log_level; + prog->prog_flags = attr->prog_flags; if (!first_prog) first_prog = prog; } @@ -3555,6 +3959,372 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, return 0; } +struct bpf_link { + int (*destroy)(struct bpf_link *link); +}; + +int bpf_link__destroy(struct bpf_link *link) +{ + int err; + + if (!link) + return 0; + + err = link->destroy(link); + free(link); + + return err; +} + +struct bpf_link_fd { + struct bpf_link link; /* has to be at the top of struct */ + int fd; /* hook FD */ +}; + +static int bpf_link__destroy_perf_event(struct bpf_link *link) +{ + struct bpf_link_fd *l = (void *)link; + int err; + + err = ioctl(l->fd, PERF_EVENT_IOC_DISABLE, 0); + if (err) + err = -errno; + + close(l->fd); + return err; +} + +struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, + int pfd) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link_fd *link; + int prog_fd, err; + + if (pfd < 0) { + pr_warning("program '%s': invalid perf event FD %d\n", + bpf_program__title(prog, false), pfd); + return ERR_PTR(-EINVAL); + } + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warning("program '%s': can't attach BPF program w/o FD (did you load it?)\n", + bpf_program__title(prog, false)); + return ERR_PTR(-EINVAL); + } + + link = malloc(sizeof(*link)); + if (!link) + return ERR_PTR(-ENOMEM); + link->link.destroy = &bpf_link__destroy_perf_event; + link->fd = pfd; + + if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) { + err = -errno; + free(link); + pr_warning("program '%s': failed to attach to pfd %d: %s\n", + bpf_program__title(prog, false), pfd, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return ERR_PTR(err); + } + if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) { + err = -errno; + free(link); + pr_warning("program '%s': failed to enable pfd %d: %s\n", + bpf_program__title(prog, false), pfd, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return ERR_PTR(err); + } + return (struct bpf_link *)link; +} + +/* + * this function is expected to parse integer in the range of [0, 2^31-1] from + * given file using scanf format string fmt. If actual parsed value is + * negative, the result might be indistinguishable from error + */ +static int parse_uint_from_file(const char *file, const char *fmt) +{ + char buf[STRERR_BUFSIZE]; + int err, ret; + FILE *f; + + f = fopen(file, "r"); + if (!f) { + err = -errno; + pr_debug("failed to open '%s': %s\n", file, + libbpf_strerror_r(err, buf, sizeof(buf))); + return err; + } + err = fscanf(f, fmt, &ret); + if (err != 1) { + err = err == EOF ? -EIO : -errno; + pr_debug("failed to parse '%s': %s\n", file, + libbpf_strerror_r(err, buf, sizeof(buf))); + fclose(f); + return err; + } + fclose(f); + return ret; +} + +static int determine_kprobe_perf_type(void) +{ + const char *file = "/sys/bus/event_source/devices/kprobe/type"; + + return parse_uint_from_file(file, "%d\n"); +} + +static int determine_uprobe_perf_type(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/type"; + + return parse_uint_from_file(file, "%d\n"); +} + +static int determine_kprobe_retprobe_bit(void) +{ + const char *file = "/sys/bus/event_source/devices/kprobe/format/retprobe"; + + return parse_uint_from_file(file, "config:%d\n"); +} + +static int determine_uprobe_retprobe_bit(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/format/retprobe"; + + return parse_uint_from_file(file, "config:%d\n"); +} + +static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, + uint64_t offset, int pid) +{ + struct perf_event_attr attr = {}; + char errmsg[STRERR_BUFSIZE]; + int type, pfd, err; + + type = uprobe ? determine_uprobe_perf_type() + : determine_kprobe_perf_type(); + if (type < 0) { + pr_warning("failed to determine %s perf type: %s\n", + uprobe ? "uprobe" : "kprobe", + libbpf_strerror_r(type, errmsg, sizeof(errmsg))); + return type; + } + if (retprobe) { + int bit = uprobe ? determine_uprobe_retprobe_bit() + : determine_kprobe_retprobe_bit(); + + if (bit < 0) { + pr_warning("failed to determine %s retprobe bit: %s\n", + uprobe ? "uprobe" : "kprobe", + libbpf_strerror_r(bit, errmsg, + sizeof(errmsg))); + return bit; + } + attr.config |= 1 << bit; + } + attr.size = sizeof(attr); + attr.type = type; + attr.config1 = (uint64_t)(void *)name; /* kprobe_func or uprobe_path */ + attr.config2 = offset; /* kprobe_addr or probe_offset */ + + /* pid filter is meaningful only for uprobes */ + pfd = syscall(__NR_perf_event_open, &attr, + pid < 0 ? -1 : pid /* pid */, + pid == -1 ? 