diff options
Diffstat (limited to '')
27 files changed, 939 insertions, 328 deletions
diff --git a/tools/lib/api/fd/array.h b/tools/lib/api/fd/array.h index 60ad197c8ee9..5c01f7b05dfb 100644 --- a/tools/lib/api/fd/array.h +++ b/tools/lib/api/fd/array.h @@ -31,8 +31,9 @@ struct fdarray { }; enum fdarray_flags { - fdarray_flag__default = 0x00000000, - fdarray_flag__nonfilterable = 0x00000001 + fdarray_flag__default = 0x00000000, + fdarray_flag__nonfilterable = 0x00000001, + fdarray_flag__non_perf_event = 0x00000002, }; void fdarray__init(struct fdarray *fda, int nr_autogrow); diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index efcc06dafbd9..1d49a0352836 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -84,9 +84,7 @@ static inline int sys_bpf_fd(enum bpf_cmd cmd, union bpf_attr *attr, return ensure_good_fd(fd); } -#define PROG_LOAD_ATTEMPTS 5 - -static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts) +int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts) { int fd; @@ -107,7 +105,7 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int */ int probe_memcg_account(void) { - const size_t prog_load_attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd); + const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd); struct bpf_insn insns[] = { BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns), BPF_EXIT_INSN(), @@ -117,13 +115,13 @@ int probe_memcg_account(void) int prog_fd; /* attempt loading freplace trying to use custom BTF */ - memset(&attr, 0, prog_load_attr_sz); + memset(&attr, 0, attr_sz); attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; attr.insns = ptr_to_u64(insns); attr.insn_cnt = insn_cnt; attr.license = ptr_to_u64("GPL"); - prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, prog_load_attr_sz); + prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz); if (prog_fd >= 0) { close(prog_fd); return 1; @@ -183,7 +181,7 @@ int bpf_map_create(enum bpf_map_type map_type, return libbpf_err(-EINVAL); attr.map_type = map_type; - if (map_name) + if (map_name && kernel_supports(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); attr.key_size = key_size; attr.value_size = value_size; @@ -234,6 +232,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, size_t insn_cnt, const struct bpf_prog_load_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, fd_array); void *finfo = NULL, *linfo = NULL; const char *func_info, *line_info; __u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd; @@ -253,7 +252,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, if (attempts == 0) attempts = PROG_LOAD_ATTEMPTS; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.prog_type = prog_type; attr.expected_attach_type = OPTS_GET(opts, expected_attach_type, 0); @@ -263,7 +262,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0); attr.kern_version = OPTS_GET(opts, kern_version, 0); - if (prog_name) + if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); attr.license = ptr_to_u64(license); @@ -316,7 +315,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.log_level = log_level; } - fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts); + fd = sys_bpf_prog_load(&attr, attr_sz, attempts); if (fd >= 0) return fd; @@ -356,7 +355,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, break; } - fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts); + fd = sys_bpf_prog_load(&attr, attr_sz, attempts); if (fd >= 0) goto done; } @@ -370,7 +369,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.log_size = log_size; attr.log_level = 1; - fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts); + fd = sys_bpf_prog_load(&attr, attr_sz, attempts); } done: /* free() doesn't affect errno, so we don't need to restore it */ @@ -382,127 +381,136 @@ done: int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags) { + const size_t attr_sz = offsetofend(union bpf_attr, flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); attr.flags = flags; - ret = sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_lookup_elem(int fd, const void *key, void *value) { + const size_t attr_sz = offsetofend(union bpf_attr, flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); - ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags) { + const size_t attr_sz = offsetofend(union bpf_attr, flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); attr.flags = flags; - ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value) { + const size_t attr_sz = offsetofend(union bpf_attr, flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); - ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, __u64 flags) { + const size_t attr_sz = offsetofend(union bpf_attr, flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); attr.flags = flags; - ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_delete_elem(int fd, const void *key) { + const size_t attr_sz = offsetofend(union bpf_attr, flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); - ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_delete_elem_flags(int fd, const void *key, __u64 flags) { + const size_t attr_sz = offsetofend(union bpf_attr, flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.flags = flags; - ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_get_next_key(int fd, const void *key, void *next_key) { + const size_t attr_sz = offsetofend(union bpf_attr, next_key); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.next_key = ptr_to_u64(next_key); - ret = sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_freeze(int fd) { + const size_t attr_sz = offsetofend(union bpf_attr, map_fd); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; - ret = sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_FREEZE, &attr, attr_sz); return libbpf_err_errno(ret); } @@ -511,13 +519,14 @@ static int bpf_map_batch_common(int cmd, int fd, void *in_batch, __u32 *count, const struct bpf_map_batch_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, batch); union bpf_attr attr; int ret; if (!OPTS_VALID(opts, bpf_map_batch_opts)) return libbpf_err(-EINVAL); - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.batch.map_fd = fd; attr.batch.in_batch = ptr_to_u64(in_batch); attr.batch.out_batch = ptr_to_u64(out_batch); @@ -527,7 +536,7 @@ static int bpf_map_batch_common(int cmd, int fd, void *in_batch, attr.batch.elem_flags = OPTS_GET(opts, elem_flags, 0); attr.batch.flags = OPTS_GET(opts, flags, 0); - ret = sys_bpf(cmd, &attr, sizeof(attr)); + ret = sys_bpf(cmd, &attr, attr_sz); *count = attr.batch.count; return libbpf_err_errno(ret); @@ -566,14 +575,15 @@ int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *co int bpf_obj_pin(int fd, const char *pathname) { + const size_t attr_sz = offsetofend(union bpf_attr, file_flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.pathname = ptr_to_u64((void *)pathname); attr.bpf_fd = fd; - ret = sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr)); + ret = sys_bpf(BPF_OBJ_PIN, &attr, attr_sz); return libbpf_err_errno(ret); } @@ -584,17 +594,18 @@ int bpf_obj_get(const char *pathname) int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, file_flags); union bpf_attr attr; int fd; if (!OPTS_VALID(opts, bpf_obj_get_opts)) return libbpf_err(-EINVAL); - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.pathname = ptr_to_u64((void *)pathname); attr.file_flags = OPTS_GET(opts, file_flags, 0); - fd = sys_bpf_fd(BPF_OBJ_GET, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_OBJ_GET, &attr, attr_sz); return libbpf_err_errno(fd); } @@ -612,52 +623,50 @@ int bpf_prog_attach_opts(int prog_fd, int target_fd, enum bpf_attach_type type, const struct bpf_prog_attach_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); union bpf_attr attr; int ret; if (!OPTS_VALID(opts, bpf_prog_attach_opts)) return libbpf_err(-EINVAL); - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.target_fd = target_fd; attr.attach_bpf_fd = prog_fd; attr.attach_type = type; attr.attach_flags = OPTS_GET(opts, flags, 0); attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0); - ret = sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_ATTACH, &attr, attr_sz); return libbpf_err_errno(ret); } -__attribute__((alias("bpf_prog_attach_opts"))) -int bpf_prog_attach_xattr(int prog_fd, int target_fd, - enum bpf_attach_type type, - const struct bpf_prog_attach_opts *opts); - int bpf_prog_detach(int target_fd, enum bpf_attach_type type) { + const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.target_fd = target_fd; attr.attach_type = type; - ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) { + const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.target_fd = target_fd; attr.attach_bpf_fd = prog_fd; attr.attach_type = type; - ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz); return libbpf_err_errno(ret); } @@ -665,6 +674,7 @@ int bpf_link_create(int prog_fd, int target_fd, enum bpf_attach_type attach_type, const struct bpf_link_create_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, link_create); __u32 target_btf_id, iter_info_len; union bpf_attr attr; int fd, err; @@ -683,7 +693,7 @@ int bpf_link_create(int prog_fd, int target_fd, return libbpf_err(-EINVAL); } - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.link_create.prog_fd = prog_fd; attr.link_create.target_fd = target_fd; attr.link_create.attach_type = attach_type; @@ -727,7 +737,7 @@ int bpf_link_create(int prog_fd, int target_fd, break; } proceed: - fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, attr_sz); if (fd >= 0) return fd; /* we'll get EINVAL if LINK_CREATE doesn't support attaching fentry @@ -763,44 +773,47 @@ proceed: int bpf_link_detach(int link_fd) { + const size_t attr_sz = offsetofend(union bpf_attr, link_detach); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.link_detach.link_fd = link_fd; - ret = sys_bpf(BPF_LINK_DETACH, &attr, sizeof(attr)); + ret = sys_bpf(BPF_LINK_DETACH, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_link_update(int link_fd, int new_prog_fd, const struct bpf_link_update_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, link_update); union bpf_attr attr; int ret; if (!OPTS_VALID(opts, bpf_link_update_opts)) return libbpf_err(-EINVAL); - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.link_update.link_fd = link_fd; attr.link_update.new_prog_fd = new_prog_fd; attr.link_update.flags = OPTS_GET(opts, flags, 0); attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); - ret = sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr)); + ret = sys_bpf(BPF_LINK_UPDATE, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_iter_create(int link_fd) { + const size_t attr_sz = offsetofend(union bpf_attr, iter_create); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.iter_create.link_fd = link_fd; - fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, attr_sz); return libbpf_err_errno(fd); } @@ -808,13 +821,14 @@ int bpf_prog_query_opts(int target_fd, enum bpf_attach_type type, struct bpf_prog_query_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, query); union bpf_attr attr; int ret; if (!OPTS_VALID(opts, bpf_prog_query_opts)) return libbpf_err(-EINVAL); - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.query.target_fd = target_fd; attr.query.attach_type = type; @@ -823,7 +837,7 @@ int bpf_prog_query_opts(int target_fd, attr.query.prog_ids = ptr_to_u64(OPTS_GET(opts, prog_ids, NULL)); attr.query.prog_attach_flags = ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL)); - ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_QUERY, &attr, attr_sz); OPTS_SET(opts, attach_flags, attr.query.attach_flags); OPTS_SET(opts, prog_cnt, attr.query.prog_cnt); @@ -852,13 +866,14 @@ int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, test); union bpf_attr attr; int ret; if (!OPTS_VALID(opts, bpf_test_run_opts)) return libbpf_err(-EINVAL); - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.test.prog_fd = prog_fd; attr.test.batch_size = OPTS_GET(opts, batch_size, 0); attr.test.cpu = OPTS_GET(opts, cpu, 0); @@ -874,7 +889,7 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts) attr.test.data_in = ptr_to_u64(OPTS_GET(opts, data_in, NULL)); attr.test.data_out = ptr_to_u64(OPTS_GET(opts, data_out, NULL)); - ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, attr_sz); OPTS_SET(opts, data_size_out, attr.test.data_size_out); OPTS_SET(opts, ctx_size_out, attr.test.ctx_size_out); @@ -886,13 +901,14 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts) static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd) { + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); union bpf_attr attr; int err; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.start_id = start_id; - err = sys_bpf(cmd, &attr, sizeof(attr)); + err = sys_bpf(cmd, &attr, attr_sz); if (!err) *next_id = attr.next_id; @@ -921,80 +937,84 @@ int bpf_link_get_next_id(__u32 start_id, __u32 *next_id) int bpf_prog_get_fd_by_id(__u32 id) { + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.prog_id = id; - fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, attr_sz); return libbpf_err_errno(fd); } int bpf_map_get_fd_by_id(__u32 id) { + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_id = id; - fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, attr_sz); return libbpf_err_errno(fd); } int bpf_btf_get_fd_by_id(__u32 id) { + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.btf_id = id; - fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, attr_sz); return libbpf_err_errno(fd); } int bpf_link_get_fd_by_id(__u32 id) { + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.link_id = id; - fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, attr_sz); return libbpf_err_errno(fd); } int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len) { + const size_t attr_sz = offsetofend(union bpf_attr, info); union bpf_attr attr; int err; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.info.bpf_fd = bpf_fd; attr.info.info_len = *info_len; attr.info.info = ptr_to_u64(info); - err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr)); - + err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, attr_sz); if (!err) *info_len = attr.info.info_len; - return libbpf_err_errno(err); } int bpf_raw_tracepoint_open(const char *name, int prog_fd) { + const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.raw_tracepoint.name = ptr_to_u64(name); attr.raw_tracepoint.prog_fd = prog_fd; - fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz); return libbpf_err_errno(fd); } @@ -1050,16 +1070,18 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, __u64 *probe_addr) { - union bpf_attr attr = {}; + const size_t attr_sz = offsetofend(union bpf_attr, task_fd_query); + union bpf_attr attr; int err; + memset(&attr, 0, attr_sz); attr.task_fd_query.pid = pid; attr.task_fd_query.fd = fd; attr.task_fd_query.flags = flags; attr.task_fd_query.buf = ptr_to_u64(buf); attr.task_fd_query.buf_len = *buf_len; - err = sys_bpf(BPF_TASK_FD_QUERY, &attr, sizeof(attr)); + err = sys_bpf(BPF_TASK_FD_QUERY, &attr, attr_sz); *buf_len = attr.task_fd_query.buf_len; *prog_id = attr.task_fd_query.prog_id; @@ -1072,30 +1094,32 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, int bpf_enable_stats(enum bpf_stats_type type) { + const size_t attr_sz = offsetofend(union bpf_attr, enable_stats); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.enable_stats.type = type; - fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, attr_sz); return libbpf_err_errno(fd); } int bpf_prog_bind_map(int prog_fd, int map_fd, const struct bpf_prog_bind_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, prog_bind_map); union bpf_attr attr; int ret; if (!OPTS_VALID(opts, bpf_prog_bind_opts)) return libbpf_err(-EINVAL); - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.prog_bind_map.prog_fd = prog_fd; attr.prog_bind_map.map_fd = map_fd; attr.prog_bind_map.flags = OPTS_GET(opts, flags, 0); - ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz); return libbpf_err_errno(ret); } diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 7349b16b8e2f..d37c4fe2849d 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -160,18 +160,6 @@ bpf_tail_call_static(void *ctx, const void *map, const __u32 slot) } #endif -/* - * Helper structure used by eBPF C program - * to describe BPF map attributes to libbpf loader - */ -struct bpf_map_def { - unsigned int type; - unsigned int key_size; - unsigned int value_size; - unsigned int max_entries; - unsigned int map_flags; -} __attribute__((deprecated("use BTF-defined maps in .maps section"))); - enum libbpf_pin_type { LIBBPF_PIN_NONE, /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 43ca3aff2292..2972dc25ff72 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -426,7 +426,7 @@ struct pt_regs; */ #define BPF_PROG(name, args...) \ name(unsigned long long *ctx); \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(unsigned long long *ctx, ##args); \ typeof(name(0)) name(unsigned long long *ctx) \ { \ @@ -435,9 +435,116 @@ typeof(name(0)) name(unsigned long long *ctx) \ return ____##name(___bpf_ctx_cast(args)); \ _Pragma("GCC diagnostic pop") \ } \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(unsigned long long *ctx, ##args) +#ifndef ___bpf_nth2 +#define ___bpf_nth2(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13, \ + _14, _15, _16, _17, _18, _19, _20, _21, _22, _23, _24, N, ...) N +#endif +#ifndef ___bpf_narg2 +#define ___bpf_narg2(...) \ + ___bpf_nth2(_, ##__VA_ARGS__, 12, 12, 11, 11, 10, 10, 9, 9, 8, 8, 7, 7, \ + 6, 6, 5, 5, 4, 4, 3, 3, 2, 2, 1, 1, 0) +#endif + +#define ___bpf_treg_cnt(t) \ + __builtin_choose_expr(sizeof(t) == 1, 1, \ + __builtin_choose_expr(sizeof(t) == 2, 1, \ + __builtin_choose_expr(sizeof(t) == 4, 1, \ + __builtin_choose_expr(sizeof(t) == 8, 1, \ + __builtin_choose_expr(sizeof(t) == 16, 2, \ + (void)0))))) + +#define ___bpf_reg_cnt0() (0) +#define ___bpf_reg_cnt1(t, x) (___bpf_reg_cnt0() + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt2(t, x, args...) (___bpf_reg_cnt1(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt3(t, x, args...) (___bpf_reg_cnt2(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt4(t, x, args...) (___bpf_reg_cnt3(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt5(t, x, args...) (___bpf_reg_cnt4(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt6(t, x, args...) (___bpf_reg_cnt5(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt7(t, x, args...) (___bpf_reg_cnt6(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt8(t, x, args...) (___bpf_reg_cnt7(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt9(t, x, args...) (___bpf_reg_cnt8(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt10(t, x, args...) (___bpf_reg_cnt9(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt11(t, x, args...) (___bpf_reg_cnt10(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt12(t, x, args...) (___bpf_reg_cnt11(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt(args...) ___bpf_apply(___bpf_reg_cnt, ___bpf_narg2(args))(args) + +#define ___bpf_union_arg(t, x, n) \ + __builtin_choose_expr(sizeof(t) == 1, ({ union { __u8 z[1]; t x; } ___t = { .z = {ctx[n]}}; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 2, ({ union { __u16 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 4, ({ union { __u32 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 8, ({ union { __u64 z[1]; t x; } ___t = {.z = {ctx[n]} }; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 16, ({ union { __u64 z[2]; t x; } ___t = {.z = {ctx[n], ctx[n + 1]} }; ___t.x; }), \ + (void)0))))) + +#define ___bpf_ctx_arg0(n, args...) +#define ___bpf_ctx_arg1(n, t, x) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt1(t, x)) +#define ___bpf_ctx_arg2(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt2(t, x, args)) ___bpf_ctx_arg1(n, args) +#define ___bpf_ctx_arg3(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt3(t, x, args)) ___bpf_ctx_arg2(n, args) +#define ___bpf_ctx_arg4(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt4(t, x, args)) ___bpf_ctx_arg3(n, args) +#define ___bpf_ctx_arg5(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt5(t, x, args)) ___bpf_ctx_arg4(n, args) +#define ___bpf_ctx_arg6(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt6(t, x, args)) ___bpf_ctx_arg5(n, args) +#define ___bpf_ctx_arg7(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt7(t, x, args)) ___bpf_ctx_arg6(n, args) +#define ___bpf_ctx_arg8(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt8(t, x, args)) ___bpf_ctx_arg7(n, args) +#define ___bpf_ctx_arg9(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt9(t, x, args)) ___bpf_ctx_arg8(n, args) +#define ___bpf_ctx_arg10(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt10(t, x, args)) ___bpf_ctx_arg9(n, args) +#define ___bpf_ctx_arg11(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt11(t, x, args)) ___bpf_ctx_arg10(n, args) +#define ___bpf_ctx_arg12(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt12(t, x, args)) ___bpf_ctx_arg11(n, args) +#define ___bpf_ctx_arg(args...) ___bpf_apply(___bpf_ctx_arg, ___bpf_narg2(args))(___bpf_reg_cnt(args), args) + +#define ___bpf_ctx_decl0() +#define ___bpf_ctx_decl1(t, x) , t x +#define ___bpf_ctx_decl2(t, x, args...) , t x ___bpf_ctx_decl1(args) +#define ___bpf_ctx_decl3(t, x, args...) , t x ___bpf_ctx_decl2(args) +#define ___bpf_ctx_decl4(t, x, args...) , t x ___bpf_ctx_decl3(args) +#define ___bpf_ctx_decl5(t, x, args...) , t x ___bpf_ctx_decl4(args) +#define ___bpf_ctx_decl6(t, x, args...) , t x ___bpf_ctx_decl5(args) +#define ___bpf_ctx_decl7(t, x, args...) , t x ___bpf_ctx_decl6(args) +#define ___bpf_ctx_decl8(t, x, args...) , t x ___bpf_ctx_decl7(args) +#define ___bpf_ctx_decl9(t, x, args...) , t x ___bpf_ctx_decl8(args) +#define ___bpf_ctx_decl10(t, x, args...) , t x ___bpf_ctx_decl9(args) +#define ___bpf_ctx_decl11(t, x, args...) , t x ___bpf_ctx_decl10(args) +#define ___bpf_ctx_decl12(t, x, args...) , t x ___bpf_ctx_decl11(args) +#define ___bpf_ctx_decl(args...) ___bpf_apply(___bpf_ctx_decl, ___bpf_narg2(args))(args) + +/* + * BPF_PROG2 is an enhanced version of BPF_PROG in order to handle struct + * arguments. Since each struct argument might take one or two u64 values + * in the trampoline stack, argument type size is needed to place proper number + * of u64 values for each argument. Therefore, BPF_PROG2 has different + * syntax from BPF_PROG. For example, for the following BPF_PROG syntax: + * + * int BPF_PROG(test2, int a, int b) { ... } + * + * the corresponding BPF_PROG2 syntax is: + * + * int BPF_PROG2(test2, int, a, int, b) { ... } + * + * where type and the corresponding argument name are separated by comma. + * + * Use BPF_PROG2 macro if one of the arguments might be a struct/union larger + * than 8 bytes: + * + * int BPF_PROG2(test_struct_arg, struct bpf_testmod_struct_arg_1, a, int, b, + * int, c, int, d, struct bpf_testmod_struct_arg_2, e, int, ret) + * { + * // access a, b, c, d, e, and ret directly + * ... + * } + */ +#define BPF_PROG2(name, args...) \ +name(unsigned long long *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx ___bpf_ctx_decl(args)); \ +typeof(name(0)) name(unsigned long long *ctx) \ +{ \ + return ____##name(ctx ___bpf_ctx_arg(args)); \ +} \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx ___bpf_ctx_decl(args)) + struct pt_regs; #define ___bpf_kprobe_args0() ctx @@ -460,7 +567,7 @@ struct pt_regs; */ #define BPF_KPROBE(name, args...) \ name(struct pt_regs *ctx); \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(struct pt_regs *ctx, ##args); \ typeof(name(0)) name(struct pt_regs *ctx) \ { \ @@ -469,7 +576,7 @@ typeof(name(0)) name(struct pt_regs *ctx) \ return ____##name(___bpf_kprobe_args(args)); \ _Pragma("GCC diagnostic pop") \ } \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(struct pt_regs *ctx, ##args) #define ___bpf_kretprobe_args0() ctx @@ -484,7 +591,7 @@ ____##name(struct pt_regs *ctx, ##args) */ #define BPF_KRETPROBE(name, args...) \ name(struct pt_regs *ctx); \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(struct pt_regs *ctx, ##args); \ typeof(name(0)) name(struct pt_regs *ctx) \ { \ @@ -540,7 +647,7 @@ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) #define BPF_KSYSCALL(name, args...) \ name(struct pt_regs *ctx); \ extern _Bool LINUX_HAS_SYSCALL_WRAPPER __kconfig; \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(struct pt_regs *ctx, ##args); \ typeof(name(0)) name(struct pt_regs *ctx) \ { \ @@ -555,7 +662,7 @@ typeof(name(0)) name(struct pt_regs *ctx) \ return ____##name(___bpf_syscall_args(args)); \ _Pragma("GCC diagnostic pop") \ } \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(struct pt_regs *ctx, ##args) #define BPF_KPROBE_SYSCALL BPF_KSYSCALL diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 2d14f1a52d7a..d88647da2c7f 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1225,8 +1225,6 @@ int btf__load_into_kernel(struct btf *btf) return btf_load_into_kernel(btf, NULL, 0, 0); } -int btf__load(struct btf *) __attribute__((alias("btf__load_into_kernel"))); - int btf__fd(const struct btf *btf) { return btf->fd; @@ -4644,20 +4642,17 @@ static int btf_dedup_remap_types(struct btf_dedup *d) */ struct btf *btf__load_vmlinux_btf(void) { - struct { - const char *path_fmt; - bool raw_btf; - } locations[] = { + const char *locations[] = { /* try canonical vmlinux BTF through sysfs first */ - { "/sys/kernel/btf/vmlinux", true /* raw BTF */ }, - /* fall back to trying to find vmlinux ELF on disk otherwise */ - { "/boot/vmlinux-%1$s" }, - { "/lib/modules/%1$s/vmlinux-%1$s" }, - { "/lib/modules/%1$s/build/vmlinux" }, - { "/usr/lib/modules/%1$s/kernel/vmlinux" }, - { "/usr/lib/debug/boot/vmlinux-%1$s" }, - { "/usr/lib/debug/boot/vmlinux-%1$s.debug" }, - { "/usr/lib/debug/lib/modules/%1$s/vmlinux" }, + "/sys/kernel/btf/vmlinux", + /* fall back to trying to find vmlinux on disk otherwise */ + "/boot/vmlinux-%1$s", + "/lib/modules/%1$s/vmlinux-%1$s", + "/lib/modules/%1$s/build/vmlinux", + "/usr/lib/modules/%1$s/kernel/vmlinux", + "/usr/lib/debug/boot/vmlinux-%1$s", + "/usr/lib/debug/boot/vmlinux-%1$s.debug", + "/usr/lib/debug/lib/modules/%1$s/vmlinux", }; char path[PATH_MAX + 1]; struct utsname buf; @@ -4667,15 +4662,12 @@ struct btf *btf__load_vmlinux_btf(void) uname(&buf); for (i = 0; i < ARRAY_SIZE(locations); i++) { - snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release); + snprintf(path, PATH_MAX, locations[i], buf.release); - if (access(path, R_OK)) + if (faccessat(AT_FDCWD, path, R_OK, AT_EACCESS)) continue; - if (locations[i].raw_btf) - btf = btf__parse_raw(path); - else - btf = btf__parse_elf(path, NULL); + btf = btf__parse(path, NULL); err = libbpf_get_error(btf); pr_debug("loading kernel BTF '%s': %d\n", path, err); if (err) diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 583760df83b4..8e6880d91c84 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -116,7 +116,6 @@ LIBBPF_API struct btf *btf__parse_raw_split(const char *path, struct btf *base_b LIBBPF_API struct btf *btf__load_vmlinux_btf(void); LIBBPF_API struct btf *btf__load_module_btf(const char *module_name, struct btf *vmlinux_btf); -LIBBPF_API struct btf *libbpf_find_kernel_btf(void); LIBBPF_API struct btf *btf__load_from_kernel_by_id(__u32 id); LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf); @@ -487,6 +486,8 @@ static inline struct btf_enum *btf_enum(const struct btf_type *t) return (struct btf_enum *)(t + 1); } +struct btf_enum64; + static inline struct btf_enum64 *btf_enum64(const struct btf_type *t) { return (struct btf_enum64 *)(t + 1); @@ -494,7 +495,28 @@ static inline struct btf_enum64 *btf_enum64(const struct btf_type *t) static inline __u64 btf_enum64_value(const struct btf_enum64 *e) { - return ((__u64)e->val_hi32 << 32) | e->val_lo32; + /* struct btf_enum64 is introduced in Linux 6.0, which is very + * bleeding-edge. Here we are avoiding relying on struct btf_enum64 + * definition coming from kernel UAPI headers to support wider range + * of system-wide kernel headers. + * + * Given this header can be also included from C++ applications, that + * further restricts C tricks we can use (like using compatible + * anonymous struct). So just treat struct btf_enum64 as + * a three-element array of u32 and access second (lo32) and third + * (hi32) elements directly. + * + * For reference, here is a struct btf_enum64 definition: + * + * const struct btf_enum64 { + * __u32 name_off; + * __u32 val_lo32; + * __u32 val_hi32; + * }; + */ + const __u32 *e64 = (const __u32 *)e; + + return ((__u64)e64[2] << 32) | e64[1]; } static inline struct btf_member *btf_members(const struct btf_type *t) diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 627edb5bb6de..4221f73a74d0 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -2385,7 +2385,7 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id, d->typed_dump->indent_lvl = OPTS_GET(opts, indent_level, 0); /* default indent string is a tab */ - if (!opts->indent_str) + if (!OPTS_GET(opts, indent_str, NULL)) d->typed_dump->indent_str[0] = '\t'; else libbpf_strlcpy(d->typed_dump->indent_str, opts->indent_str, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 50d41815f431..184ce1684dcd 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -163,6 +163,7 @@ static const char * const map_type_name[] = { [BPF_MAP_TYPE_INODE_STORAGE] = "inode_storage", [BPF_MAP_TYPE_TASK_STORAGE] = "task_storage", [BPF_MAP_TYPE_BLOOM_FILTER] = "bloom_filter", + [BPF_MAP_TYPE_USER_RINGBUF] = "user_ringbuf", }; static const char * const prog_type_name[] = { @@ -223,13 +224,18 @@ __printf(2, 3) void libbpf_print(enum libbpf_print_level level, const char *format, ...) { va_list args; + int old_errno; if (!