0 : -1 /* cpu */, + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warning("%s perf_event_open() failed: %s\n", + uprobe ? "uprobe" : "kprobe", + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + return pfd; +} + +struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, + bool retprobe, + const char *func_name) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int pfd, err; + + pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name, + 0 /* offset */, -1 /* pid */); + if (pfd < 0) { + pr_warning("program '%s': failed to create %s '%s' perf event: %s\n", + bpf_program__title(prog, false), + retprobe ? "kretprobe" : "kprobe", func_name, + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link = bpf_program__attach_perf_event(prog, pfd); + if (IS_ERR(link)) { + close(pfd); + err = PTR_ERR(link); + pr_warning("program '%s': failed to attach to %s '%s': %s\n", + bpf_program__title(prog, false), + retprobe ? "kretprobe" : "kprobe", func_name, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return link; + } + return link; +} + +struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog, + bool retprobe, pid_t pid, + const char *binary_path, + size_t func_offset) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int pfd, err; + + pfd = perf_event_open_probe(true /* uprobe */, retprobe, + binary_path, func_offset, pid); + if (pfd < 0) { + pr_warning("program '%s': failed to create %s '%s:0x%zx' perf event: %s\n", + bpf_program__title(prog, false), + retprobe ? "uretprobe" : "uprobe", + binary_path, func_offset, + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link = bpf_program__attach_perf_event(prog, pfd); + if (IS_ERR(link)) { + close(pfd); + err = PTR_ERR(link); + pr_warning("program '%s': failed to attach to %s '%s:0x%zx': %s\n", + bpf_program__title(prog, false), + retprobe ? "uretprobe" : "uprobe", + binary_path, func_offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return link; + } + return link; +} + +static int determine_tracepoint_id(const char *tp_category, + const char *tp_name) +{ + char file[PATH_MAX]; + int ret; + + ret = snprintf(file, sizeof(file), + "/sys/kernel/debug/tracing/events/%s/%s/id", + tp_category, tp_name); + if (ret < 0) + return -errno; + if (ret >= sizeof(file)) { + pr_debug("tracepoint %s/%s path is too long\n", + tp_category, tp_name); + return -E2BIG; + } + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_open_tracepoint(const char *tp_category, + const char *tp_name) +{ + struct perf_event_attr attr = {}; + char errmsg[STRERR_BUFSIZE]; + int tp_id, pfd, err; + + tp_id = determine_tracepoint_id(tp_category, tp_name); + if (tp_id < 0) { + pr_warning("failed to determine tracepoint '%s/%s' perf event ID: %s\n", + tp_category, tp_name, + libbpf_strerror_r(tp_id, errmsg, sizeof(errmsg))); + return tp_id; + } + + attr.type = PERF_TYPE_TRACEPOINT; + attr.size = sizeof(attr); + attr.config = tp_id; + + pfd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu */, + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warning("tracepoint '%s/%s' perf_event_open() failed: %s\n", + tp_category, tp_name, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + return pfd; +} + +struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog, + const char *tp_category, + const char *tp_name) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int pfd, err; + + pfd = perf_event_open_tracepoint(tp_category, tp_name); + if (pfd < 