__libbpf_pr) return; + old_errno = errno; + va_start(args, format); __libbpf_pr(level, format, args); va_end(args); + + errno = old_errno; } static void pr_perm_msg(int err) @@ -412,6 +418,7 @@ struct bpf_program { int fd; bool autoload; + bool autoattach; bool mark_btf_static; enum bpf_prog_type type; enum bpf_attach_type expected_attach_type; @@ -591,7 +598,6 @@ struct elf_state { size_t strtabidx; struct elf_sec_desc *secs; int sec_cnt; - int maps_shndx; int btf_maps_shndx; __u32 btf_maps_sec_btf_id; int text_shndx; @@ -751,6 +757,8 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, prog->autoload = true; } + prog->autoattach = true; + /* inherit object's log_level */ prog->log_level = obj->log_level; @@ -876,7 +884,7 @@ __u32 get_kernel_version(void) __u32 major, minor, patch; struct utsname info; - if (access(ubuntu_kver_file, R_OK) == 0) { + if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) == 0) { FILE *f; f = fopen(ubuntu_kver_file, "r"); @@ -1272,7 +1280,6 @@ 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.st_ops_shndx = -1; obj->kconfig_map_idx = -1; @@ -1642,6 +1649,10 @@ static int bpf_object__init_global_data_maps(struct bpf_object *obj) for (sec_idx = 1; sec_idx < obj->efile.sec_cnt; sec_idx++) { sec_desc = &obj->efile.secs[sec_idx]; + /* Skip recognized sections with size 0. */ + if (!sec_desc->data || sec_desc->data->d_size == 0) + continue; + switch (sec_desc->sec_type) { case SEC_DATA: sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx)); @@ -2086,19 +2097,30 @@ static bool get_map_field_int(const char *map_name, const struct btf *btf, return true; } +static int pathname_concat(char *buf, size_t buf_sz, const char *path, const char *name) +{ + int len; + + len = snprintf(buf, buf_sz, "%s/%s", path, name); + if (len < 0) + return -EINVAL; + if (len >= buf_sz) + return -ENAMETOOLONG; + + return 0; +} + static int build_map_pin_path(struct bpf_map *map, const char *path) { char buf[PATH_MAX]; - int len; + int err; if (!path) path = "/sys/fs/bpf"; - len = snprintf(buf, PATH_MAX, "%s/%s", path, bpf_map__name(map)); - if (len < 0) - return -EINVAL; - else if (len >= PATH_MAX) - return -ENAMETOOLONG; + err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map)); + if (err) + return err; return bpf_map__set_pin_path(map, buf); } @@ -2362,6 +2384,12 @@ static size_t adjust_ringbuf_sz(size_t sz) return sz; } +static bool map_is_ringbuf(const struct bpf_map *map) +{ + return map->def.type == BPF_MAP_TYPE_RINGBUF || + map->def.type == BPF_MAP_TYPE_USER_RINGBUF; +} + static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def) { map->def.type = def->map_type; @@ -2376,7 +2404,7 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def map->btf_value_type_id = def->value_type_id; /* auto-adjust BPF ringbuf map max_entries to be a multiple of page size */ - if (map->def.type == BPF_MAP_TYPE_RINGBUF) + if (map_is_ringbuf(map)) map->def.max_entries = adjust_ringbuf_sz(map->def.max_entries); if (def->parts & MAP_DEF_MAP_TYPE) @@ -3359,7 +3387,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) if (err) return err; } else if (strcmp(name, "maps") == 0) { - obj->efile.maps_shndx = idx; + pr_warn("elf: legacy map definitions in 'maps' section are not supported by libbpf v1.0+\n"); + return -ENOTSUP; } else if (strcmp(name, MAPS_ELF_SEC) == 0) { obj->efile.btf_maps_shndx = idx; } else if (strcmp(name, BTF_ELF_SEC) == 0) { @@ -3891,8 +3920,7 @@ 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 || - shndx == obj->efile.btf_maps_shndx; + return shndx == obj->efile.btf_maps_shndx; } static enum libbpf_map_type @@ -4277,11 +4305,12 @@ int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate) int bpf_map__reuse_fd(struct bpf_map *map, int fd) { - struct bpf_map_info info = {}; + struct bpf_map_info info; __u32 len = sizeof(info), name_len; int new_fd, err; char *new_name; + memset(&info, 0, len); err = bpf_obj_get_info_by_fd(fd, &info, &len); if (err && errno == EINVAL) err = bpf_get_map_info_from_fdinfo(fd, &info); @@ -4358,7 +4387,7 @@ int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) map->def.max_entries = max_entries; /* auto-adjust BPF ringbuf map max_entries to be a multiple of page size */ - if (map->def.type == BPF_MAP_TYPE_RINGBUF) + if (map_is_ringbuf(map)) map->def.max_entries = adjust_ringbuf_sz(map->def.max_entries); return 0; @@ -4408,14 +4437,23 @@ static int probe_fd(int fd) static int probe_kern_prog_name(void) { + const size_t attr_sz = offsetofend(union bpf_attr, prog_name); struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - int ret, insn_cnt = ARRAY_SIZE(insns); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.license = ptr_to_u64("GPL"); + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = (__u32)ARRAY_SIZE(insns); + libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); /* make sure loading with name works */ - ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "test", "GPL", insns, insn_cnt, NULL); + ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS); return probe_fd(ret); } @@ -4430,7 +4468,7 @@ static int probe_kern_global_data(void) }; int ret, map, insn_cnt = ARRAY_SIZE(insns); - map = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), 32, 1, NULL); + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL); if (map < 0) { ret = -errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4563,7 +4601,7 @@ static int probe_kern_array_mmap(void) LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE); int fd; - fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), sizeof(int), 1, &opts); + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); return probe_fd(fd); } @@ -4610,7 +4648,7 @@ static int probe_prog_bind_map(void) }; int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); - map = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), 32, 1, NULL); + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, NULL); if (map < 0) { ret = -errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4814,13 +4852,12 @@ bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) { - struct bpf_map_info map_info = {}; + struct bpf_map_info map_info; char msg[STRERR_BUFSIZE]; - __u32 map_info_len; + __u32 map_info_len = sizeof(map_info); int err; - map_info_len = sizeof(map_info); - + memset(&map_info, 0, map_info_len); err = bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len); if (err && errno == EINVAL) err = bpf_get_map_info_from_fdinfo(map_fd, &map_info); @@ -7244,8 +7281,6 @@ static int bpf_object_unload(struct bpf_object *obj) return 0; } -int bpf_object__unload(struct bpf_object *obj) __attribute__((alias("bpf_object_unload"))); - static int bpf_object__sanitize_maps(struct bpf_object *obj) { struct bpf_map *m; @@ -7944,17 +7979,9 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) continue; if (path) { - int len; - - len = snprintf(buf, PATH_MAX, "%s/%s", path, - bpf_map__name(map)); - if (len < 0) { - err = -EINVAL; - goto err_unpin_maps; - } else if (len >= PATH_MAX) { - err = -ENAMETOOLONG; + err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map)); + if (err) goto err_unpin_maps; - } sanitize_pin_path(buf); pin_path = buf; } else if (!map->pin_path) { @@ -7992,14 +8019,9 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) char buf[PATH_MAX]; if (path) { - int len; - - len = snprintf(buf, PATH_MAX, "%s/%s", path, - bpf_map__name(map)); - if (len < 0) - return libbpf_err(-EINVAL); - else if (len >= PATH_MAX) - return libbpf_err(-ENAMETOOLONG); + err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map)); + if (err) + return libbpf_err(err); sanitize_pin_path(buf); pin_path = buf; } else if (!map->pin_path) { @@ -8017,6 +8039,7 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) int bpf_object__pin_programs(struct bpf_object *obj, const char *path) { struct bpf_program *prog; + char buf[PATH_MAX]; int err; if (!obj) @@ -8028,17 +8051,9 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path) } bpf_object__for_each_program(prog, obj) { - char buf[PATH_MAX]; - int len; - - len = snprintf(buf, PATH_MAX, "%s/%s", path, prog->name); - if (len < 0) { - err = -EINVAL; - goto err_unpin_programs; - } else if (len >= PATH_MAX) { - err = -ENAMETOOLONG; + err = pathname_concat(buf, sizeof(buf), path, prog->name); + if (err) goto err_unpin_programs; - } err = bpf_program__pin(prog, buf); if (err) @@ -8049,13 +8064,7 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path) err_unpin_programs: while ((prog = bpf_object__prev_program(obj, prog))) { - char buf[PATH_MAX]; - int len; - - len = snprintf(buf, PATH_MAX, "%s/%s", path, prog->name); - if (len < 0) - continue; - else if (len >= PATH_MAX) + if (pathname_concat(buf, sizeof(buf), path, prog->name)) continue; bpf_program__unpin(prog, buf); @@ -8074,13 +8083,10 @@ int bpf_object__unpin_programs(struct bpf_object *obj, const char *path) bpf_object__for_each_program(prog, obj) { char buf[PATH_MAX]; - int len; - len = snprintf(buf, PATH_MAX, "%s/%s", path, prog->name); - if (len < 0) - return libbpf_err(-EINVAL); - else if (len >= PATH_MAX) - return libbpf_err(-ENAMETOOLONG); + err = pathname_concat(buf, sizeof(buf), path, prog->name); + if (err) + return libbpf_err(err); err = bpf_program__unpin(prog, buf); if (err) @@ -8298,6 +8304,16 @@ int bpf_program__set_autoload(struct