0) { + pr_warning("program '%s': failed to create tracepoint '%s/%s' perf event: %s\n", + bpf_program__title(prog, false), + tp_category, tp_name, + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link = bpf_program__attach_perf_event(prog, pfd); + if (IS_ERR(link)) { + close(pfd); + err = PTR_ERR(link); + pr_warning("program '%s': failed to attach to tracepoint '%s/%s': %s\n", + bpf_program__title(prog, false), + tp_category, tp_name, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return link; + } + return link; +} + +static int bpf_link__destroy_fd(struct bpf_link *link) +{ + struct bpf_link_fd *l = (void *)link; + + return close(l->fd); +} + +struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, + const char *tp_name) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link_fd *link; + int prog_fd, pfd; + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warning("program '%s': can't attach before loaded\n", + bpf_program__title(prog, false)); + return ERR_PTR(-EINVAL); + } + + link = malloc(sizeof(*link)); + if (!link) + return ERR_PTR(-ENOMEM); + link->link.destroy = &bpf_link__destroy_fd; + + pfd = bpf_raw_tracepoint_open(tp_name, prog_fd); + if (pfd < 0) { + pfd = -errno; + free(link); + pr_warning("program '%s': failed to attach to raw tracepoint '%s': %s\n", + bpf_program__title(prog, false), tp_name, + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link->fd = pfd; + return (struct bpf_link *)link; +} + enum bpf_perf_event_ret bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, void **copy_mem, size_t *copy_size, @@ -3603,6 +4373,370 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, return ret; } +struct perf_buffer; + +struct perf_buffer_params { + struct perf_event_attr *attr; + /* if event_cb is specified, it takes precendence */ + perf_buffer_event_fn event_cb; + /* sample_cb and lost_cb are higher-level common-case callbacks */ + perf_buffer_sample_fn sample_cb; + perf_buffer_lost_fn lost_cb; + void *ctx; + int cpu_cnt; + int *cpus; + int *map_keys; +}; + +struct perf_cpu_buf { + struct perf_buffer *pb; + void *base; /* mmap()'ed memory */ + void *buf; /* for reconstructing segmented data */ + size_t buf_size; + int fd; + int cpu; + int map_key; +}; + +struct perf_buffer { + perf_buffer_event_fn event_cb; + perf_buffer_sample_fn sample_cb; + perf_buffer_lost_fn lost_cb; + void *ctx; /* passed into callbacks */ + + size_t page_size; + size_t mmap_size; + struct perf_cpu_buf **cpu_bufs; + struct epoll_event *events; + int cpu_cnt; + int epoll_fd; /* perf event FD */ + int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */ +}; + +static void perf_buffer__free_cpu_buf(struct perf_buffer *pb, + struct perf_cpu_buf *cpu_buf) +{ + if (!cpu_buf) + return; + if (cpu_buf->base && + munmap(cpu_buf->base, pb->mmap_size + pb->page_size)) + pr_warning("failed to munmap cpu_buf #%d\n", cpu_buf->cpu); + if (cpu_buf->fd >= 0) { + ioctl(cpu_buf->fd, PERF_EVENT_IOC_DISABLE, 0); + close(cpu_buf->fd); + } + free(cpu_buf->buf); + free(cpu_buf); +} + +void perf_buffer__free(struct perf_buffer *pb) +{ + int i; + + if (!pb) + return; + if (pb->cpu_bufs) { + for (i = 0; i < pb->cpu_cnt && pb->cpu_bufs[i]; i++) { + struct perf_cpu_buf *cpu_buf = pb->cpu_bufs[i]; + + bpf_map_delete_elem(pb->map_fd, &cpu_buf->map_key); + perf_buffer__free_cpu_buf(pb, cpu_buf); + } + free(pb->cpu_bufs); + } + if (pb->epoll_fd >= 0) + close(pb->epoll_fd); + free(pb->events); + free(pb); +} + +static struct perf_cpu_buf * +perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr, + int cpu, int map_key) +{ + struct perf_cpu_buf *cpu_buf; + char msg[STRERR_BUFSIZE]; + int err; + + cpu_buf = calloc(1, sizeof(*cpu_buf)); + if (!cpu_buf) + return ERR_PTR(-ENOMEM); + + cpu_buf->pb = pb; + cpu_buf->cpu = cpu; + cpu_buf->map_key = map_key; + + cpu_buf->fd = syscall(__NR_perf_event_open, attr, -1 /* pid */, cpu, + -1, PERF_FLAG_FD_CLOEXEC); + if (cpu_buf->fd < 0) { + err = -errno; + pr_warning("failed