bpf_program *prog, bool autoload) return 0; } +bool bpf_program__autoattach(const struct bpf_program *prog) +{ + return prog->autoattach; +} + +void bpf_program__set_autoattach(struct bpf_program *prog, bool autoattach) +{ + prog->autoattach = autoattach; +} + const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog) { return prog->insns; @@ -8978,11 +8994,12 @@ int libbpf_find_vmlinux_btf_id(const char *name, static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) { - struct bpf_prog_info info = {}; + struct bpf_prog_info info; __u32 info_len = sizeof(info); struct btf *btf; int err; + memset(&info, 0, info_len); err = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len); if (err) { pr_warn("failed bpf_obj_get_info_by_fd for FD %d: %d\n", @@ -9056,11 +9073,15 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac int err = 0; /* BPF program's BTF ID */ - if (attach_prog_fd) { + if (prog->type == BPF_PROG_TYPE_EXT || attach_prog_fd) { + if (!attach_prog_fd) { + pr_warn("prog '%s': attach program FD is not set\n", prog->name); + return -EINVAL; + } err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd); if (err < 0) { - pr_warn("failed to find BPF program (FD %d) BTF ID for '%s': %d\n", - attach_prog_fd, attach_name, err); + pr_warn("prog '%s': failed to find BPF program (FD %d) BTF ID for '%s': %d\n", + prog->name, attach_prog_fd, attach_name, err); return err; } *btf_obj_fd = 0; @@ -9077,7 +9098,8 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id); } if (err) { - pr_warn("failed to find kernel BTF type ID of '%s': %d\n", attach_name, err); + pr_warn("prog '%s': failed to find kernel BTF type ID of '%s': %d\n", + prog->name, attach_name, err); return err; } return 0; @@ -9810,13 +9832,16 @@ static int determine_uprobe_retprobe_bit(void) static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, uint64_t offset, int pid, size_t ref_ctr_off) { - struct perf_event_attr attr = {}; + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_event_attr attr; char errmsg[STRERR_BUFSIZE]; int type, pfd; if (ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS)) return -EINVAL; + memset(&attr, 0, attr_sz); + type = uprobe ? determine_uprobe_perf_type() : determine_kprobe_perf_type(); if (type < 0) { @@ -9837,7 +9862,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, } attr.config |= 1 << bit; } - attr.size = sizeof(attr); + attr.size = attr_sz; attr.type = type; attr.config |= (__u64)ref_ctr_off << PERF_UPROBE_REF_CTR_OFFSET_SHIFT; attr.config1 = ptr_to_u64(name); /* kprobe_func or uprobe_path */ @@ -9879,7 +9904,7 @@ static bool use_debugfs(void) static int has_debugfs = -1; if (has_debugfs < 0) - has_debugfs = access(DEBUGFS, F_OK) == 0; + has_debugfs = faccessat(AT_FDCWD, DEBUGFS, F_OK, AT_EACCESS) == 0; return has_debugfs == 1; } @@ -9936,7 +9961,8 @@ static int determine_kprobe_perf_type_legacy(const char *probe_name, bool retpro static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, const char *kfunc_name, size_t offset, int pid) { - struct perf_event_attr attr = {}; + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_event_attr attr; char errmsg[STRERR_BUFSIZE]; int type, pfd, err; @@ -9955,7 +9981,9 @@ static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); goto err_clean_legacy; } - attr.size = sizeof(attr); + + memset(&attr, 0, attr_sz); + attr.size = attr_sz; attr.config = type; attr.type = PERF_TYPE_TRACEPOINT; @@ -10412,6 +10440,7 @@ static int determine_uprobe_perf_type_legacy(const char *probe_name, bool retpro static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, const char *binary_path, size_t offset, int pid) { + const size_t attr_sz = sizeof(struct perf_event_attr); struct perf_event_attr attr; int type, pfd, err; @@ -10429,8 +10458,8 @@ static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, goto err_clean_legacy; } - memset(&attr, 0, sizeof(attr)); - attr.size = sizeof(attr); + memset(&attr, 0, attr_sz); + attr.size = attr_sz; attr.config = type; attr.type = PERF_TYPE_TRACEPOINT; @@ -10662,15 +10691,17 @@ static const char *arch_specific_lib_paths(void) static int resolve_full_path(const char *file, char *result, size_t result_sz) { const char *search_paths[3] = {}; - int i; + int i, perm; if (str_has_sfx(file, ".so") || strstr(file, ".so.")) { search_paths[0] = getenv("LD_LIBRARY_PATH"); search_paths[1] = "/usr/lib64:/usr/lib"; search_paths[2] = arch_specific_lib_paths(); + perm = R_OK; } else { search_paths[0] = getenv("PATH"); search_paths[1] = "/usr/bin:/usr/sbin"; + perm = R_OK | X_OK; } for (i = 0; i < ARRAY_SIZE(search_paths); i++) { @@ -10689,8 +10720,8 @@ static int resolve_full_path(const char *file, char *result, size_t result_sz) if (!seg_len) continue; snprintf(result, result_sz, "%.*s/%s", seg_len, s, file); - /* ensure it is an executable file/link */ - if (access(result, R_OK | X_OK) < 0) + /* ensure it has required permissions */ + if (faccessat(AT_FDCWD, result, perm, AT_EACCESS) < 0) continue; pr_debug("resolved '%s' to '%s'\n", file, result); return 0; @@ -10967,7 +10998,8 @@ static int determine_tracepoint_id(const char *tp_category, static int perf_event_open_tracepoint(const char *tp_category, const char *tp_name) { - struct perf_event_attr attr = {}; + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_event_attr attr; char errmsg[STRERR_BUFSIZE]; int tp_id, pfd, err; @@ -10979,8 +11011,9 @@ static int perf_event_open_tracepoint(const char *tp_category, return tp_id; } + memset(&attr, 0, attr_sz); attr.type = PERF_TYPE_TRACEPOINT; - attr.size = sizeof(attr); + attr.size = attr_sz; attr.config = tp_id; pfd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu */, @@ -11600,12 +11633,15 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, void *ctx, const struct perf_buffer_opts *opts) { + const size_t attr_sz = sizeof(struct perf_event_attr); struct perf_buffer_params p = {}; - struct perf_event_attr attr = {}; + struct perf_event_attr attr; if (!OPTS_VALID(opts, perf_buffer_opts)) return libbpf_err_ptr(-EINVAL); + memset(&attr, 0, attr_sz); + attr.size = attr_sz; attr.config = PERF_COUNT_SW_BPF_OUTPUT; attr.type = PERF_TYPE_SOFTWARE; attr.sample_type = PERF_SAMPLE_RAW; @@ -12328,7 +12364,7 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) struct bpf_program *prog = *s->progs[i].prog; struct bpf_link **link = s->progs[i].link; - if (!prog->autoload) + if (!prog->autoload || !prog->autoattach) continue; /* auto-attaching not supported for this program */ diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 61493c4cddac..eee883f007f9 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -118,7 +118,9 @@ struct bpf_object_open_opts { * auto-pinned to that path on load; defaults to "/sys/fs/bpf". */ const char *pin_root_path; - long :0; + + __u32 :32; /* stub out now removed attach_prog_fd */ + /* Additional kernel config content that augments and overrides * system Kconfig for CONFIG_xxx externs. */ @@ -260,6 +262,8 @@ LIBBPF_API const char *bpf_program__name(const struct bpf_program *prog); LIBBPF_API const char *bpf_program__section_name(const struct bpf_program *prog); LIBBPF_API bool bpf_program__autoload(const struct bpf_program *prog); LIBBPF_API int bpf_program__set_autoload(struct bpf_program *prog, bool autoload); +LIBBPF_API bool bpf_program__autoattach(const struct bpf_program *prog); +LIBBPF_API void bpf_program__set_autoattach(struct bpf_program *prog, bool autoattach); struct bpf_insn; @@ -1009,6 +1013,7 @@ LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook, /* Ring buffer APIs */ struct ring_buffer; +struct user_ring_buffer; typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size); @@ -1028,6 +1033,112 @@ LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms); LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb); LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb); +struct user_ring_buffer_opts { + size_t sz; /* size of this struct, for forward/backward compatibility */ +}; + +#define user_ring_buffer_opts__last_field sz + +/* @brief **user_ring_buffer__new()** creates a new instance of a user ring + * buffer. + * + * @param map_fd A file descriptor to a BPF_MAP_TYPE_USER_RINGBUF map. + * @param opts Options for how the ring buffer should be created. + * @return A user ring buffer on success; NULL and errno being set on a + * failure. + */ +LIBBPF_API struct user_ring_buffer * +user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts); + +/* @brief **user_ring_buffer__reserve()** reserves a pointer to a sample in the + * user ring buffer. + * @param rb A pointer to a user ring buffer. + * @param size The size of the sample, in bytes. + * @return A pointer to an 8-byte aligned reserved region of the user ring + * buffer; NULL, and errno being set if a sample could not be reserved. + * + * This function is *not* thread safe, and callers must synchronize accessing + * this function if there are multiple producers. If a size is requested that + * is larger than the size of the entire ring buffer, errno will be set to + * E2BIG and NULL is returned. If the ring buffer could accommodate the size, + * but currently does not have enough space, errno is set to ENOSPC and NULL is + * returned. + * + * After initializing the sample, callers must invoke + * **user_ring_buffer__submit()** to post the sample to the kernel. Otherwise, + * the sample must be freed with **user_ring_buffer__discard()**. + */ +LIBBPF_API void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size); + +/* @brief **user_ring_buffer__reserve_blocking()** reserves a record in the + * ring buffer, possibly blocking for up to @timeout_ms until a sample becomes + * available. + * @param rb The user ring buffer. + * @param size The size of the sample, in bytes. + * @param