to open perf buffer event on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + cpu_buf->base = mmap(NULL, pb->mmap_size + pb->page_size, + PROT_READ | PROT_WRITE, MAP_SHARED, + cpu_buf->fd, 0); + if (cpu_buf->base == MAP_FAILED) { + cpu_buf->base = NULL; + err = -errno; + pr_warning("failed to mmap perf buffer on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + if (ioctl(cpu_buf->fd, PERF_EVENT_IOC_ENABLE, 0) < 0) { + err = -errno; + pr_warning("failed to enable perf buffer event on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + return cpu_buf; + +error: + perf_buffer__free_cpu_buf(pb, cpu_buf); + return (struct perf_cpu_buf *)ERR_PTR(err); +} + +static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, + struct perf_buffer_params *p); + +struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, + const struct perf_buffer_opts *opts) +{ + struct perf_buffer_params p = {}; + struct perf_event_attr attr = { + .config = PERF_COUNT_SW_BPF_OUTPUT, + .type = PERF_TYPE_SOFTWARE, + .sample_type = PERF_SAMPLE_RAW, + .sample_period = 1, + .wakeup_events = 1, + }; + + p.attr = &attr; + p.sample_cb = opts ? opts->sample_cb : NULL; + p.lost_cb = opts ? opts->lost_cb : NULL; + p.ctx = opts ? opts->ctx : NULL; + + return __perf_buffer__new(map_fd, page_cnt, &p); +} + +struct perf_buffer * +perf_buffer__new_raw(int map_fd, size_t page_cnt, + const struct perf_buffer_raw_opts *opts) +{ + struct perf_buffer_params p = {}; + + p.attr = opts->attr; + p.event_cb = opts->event_cb; + p.ctx = opts->ctx; + p.cpu_cnt = opts->cpu_cnt; + p.cpus = opts->cpus; + p.map_keys = opts->map_keys; + + return __perf_buffer__new(map_fd, page_cnt, &p); +} + +static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, + struct perf_buffer_params *p) +{ + struct bpf_map_info map = {}; + char msg[STRERR_BUFSIZE]; + struct perf_buffer *pb; + __u32 map_info_len; + int err, i; + + if (page_cnt & (page_cnt - 1)) { + pr_warning("page count should be power of two, but is %zu\n", + page_cnt); + return ERR_PTR(-EINVAL); + } + + map_info_len = sizeof(map); + err = bpf_obj_get_info_by_fd(map_fd, &map, &map_info_len); + if (err) { + err = -errno; + pr_warning("failed to get map info for map FD %d: %s\n", + map_fd, libbpf_strerror_r(err, msg, sizeof(msg))); + return ERR_PTR(err); + } + + if (map.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + pr_warning("map '%s' should be BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", + map.name); + return ERR_PTR(-EINVAL); + } + + pb = calloc(1, sizeof(*pb)); + if (!pb) + return ERR_PTR(-ENOMEM); + + pb->event_cb = p->event_cb; + pb->sample_cb = p->sample_cb; + pb->lost_cb = p->lost_cb; + pb->ctx = p->ctx; + + pb->page_size = getpagesize(); + pb->mmap_size = pb->page_size * page_cnt; + pb->map_fd = map_fd; + + pb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (pb->epoll_fd < 0) { + err = -errno; + pr_warning("failed to create epoll instance: %s\n", + libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + if (p->cpu_cnt > 0) { + pb->cpu_cnt = p->cpu_cnt; + } else { + pb->cpu_cnt = libbpf_num_possible_cpus(); + if (pb->cpu_cnt < 0) { + err = pb->cpu_cnt; + goto error; + } + if (map.max_entries < pb->cpu_cnt) + pb->cpu_cnt = map.max_entries; + } + + pb->events = calloc(pb->cpu_cnt, sizeof(*pb->events)); + if (!pb->events) { + err = -ENOMEM; + pr_warning("failed to allocate events: out of memory\n"); + goto error; + } + pb->cpu_bufs = calloc(pb->cpu_cnt, sizeof(*pb->cpu_bufs)); + if (!pb->cpu_bufs) { + err = -ENOMEM; + pr_warning("failed to allocate buffers: out of memory\n"); + goto error; + } + + for (i = 0; i < pb->cpu_cnt; i++) { + struct perf_cpu_buf *cpu_buf; + int cpu, map_key; + + cpu = p->cpu_cnt > 0 ? p->cpus[i] : i; + map_key = p->cpu_cnt > 0 ? p->map_keys[i] : i; + + cpu_buf = perf_buffer__open_cpu_buf(pb, p->attr, cpu, map_key); + if (IS_ERR(cpu_buf)) { + err = PTR_ERR(cpu_buf); + goto error; + } + + pb->cpu_bufs[i] = cpu_buf; + + err = bpf_map_update_elem(pb->map_fd, &map_key, + &cpu_buf->fd, 0); + if (err) { + err = -errno; + pr_warning("failed to set cpu #%d, key %d -> perf FD %d: %s\n", + cpu, map_key, cpu_buf->fd, + libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + pb->events[i].events = EPOLLIN; + pb->events[i].data.ptr = cpu_buf; + if (epoll_ctl(pb->epoll_fd, EPOLL_CTL_ADD, cpu_buf->fd, + &pb->events[i]) < 0) { + err = -errno; + pr_warning("failed to epoll_ctl cpu #%d perf FD %d: %s\n", + cpu, cpu_buf->fd, + libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + } + + return pb; + +error: + if (pb) + perf_buffer__free(pb); + return ERR_PTR(err); +} + +struct perf_sample_raw { + struct perf_event_header header; + uint32_t size; + char data[0]; +}; + +struct perf_sample_lost { + struct perf_event_header header; + uint64_t id; + uint64_t lost; + uint64_t sample_id; +}; + +static enum bpf_perf_event_ret +perf_buffer__process_record(struct perf_event_header *e, void *ctx) +{ + struct perf_cpu_buf *cpu_buf = ctx; + struct perf_buffer *pb = cpu_buf->pb; + void *data = e; + + /* user wants full control over parsing perf event */ + if (pb->event_cb) + return pb->event_cb(pb->ctx, cpu_buf->cpu, e); + + switch (e->type) { + case PERF_RECORD_SAMPLE: { + struct perf_sample_raw *s = data; + + if (pb->sample_cb) + pb->sample_cb(pb->ctx, cpu_buf->cpu, s->data, s->size); + break; + } + case PERF_RECORD_LOST: { + struct perf_sample_lost *s = data; + + if (pb->lost_cb) + pb->lost_cb(pb->ctx, cpu_buf->cpu, s->lost); + break; + } + default: + pr_warning("unknown perf sample type %d\n", e->type); + return LIBBPF_PERF_EVENT_ERROR; + } + return LIBBPF_PERF_EVENT_CONT; +} + +static int perf_buffer__process_records(struct perf_buffer *pb, + struct perf_cpu_buf *cpu_buf) +{ + enum bpf_perf_event_ret ret; + + ret = bpf_perf_event_read_simple(cpu_buf->base, pb->mmap_size, + pb->page_size, &cpu_buf->buf, + &cpu_buf->buf_size, + perf_buffer__process_record, cpu_buf); + if (ret != LIBBPF_PERF_EVENT_CONT) + return ret; + return 0; +} + +int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) +{ + int i, cnt, err; + + cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms); + for (i = 0; i < cnt; i++) { + struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr; + + err = perf_buffer__process_records(pb, cpu_buf); + if (err) { + pr_warning("error while processing records: %d\n", err); + return err; + } + } + return cnt < 0 ? -errno : cnt; +} + struct bpf_prog_info_array_desc { int array_offset; /* e.g. offset of jited_prog_insns */ int count_offset; /* e.g. offset of jited_prog_len */ @@ -3848,3 +4982,60 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear) desc->array_offset, addr); } } + +int libbpf_num_possible_cpus(void) +{ + static const char *fcpu = "/sys/devices/system/cpu/possible"; + int len = 0, n = 0, il = 0, ir = 0; + unsigned int start = 0, end = 0; + static int cpus; + char buf[128]; + int error = 0; + int fd = -1; + + if (cpus > 0) + return cpus; + + fd = open(fcpu, O_RDONLY); + if (fd < 0) { + error = errno; + pr_warning("Failed to open file %s: %s\n", + fcpu, strerror(error)); + return -error; + } + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len <= 0) { + error = len ? errno : EINVAL; + pr_warning("Failed to read # of possible cpus from %s: %s\n", + fcpu, strerror(error)); + return -error; + } + if (len == sizeof(buf)) { + pr_warning("File %s size overflow\n", fcpu); + return -EOVERFLOW; + } + buf[len] = '\0'; + + for (ir = 0, cpus = 0; ir <= len; ir++) { + /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ + if (buf[ir] == ',' || buf[ir] == '\0') { + buf[ir] = '\0'; + n = sscanf(&buf[il], "%u-%u", &start, &end); + if (n <= 0) { + pr_warning("Failed to get # CPUs from %s\n", + &buf[il]); + return -EINVAL; + } else if (n == 1) { + end = start; + } + cpus += end - start + 1; + il = ir + 1; + } + } + if (cpus <= 0) { + pr_warning("Invalid #CPUs %d from %s\n", cpus, fcpu); + return -EINVAL; + } + return cpus; +} |