timeout_ms The amount of time, in milliseconds, for which the caller + * should block when waiting for a sample. -1 causes the caller to block + * indefinitely. + * @return A pointer to an 8-byte aligned reserved region of the user ring + * buffer; NULL, and errno being set if a sample could not be reserved. + * + * This function is *not* thread safe, and callers must synchronize + * accessing this function if there are multiple producers + * + * If **timeout_ms** is -1, the function will block indefinitely until a sample + * becomes available. Otherwise, **timeout_ms** must be non-negative, or errno + * is set to EINVAL, and NULL is returned. If **timeout_ms** is 0, no blocking + * will occur and the function will return immediately after attempting to + * reserve a sample. + * + * If **size** is larger than the size of the entire ring buffer, errno is set + * to E2BIG and NULL is returned. If the ring buffer could accommodate + * **size**, but currently does not have enough space, the caller will block + * until at most **timeout_ms** has elapsed. If insufficient space is available + * at that time, errno is set to ENOSPC, and NULL is returned. + * + * The kernel guarantees that it will wake up this thread to check if + * sufficient space is available in the ring buffer at least once per + * invocation of the **bpf_ringbuf_drain()** helper function, provided that at + * least one sample is consumed, and the BPF program did not invoke the + * function with BPF_RB_NO_WAKEUP. A wakeup may occur sooner than that, but the + * kernel does not guarantee this. If the helper function is invoked with + * BPF_RB_FORCE_WAKEUP, a wakeup event will be sent even if no sample is + * consumed. + * + * When a sample of size **size** is found within **timeout_ms**, a pointer to + * the sample is returned. After initializing the sample, callers must invoke + * **user_ring_buffer__submit()** to post the sample to the ring buffer. + * Otherwise, the sample must be freed with **user_ring_buffer__discard()**. + */ +LIBBPF_API void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, + __u32 size, + int timeout_ms); + +/* @brief **user_ring_buffer__submit()** submits a previously reserved sample + * into the ring buffer. + * @param rb The user ring buffer. + * @param sample A reserved sample. + * + * It is not necessary to synchronize amongst multiple producers when invoking + * this function. + */ +LIBBPF_API void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample); + +/* @brief **user_ring_buffer__discard()** discards a previously reserved sample. + * @param rb The user ring buffer. + * @param sample A reserved sample. + * + * It is not necessary to synchronize amongst multiple producers when invoking + * this function. + */ +LIBBPF_API void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample); + +/* @brief **user_ring_buffer__free()** frees a ring buffer that was previously + * created with **user_ring_buffer__new()**. + * @param rb The user ring buffer being freed. + */ +LIBBPF_API void user_ring_buffer__free(struct user_ring_buffer *rb); + /* Perf buffer APIs */ struct perf_buffer; diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 119e6e1ea7f1..c1d6aa7c82b6 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -358,6 +358,8 @@ LIBBPF_1.0.0 { bpf_obj_get_opts; bpf_prog_query_opts; bpf_program__attach_ksyscall; + bpf_program__autoattach; + bpf_program__set_autoattach; btf__add_enum64; btf__add_enum64_value; libbpf_bpf_attach_type_str; @@ -366,3 +368,13 @@ LIBBPF_1.0.0 { libbpf_bpf_prog_type_str; perf_buffer__buffer; }; + +LIBBPF_1.1.0 { + global: + user_ring_buffer__discard; + user_ring_buffer__free; + user_ring_buffer__new; + user_ring_buffer__reserve; + user_ring_buffer__reserve_blocking; + user_ring_buffer__submit; +} LIBBPF_1.0.0; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 4135ae0a2bc3..377642ff51fc 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -573,4 +573,7 @@ static inline bool is_pow_of_2(size_t x) return x && (x & (x - 1)) == 0; } +#define PROG_LOAD_ATTEMPTS 5 +int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts); + #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index 5b7e0155db6a..1e1be467bede 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -125,6 +125,8 @@ struct bpf_map; struct btf; struct btf_ext; +LIBBPF_API struct btf *libbpf_find_kernel_btf(void); + LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog); LIBBPF_API enum bpf_attach_type bpf_program__get_expected_attach_type(const struct bpf_program *prog); LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 0b5398786bf3..f3a8e8e74eb8 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -193,7 +193,7 @@ static int probe_map_create(enum bpf_map_type map_type) LIBBPF_OPTS(bpf_map_create_opts, opts); int key_size, value_size, max_entries; __u32 btf_key_type_id = 0, btf_value_type_id = 0; - int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err; + int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err = 0; key_size = sizeof(__u32); value_size = sizeof(__u32); @@ -231,6 +231,7 @@ static int probe_map_create(enum bpf_map_type map_type) return btf_fd; break; case BPF_MAP_TYPE_RINGBUF: + case BPF_MAP_TYPE_USER_RINGBUF: key_size = 0; value_size = 0; max_entries = 4096; diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h index 2fb2f4290080..e944f5bce728 100644 --- a/tools/lib/bpf/libbpf_version.h +++ b/tools/lib/bpf/libbpf_version.h @@ -4,6 +4,6 @@ #define __LIBBPF_VERSION_H #define LIBBPF_MAJOR_VERSION 1 -#define LIBBPF_MINOR_VERSION 0 +#define LIBBPF_MINOR_VERSION 1 #endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 6c013168032d..35104580870c 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -587,11 +587,12 @@ static int get_tc_info(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, static int tc_add_fd_and_name(struct libbpf_nla_req *req, int fd) { - struct bpf_prog_info info = {}; + struct bpf_prog_info info; __u32 info_len = sizeof(info); char name[256]; int len, ret; + memset(&info, 0, info_len); ret = bpf_obj_get_info_by_fd(fd, &info, &info_len); if (ret < 0) return ret; diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index f57e77a6e40f..3900d052ed19 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -32,7 +32,7 @@ static struct nlattr *nla_next(const struct nlattr *nla, int *remaining) static int nla_ok(const struct nlattr *nla, int remaining) { - return remaining >= sizeof(*nla) && + return remaining >= (int)sizeof(*nla) && nla->nla_len >= sizeof(*nla) && nla->nla_len <= remaining; } diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index 8bc117bcc7bc..d285171d4b69 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -16,6 +16,7 @@ #include <asm/barrier.h> #include <sys/mman.h> #include <sys/epoll.h> +#include <time.h> #include "libbpf.h" #include "libbpf_internal.h" @@ -39,6 +40,23 @@ struct ring_buffer { int ring_cnt; }; +struct user_ring_buffer { + struct epoll_event event; + unsigned long *consumer_pos; + unsigned long *producer_pos; + void *data; + unsigned long mask; + size_t page_size; + int map_fd; + int epoll_fd; +}; + +/* 8-byte ring buffer header structure */ +struct ringbuf_hdr { + __u32 len; + __u32 pad; +}; + static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r) { if (r->consumer_pos) { @@ -300,3 +318,256 @@ int ring_buffer__epoll_fd(const struct ring_buffer *rb) { return rb->epoll_fd; } + +static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb) +{ + if (rb->consumer_pos) { + munmap(rb->consumer_pos, rb->page_size); + rb->consumer_pos = NULL; + } + if (rb->producer_pos) { + munmap(rb->producer_pos, rb->page_size + 2 * (rb->mask + 1)); + rb->producer_pos = NULL; + } +} + +void user_ring_buffer__free(struct user_ring_buffer *rb) +{ + if (!rb) + return; + + user_ringbuf_unmap_ring(rb); + + if (rb->epoll_fd >= 0) + close(rb->epoll_fd); + + free(rb); +} + +static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) +{ + struct bpf_map_info info; + __u32 len = sizeof(info); + void *tmp; + struct epoll_event *rb_epoll; + int err; + + memset(&info, 0, sizeof(info)); + + err = bpf_obj_get_info_by_fd(map_fd, &info, &len); + if (err) { + err = -errno; + pr_warn("user ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err); + return err; + } + + if (info.type != BPF_MAP_TYPE_USER_RINGBUF) { + pr_warn("user ringbuf: map fd=%d is not BPF_MAP_TYPE_USER_RINGBUF\n", map_fd); + return -EINVAL; + } + + rb->map_fd = map_fd; + rb->mask = info.max_entries - 1; + + /* Map read-only consumer page */ + tmp = mmap(NULL, rb->page_size, PROT_READ, MAP_SHARED, map_fd, 0); + if (tmp == MAP_FAILED) { + err = -errno; + pr_warn("user ringbuf: failed to mmap consumer page for map fd=%d: %d\n", + map_fd, err); + return err; + } + rb->consumer_pos = tmp; + + /* Map read-write the producer page and data pages. We map the data + * region as twice the total size of the ring buffer to allow the + * simple reading and writing of samples that wrap around the end of + * the buffer. See the kernel implementation for details. + */ + tmp = mmap(NULL, rb->page_size + 2 * info.max_entries, + PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, rb->page_size); + if (tmp == MAP_FAILED) { + err = -errno; + pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %d\n", + map_fd, err); + return err; + } + + rb->producer_pos = tmp; + rb->data = tmp + rb->page_size; + + rb_epoll = &rb->event; + rb_epoll->events = EPOLLOUT; + if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, rb_epoll) < 0) { + err = -errno; + pr_warn("user ringbuf: failed to epoll add map fd=%d: %d\n", map_fd, err); + return err; + } + + return 0; +} + +struct user_ring_buffer * +user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts) +{ + struct user_ring_buffer *rb; + int err; + + if (!OPTS_VALID(opts, user_ring_buffer_opts)) + return errno = EINVAL, NULL; + + rb = calloc(1, sizeof(*rb)); + if (!rb) + return errno = ENOMEM, NULL; + + rb->page_size = getpagesize(); + + rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (rb->epoll_fd < 0) { + err = -errno; + pr_warn("user ringbuf: failed to create epoll instance: %d\n", err); + goto err_out; + } + + err = user_ringbuf_map(rb, map_fd); + if (err) + goto err_out; + + return rb; + +err_out: + user_ring_buffer__free(rb); + return errno = -err, NULL; +} + +static void user_ringbuf_commit(struct user_ring_buffer *rb, void *sample, bool discard) +{ + __u32 new_len; + struct ringbuf_hdr *hdr; + uintptr_t hdr_offset; + + hdr_offset = rb->mask + 1 + (sample - rb->data) - BPF_RINGBUF_HDR_SZ; + hdr = rb->data + (hdr_offset & rb->mask); + + new_len = hdr->len & ~BPF_RINGBUF_BUSY_BIT; + if (discard) + new_len |= BPF_RINGBUF_DISCARD_BIT; + + /* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in + * the kernel. + */ + __atomic_exchange_n(&hdr->len, new_len, __ATOMIC_ACQ_REL); +} + +void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample) +{ + user_ringbuf_commit(rb, sample, true); +} + +void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample) +{ + user_ringbuf_commit(rb, sample, false); +} + +void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size) +{ + __u32 avail_size, total_size, max_size; + /* 64-bit to avoid overflow in case of extreme application behavior */ + __u64 cons_pos, prod_pos; + struct ringbuf_hdr *hdr; + + /* Synchronizes with smp_store_release() in __bpf_user_ringbuf_peek() in + * the kernel. + */ + cons_pos = smp_load_acquire(rb->consumer_pos); + /* Synchronizes with smp_store_release() in user_ringbuf_commit() */ + prod_pos = smp_load_acquire(rb->producer_pos); + + max_size = rb->mask + 1; + avail_size = max_size - (prod_pos - cons_pos); + /* Round up total size to a multiple of 8. */ + total_size = (size + BPF_RINGBUF_HDR_SZ + 7) / 8 * 8; + + if (total_size > max_size) + return errno = E2BIG, NULL; + + if (avail_size < total_size) + return errno = ENOSPC, NULL; + + hdr = rb->data + (prod_pos & rb->mask); + hdr->len = size | BPF_RINGBUF_BUSY_BIT; + hdr->pad = 0; + + /* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in + * the kernel. + */ + smp_store_release(rb->producer_pos, prod_pos + total_size); + + return (void *)rb->data + ((prod_pos + BPF_RINGBUF_HDR_SZ) & rb->mask); +} + +static __u64 ns_elapsed_timespec(const struct timespec *start, const struct timespec *end) +{ + __u64 start_ns, end_ns, ns_per_s = 1000000000; + + start_ns = (__u64)start->tv_sec * ns_per_s + start->tv_nsec; + end_ns = (__u64)end->tv_sec * ns_per_s + end->tv_nsec; + + return end_ns - start_ns; +} + +void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, __u32 size, int timeout_ms) +{ + void *sample; + int err, ms_remaining = timeout_ms; + struct timespec start; + + if (timeout_ms < 0 && timeout_ms != -1) + return errno = EINVAL, NULL; + + if (timeout_ms != -1) { + err = clock_gettime(CLOCK_MONOTONIC, &start); + if (err) + return NULL; + } + + do { + int cnt, ms_elapsed; + struct timespec curr; + __u64 ns_per_ms = 1000000; + + sample = user_ring_buffer__reserve(rb, size); + if (sample) + return sample; + else if (errno != ENOSPC) + return NULL; + + /* The kernel guarantees at least one event notification + * delivery whenever at least one sample is drained from the + * ring buffer in an invocation to bpf_ringbuf_drain(). Other + * additional events may be delivered at any time, but only one + * event is guaranteed per bpf_ringbuf_drain() invocation, + * provided that a sample is drained, and the BPF program did + * not pass BPF_RB_NO_WAKEUP to bpf_ringbuf_drain(). If + * BPF_RB_FORCE_WAKEUP is passed to bpf_ringbuf_drain(), a + * wakeup event will be delivered even if no samples are + * drained. + */ + cnt = epoll_wait(rb->epoll_fd, &rb->event, 1, ms_remaining); + if (cnt < 0) + return NULL; + + if (timeout_ms == -1) + continue; + + err = clock_gettime(CLOCK_MONOTONIC, &curr); + if (err) + return NULL; + + ms_elapsed = ns_elapsed_timespec(&start, &curr) / ns_per_ms; + ms_remaining = timeout_ms - ms_elapsed; + } while (ms_remaining > 0); + + /* Try one more time to reserve a sample after the specified timeout has elapsed. */ + return user_ring_buffer__reserve(rb, size); +} diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index 70adf7b119b9..1e82ab06c3eb 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -251,6 +251,29 @@ static inline int skel_map_update_elem(int fd, const void *key, return skel_sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz); } +static inline int skel_map_delete_elem(int fd, const void *key) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = (long)key; + + return skel_sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz); +} + +static inline int skel_map_get_fd_by_id(__u32 id) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.map_id = id; + + return skel_sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, attr_sz); +} + static inline int skel_raw_tracepoint_open(const char *name, int prog_fd) { const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint.prog_fd); @@ -285,6 +308,8 @@ static inline int skel_link_create(int prog_fd, int target_fd, static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) { + const size_t prog_load_attr_sz = offsetofend(union bpf_attr, fd_array); + const size_t test_run_attr_sz = offsetofend(union bpf_attr, test); int map_fd = -1, prog_fd = -1, key = 0, err; union bpf_attr attr; @@ -302,7 +327,7 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) goto out; } - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, prog_load_attr_sz); attr.prog_type = BPF_PROG_TYPE_SYSCALL; attr.insns = (long) opts->insns; attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn); @@ -313,18 +338,18 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) attr.log_size = opts->ctx->log_size; attr.log_buf = opts->ctx->log_buf; attr.prog_flags = BPF_F_SLEEPABLE; - err = prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); + err = prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, prog_load_attr_sz); if (prog_fd < 0) { opts->errstr = "failed to load loader prog"; set_err; goto out; } - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, test_run_attr_sz); attr.test.prog_fd = prog_fd; attr.test.ctx_in = (long) opts->ctx; attr.test.ctx_size_in = opts->ctx->sz; - err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr)); + err = skel_sys_bpf(BPF_PROG_RUN, &attr, test_run_attr_sz); if (err < 0 || (int)attr.test.retval < 0) { opts->errstr = "failed to execute loader prog"; if (err < 0) { diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h index 4f2adc0bd6ca..fdfd235e52c4 100644 --- a/tools/lib/bpf/usdt.bpf.h +++ b/tools/lib/bpf/usdt.bpf.h @@ -232,7 +232,7 @@ long bpf_usdt_cookie(struct pt_regs *ctx) */ #define BPF_USDT(name, args...) \ name(struct pt_regs *ctx); \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(struct pt_regs *ctx, ##args); \ typeof(name(0)) name(struct pt_regs *ctx) \ { \ @@ -241,7 +241,7 @@ typeof(name(0)) name(struct pt_regs *ctx) \ return ____##name(___bpf_usdt_args(args)); \ _Pragma("GCC diagnostic pop") \ } \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(struct pt_regs *ctx, ##args) #endif /* __USDT_BPF_H__ */ diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index d18e37982344..e83b497c2245 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -282,7 +282,7 @@ struct usdt_manager *usdt_manager_new(struct bpf_object *obj) * If this is not supported, USDTs with semaphores will not be supported. * Added in: a6ca88b241d5 ("trace_uprobe: support reference counter in fd-based uprobe") */ - man->has_sema_refcnt = access(ref_ctr_sysfs_path, F_OK) == 0; + man->has_sema_refcnt = faccessat(AT_FDCWD, ref_ctr_sysfs_path, F_OK, AT_EACCESS) == 0; return man; } diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c index ba4b8d94e004..6a3dc167d30e 100644 --- a/tools/lib/find_bit.c +++ b/tools/lib/find_bit.c @@ -18,66 +18,54 @@ #include <linux/bitmap.h> #include <linux/kernel.h> -#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ - !defined(find_next_and_bit) - /* - * This is a common helper function for find_next_bit, find_next_zero_bit, and - * find_next_and_bit. The differences are: - * - The "invert" argument, which is XORed with each fetched word before - * searching it for one bits. - * - The optional "addr2", which is anded with "addr1" if present. + * Common helper for find_bit() function family + * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) + * @MUNGE: The expression that post-processes a word containing found bit (may be empty) + * @size: The bitmap size in bits */ -unsigned long _find_next_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert, unsigned long le) -{ - unsigned long tmp, mask; - (void) le; - - if (unlikely(start >= nbits)) - return nbits; - - tmp = addr1[start / BITS_PER_LONG]; - if (addr2) - tmp &= addr2[start / BITS_PER_LONG]; - tmp ^= invert; - - /* Handle 1st word. */ - mask = BITMAP_FIRST_WORD_MASK(start); - - /* - * Due to the lack of swab() in tools, and the fact that it doesn't - * need little-endian support, just comment it out - */ -#if (0) - if (le) - mask = swab(mask); -#endif - - tmp &= mask; +#define FIND_FIRST_BIT(FETCH, MUNGE, size) \ +({ \ + unsigned long idx, val, sz = (size); \ + \ + for (idx = 0; idx * BITS_PER_LONG < sz; idx++) { \ + val = (FETCH); \ + if (val) { \ + sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(val)), sz); \ + break; \ + } \ + } \ + \ + sz; \ +}) - start = round_down(start, BITS_PER_LONG); - - while (!tmp) { - start += BITS_PER_LONG; - if (start >= nbits) - return nbits; - - tmp = addr1[start / BITS_PER_LONG]; - if (addr2) - tmp &= addr2[start / BITS_PER_LONG]; - tmp ^= invert; - } - -#if (0) - if (le) - tmp = swab(tmp); -#endif - - return min(start + __ffs(tmp), nbits); -} -#endif +/* + * Common helper for find_next_bit() function family + * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) + * @MUNGE: The expression that post-processes a word containing found bit (may be empty) + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at + */ +#define FIND_NEXT_BIT(FETCH, MUNGE, size, start) \ +({ \ + unsigned long mask, idx, tmp, sz = (size), __start = (start); \ + \ + if (unlikely(__start >= sz)) \ + goto out; \ + \ + mask = MUNGE(BITMAP_FIRST_WORD_MASK(__start)); \ + idx = __start / BITS_PER_LONG; \ + \ + for (tmp = (FETCH) & mask; !tmp; tmp = (FETCH)) { \ + if ((idx + 1) * BITS_PER_LONG >= sz) \ + goto out; \ + idx++; \ + } \ + \ + sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(tmp)), sz); \ +out: \ + sz; \ +}) #ifndef find_first_bit /* @@ -85,14 +73,7 @@ unsigned long _find_next_bit(const unsigned long *addr1, */ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) { - unsigned long idx; - - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - if (addr[idx]) - return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size); - } - - return size; + return FIND_FIRST_BIT(addr[idx], /* nop */, size); } #endif @@ -104,15 +85,7 @@ unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) { - unsigned long idx, val; - - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - val = addr1[idx] & addr2[idx]; - if (val) - return min(idx * BITS_PER_LONG + __ffs(val), size); - } - - return size; + return FIND_FIRST_BIT(addr1[idx] & addr2[idx], /* nop */, size); } #endif @@ -122,13 +95,29 @@ unsigned long _find_first_and_bit(const unsigned long *addr1, */ unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size) { - unsigned long idx; + return FIND_FIRST_BIT(~addr[idx], /* nop */, size); +} +#endif - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - if (addr[idx] != ~0UL) - return min(idx * BITS_PER_LONG + ffz(addr[idx]), size); - } +#ifndef find_next_bit +unsigned long _find_next_bit(const unsigned long *addr, unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr[idx], /* nop */, nbits, start); +} +#endif - return size; +#ifndef find_next_and_bit +unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr1[idx] & addr2[idx], /* nop */, nbits, start); +} +#endif + +#ifndef find_next_zero_bit +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start) +{ + return FIND_NEXT_BIT(~addr[idx], /* nop */, nbits, start); } #endif diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 6b1bafe267a4..61b637f29b82 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -40,11 +40,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, * We already have cpus for evsel (via PMU sysfs) so * keep it, if there's no target cpu list defined. */ - if (!evsel->own_cpus || - (!evsel->system_wide && evlist->has_user_cpus) || - (!evsel->system_wide && - !evsel->requires_cpu && - perf_cpu_map__empty(evlist->user_requested_cpus))) { + if (evsel->system_wide) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__new(NULL); + } else if (!evsel->own_cpus || evlist->has_user_cpus || + (!evsel->requires_cpu && perf_cpu_map__empty(evlist->user_requested_cpus))) { perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); } else if (evsel->cpus != evsel->own_cpus) { @@ -52,7 +52,10 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, evsel->cpus = perf_cpu_map__get(evsel->own_cpus); } - if (!evsel->system_wide) { + if (evsel->system_wide) { + perf_thread_map__put(evsel->threads); + evsel->threads = perf_thread_map__new_dummy(); + } else { perf_thread_map__put(evsel->threads); evsel->threads = perf_thread_map__get(evlist->threads); } @@ -64,9 +67,7 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist) { struct perf_evsel *evsel; - /* Recomputing all_cpus, so start with a blank slate. */ - perf_cpu_map__put(evlist->all_cpus); - evlist->all_cpus = NULL; + evlist->needs_map_propagation = true; perf_evlist__for_each_evsel(evlist, evsel) __perf_evlist__propagate_maps(evlist, evsel); @@ -78,7 +79,9 @@ void perf_evlist__add(struct perf_evlist *evlist, evsel->idx = evlist->nr_entries; list_add_tail(&evsel->node, &evlist->entries); evlist->nr_entries += 1; - __perf_evlist__propagate_maps(evlist, evsel); + + if (evlist->needs_map_propagation) + __perf_evlist__propagate_maps(evlist, evsel); } void perf_evlist__remove(struct perf_evlist *evlist, @@ -174,9 +177,6 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, evlist->threads = perf_thread_map__get(threads); } - if (!evlist->all_cpus && cpus) - evlist->all_cpus = perf_cpu_map__get(cpus); - perf_evlist__propagate_maps(evlist); } @@ -441,6 +441,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, perf_evlist__for_each_entry(evlist, evsel) { bool overwrite = evsel->attr.write_backward; + enum fdarray_flags flgs; struct perf_mmap *map; int *output, fd, cpu; @@ -486,6 +487,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, if (ops->idx) ops->idx(evlist, evsel, mp, idx); + /* Debug message used by test scripts */ pr_debug("idx %d: mmapping fd %d\n", idx, *output); if (ops->mmap(map, mp, *output, evlist_cpu) < 0) return -1; @@ -495,6 +497,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, if (!idx) perf_evlist__set_mmap_first(evlist, map, overwrite); } else { + /* Debug message used by test scripts */ pr_debug("idx %d: set output fd %d -> %d\n", idx, fd, *output); if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) return -1; @@ -504,8 +507,8 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, revent = !overwrite ? POLLIN : 0; - if (!evsel->system_wide && - perf_evlist__add_pollfd(evlist, fd, map, revent, fdarray_flag__default) < 0) { + flgs = evsel->system_wide ? fdarray_flag__nonfilterable : fdarray_flag__default; + if (perf_evlist__add_pollfd(evlist, fd, map, revent, flgs) < 0) { perf_mmap__put(map); return -1; } diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index 8ce5bbd09666..8b51b008a81f 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -515,9 +515,6 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) if (ncpus == 0 || nthreads == 0) return 0; - if (evsel->system_wide) - nthreads = 1; - evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id)); if (evsel->sample_id == NULL) return -ENOMEM; diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h index 6f89aec3e608..850f07070036 100644 --- a/tools/lib/perf/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h @@ -19,6 +19,7 @@ struct perf_evlist { int nr_entries; int nr_groups; bool has_user_cpus; + bool needs_map_propagation; /** * The cpus passed from the command line or all online CPUs by * default. diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index 93bf93a59c99..ad47d7b31046 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -6,7 +6,6 @@ #include <linux/types.h> #include <linux/limits.h> #include <linux/bpf.h> -#include <linux/compiler.h> #include <sys/types.h> /* pid_t */ #define event_contains(obj, mem) ((obj).header.size > offsetof(typeof(obj), mem)) @@ -97,7 +96,7 @@ struct perf_record_throttle { }; #ifndef KSYM_NAME_LEN -#define KSYM_NAME_LEN 256 +#define KSYM_NAME_LEN 512 #endif struct perf_record_ksymbol { @@ -153,6 +152,7 @@ struct perf_record_header_attr { enum { PERF_CPU_MAP__CPUS = 0, PERF_CPU_MAP__MASK = 1, + PERF_CPU_MAP__RANGE_CPUS = 2, }; /* @@ -195,7 +195,18 @@ struct perf_record_mask_cpu_map64 { #pragma GCC diagnostic ignored "-Wpacked" #pragma GCC diagnostic ignored "-Wattributes" -struct __packed perf_record_cpu_map_data { +/* + * An encoding of a CPU map for a range starting at start_cpu through to + * end_cpu. If any_cpu is 1, an any CPU (-1) value (aka dummy value) is present. + */ +struct perf_record_range_cpu_map { + __u8 any_cpu; + __u8 __pad; + __u16 start_cpu; + __u16 end_cpu; +}; + +struct perf_record_cpu_map_data { __u16 type; union { /* Used when type == PERF_CPU_MAP__CPUS. */ @@ -204,8 +215,10 @@ struct __packed perf_record_cpu_map_data { struct perf_record_mask_cpu_map32 mask32_data; /* Used when type == PERF_CPU_MAP__MASK and long_size == 8. */ struct perf_record_mask_cpu_map64 mask64_data; + /* Used when type == PERF_CPU_MAP__RANGE_CPUS. */ + struct perf_record_range_cpu_map range_cpu_data; }; -}; +} __attribute__((packed)); #pragma GCC diagnostic pop @@ -233,7 +246,16 @@ struct perf_record_event_update { struct perf_event_header header; __u64 type; __u64 id; - char data[]; + union { + /* Used when type == PERF_EVENT_UPDATE__SCALE. */ + struct perf_record_event_update_scale scale; + /* Used when type == PERF_EVENT_UPDATE__UNIT. */ + char unit[0]; + /* Used when type == PERF_EVENT_UPDATE__NAME. */ + char name[0]; + /* Used when type == PERF_EVENT_UPDATE__CPUS. */ + struct perf_record_event_update_cpus cpus; + }; }; #define MAX_EVENT_NAME 64 diff --git a/tools/lib/subcmd/exec-cmd.c b/tools/lib/subcmd/exec-cmd.c index 33e94fb83986..5dbea456973e 100644 --- a/tools/lib/subcmd/exec-cmd.c +++ b/tools/lib/subcmd/exec-cmd.c @@ -24,6 +24,9 @@ void exec_cmd_init(const char *exec_name, const char *prefix, subcmd_config.prefix = prefix; subcmd_config.exec_path = exec_path; subcmd_config.exec_path_env = exec_path_env; + + /* Setup environment variable for invoked shell script. */ + setenv("PREFIX", prefix, 1); } #define is_dir_sep(c) ((c) == '/') diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h index 72ab9870454b..542f9b059c3b 100644 --- a/tools/lib/symbol/kallsyms.h +++ b/tools/lib/symbol/kallsyms.h @@ -7,7 +7,7 @@ #include <linux/types.h> #ifndef KSYM_NAME_LEN -#define KSYM_NAME_LEN 256 +#define KSYM_NAME_LEN 512 #endif static inline u8 kallsyms2elf_binding(char type) |