diff options
Diffstat (limited to 'src/contrib/libbpf')
42 files changed, 24957 insertions, 0 deletions
diff --git a/src/contrib/libbpf/LICENSE b/src/contrib/libbpf/LICENSE new file mode 100644 index 0000000..149c7b0 --- /dev/null +++ b/src/contrib/libbpf/LICENSE @@ -0,0 +1 @@ +../licenses/LGPL-2.1
\ No newline at end of file diff --git a/src/contrib/libbpf/bpf/bpf.c b/src/contrib/libbpf/bpf/bpf.c new file mode 100644 index 0000000..98596e1 --- /dev/null +++ b/src/contrib/libbpf/bpf/bpf.c @@ -0,0 +1,710 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * common eBPF ELF operations. + * + * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> + * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015 Huawei Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; + * version 2.1 of the License (not later!) + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this program; if not, see <http://www.gnu.org/licenses> + */ + +#include <stdlib.h> +#include <string.h> +#include <memory.h> +#include <unistd.h> +#include <asm/unistd.h> +#include <errno.h> +#include <linux/bpf.h> +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" + +/* + * When building perf, unistd.h is overridden. __NR_bpf is + * required to be defined explicitly. + */ +#ifndef __NR_bpf +# if defined(__i386__) +# define __NR_bpf 357 +# elif defined(__x86_64__) +# define __NR_bpf 321 +# elif defined(__aarch64__) +# define __NR_bpf 280 +# elif defined(__sparc__) +# define __NR_bpf 349 +# elif defined(__s390__) +# define __NR_bpf 351 +# elif defined(__arc__) +# define __NR_bpf 280 +# else +# error __NR_bpf not defined. libbpf does not support your arch. +# endif +#endif + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64) (unsigned long) ptr; +} + +static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, + unsigned int size) +{ + return syscall(__NR_bpf, cmd, attr, size); +} + +static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size) +{ + int fd; + + do { + fd = sys_bpf(BPF_PROG_LOAD, attr, size); + } while (fd < 0 && errno == EAGAIN); + + return fd; +} + +int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) +{ + union bpf_attr attr; + + memset(&attr, '\0', sizeof(attr)); + + attr.map_type = create_attr->map_type; + attr.key_size = create_attr->key_size; + attr.value_size = create_attr->value_size; + attr.max_entries = create_attr->max_entries; + attr.map_flags = create_attr->map_flags; + if (create_attr->name) + memcpy(attr.map_name, create_attr->name, + min(strlen(create_attr->name), BPF_OBJ_NAME_LEN - 1)); + attr.numa_node = create_attr->numa_node; + attr.btf_fd = create_attr->btf_fd; + attr.btf_key_type_id = create_attr->btf_key_type_id; + attr.btf_value_type_id = create_attr->btf_value_type_id; + attr.map_ifindex = create_attr->map_ifindex; + attr.inner_map_fd = create_attr->inner_map_fd; + + return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); +} + +int bpf_create_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags, int node) +{ + struct bpf_create_map_attr map_attr = {}; + + map_attr.name = name; + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; + if (node >= 0) { + map_attr.numa_node = node; + map_attr.map_flags |= BPF_F_NUMA_NODE; + } + + return bpf_create_map_xattr(&map_attr); +} + +int bpf_create_map(enum bpf_map_type map_type, int key_size, + int value_size, int max_entries, __u32 map_flags) +{ + struct bpf_create_map_attr map_attr = {}; + + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; + + return bpf_create_map_xattr(&map_attr); +} + +int bpf_create_map_name(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags) +{ + struct bpf_create_map_attr map_attr = {}; + + map_attr.name = name; + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; + + return bpf_create_map_xattr(&map_attr); +} + +int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, + __u32 map_flags, int node) +{ + union bpf_attr attr; + + memset(&attr, '\0', sizeof(attr)); + + attr.map_type = map_type; + attr.key_size = key_size; + attr.value_size = 4; + attr.inner_map_fd = inner_map_fd; + attr.max_entries = max_entries; + attr.map_flags = map_flags; + if (name) + memcpy(attr.map_name, name, + min(strlen(name), BPF_OBJ_NAME_LEN - 1)); + + if (node >= 0) { + attr.map_flags |= BPF_F_NUMA_NODE; + attr.numa_node = node; + } + + return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); +} + +int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, + int key_size, int inner_map_fd, int max_entries, + __u32 map_flags) +{ + return bpf_create_map_in_map_node(map_type, name, key_size, + inner_map_fd, max_entries, map_flags, + -1); +} + +static void * +alloc_zero_tailing_info(const void *orecord, __u32 cnt, + __u32 actual_rec_size, __u32 expected_rec_size) +{ + __u64 info_len = (__u64)actual_rec_size * cnt; + void *info, *nrecord; + int i; + + info = malloc(info_len); + if (!info) + return NULL; + + /* zero out bytes kernel does not understand */ + nrecord = info; + for (i = 0; i < cnt; i++) { + memcpy(nrecord, orecord, expected_rec_size); + memset(nrecord + expected_rec_size, 0, + actual_rec_size - expected_rec_size); + orecord += actual_rec_size; + nrecord += actual_rec_size; + } + + return info; +} + +int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, + char *log_buf, size_t log_buf_sz) +{ + void *finfo = NULL, *linfo = NULL; + union bpf_attr attr; + __u32 log_level; + int fd; + + if (!load_attr || !log_buf != !log_buf_sz) + return -EINVAL; + + log_level = load_attr->log_level; + if (log_level > (4 | 2 | 1) || (log_level && !log_buf)) + return -EINVAL; + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = load_attr->prog_type; + attr.expected_attach_type = load_attr->expected_attach_type; + if (attr.prog_type == BPF_PROG_TYPE_TRACING) { + attr.attach_btf_id = load_attr->attach_btf_id; + attr.attach_prog_fd = load_attr->attach_prog_fd; + } else { + attr.prog_ifindex = load_attr->prog_ifindex; + attr.kern_version = load_attr->kern_version; + } + attr.insn_cnt = (__u32)load_attr->insns_cnt; + attr.insns = ptr_to_u64(load_attr->insns); + attr.license = ptr_to_u64(load_attr->license); + + attr.log_level = log_level; + if (log_level) { + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_buf_sz; + } else { + attr.log_buf = ptr_to_u64(NULL); + attr.log_size = 0; + } + + attr.prog_btf_fd = load_attr->prog_btf_fd; + attr.func_info_rec_size = load_attr->func_info_rec_size; + attr.func_info_cnt = load_attr->func_info_cnt; + attr.func_info = ptr_to_u64(load_attr->func_info); + attr.line_info_rec_size = load_attr->line_info_rec_size; + attr.line_info_cnt = load_attr->line_info_cnt; + attr.line_info = ptr_to_u64(load_attr->line_info); + if (load_attr->name) + memcpy(attr.prog_name, load_attr->name, + min(strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1)); + attr.prog_flags = load_attr->prog_flags; + + fd = sys_bpf_prog_load(&attr, sizeof(attr)); + if (fd >= 0) + return fd; + + /* After bpf_prog_load, the kernel may modify certain attributes + * to give user space a hint how to deal with loading failure. + * Check to see whether we can make some changes and load again. + */ + while (errno == E2BIG && (!finfo || !linfo)) { + if (!finfo && attr.func_info_cnt && + attr.func_info_rec_size < load_attr->func_info_rec_size) { + /* try with corrected func info records */ + finfo = alloc_zero_tailing_info(load_attr->func_info, + load_attr->func_info_cnt, + load_attr->func_info_rec_size, + attr.func_info_rec_size); + if (!finfo) + goto done; + + attr.func_info = ptr_to_u64(finfo); + attr.func_info_rec_size = load_attr->func_info_rec_size; + } else if (!linfo && attr.line_info_cnt && + attr.line_info_rec_size < + load_attr->line_info_rec_size) { + linfo = alloc_zero_tailing_info(load_attr->line_info, + load_attr->line_info_cnt, + load_attr->line_info_rec_size, + attr.line_info_rec_size); + if (!linfo) + goto done; + + attr.line_info = ptr_to_u64(linfo); + attr.line_info_rec_size = load_attr->line_info_rec_size; + } else { + break; + } + + fd = sys_bpf_prog_load(&attr, sizeof(attr)); + + if (fd >= 0) + goto done; + } + + if (log_level || !log_buf) + goto done; + + /* Try again with log */ + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_buf_sz; + attr.log_level = 1; + log_buf[0] = 0; + fd = sys_bpf_prog_load(&attr, sizeof(attr)); +done: + free(finfo); + free(linfo); + return fd; +} + +int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, const char *license, + __u32 kern_version, char *log_buf, + size_t log_buf_sz) +{ + struct bpf_load_program_attr load_attr; + + memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); + load_attr.prog_type = type; + load_attr.expected_attach_type = 0; + load_attr.name = NULL; + load_attr.insns = insns; + load_attr.insns_cnt = insns_cnt; + load_attr.license = license; + load_attr.kern_version = kern_version; + + return bpf_load_program_xattr(&load_attr, log_buf, log_buf_sz); +} + +int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, __u32 prog_flags, const char *license, + __u32 kern_version, char *log_buf, size_t log_buf_sz, + int log_level) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = type; + attr.insn_cnt = (__u32)insns_cnt; + attr.insns = ptr_to_u64(insns); + attr.license = ptr_to_u64(license); + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_buf_sz; + attr.log_level = log_level; + log_buf[0] = 0; + attr.kern_version = kern_version; + attr.prog_flags = prog_flags; + + return sys_bpf_prog_load(&attr, sizeof(attr)); +} + +int bpf_map_update_elem(int fd, const void *key, const void *value, + __u64 flags) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + attr.flags = flags; + + return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr)); +} + +int bpf_map_lookup_elem(int fd, const void *key, void *value) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + + return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); +} + +int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + attr.flags = flags; + + return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); +} + +int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + + return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr)); +} + +int bpf_map_delete_elem(int fd, const void *key) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + + return sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr)); +} + +int bpf_map_get_next_key(int fd, const void *key, void *next_key) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.next_key = ptr_to_u64(next_key); + + return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr)); +} + +int bpf_map_freeze(int fd) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + + return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); +} + +int bpf_obj_pin(int fd, const char *pathname) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.pathname = ptr_to_u64((void *)pathname); + attr.bpf_fd = fd; + + return sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr)); +} + +int bpf_obj_get(const char *pathname) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.pathname = ptr_to_u64((void *)pathname); + + return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr)); +} + +int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, + unsigned int flags) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.target_fd = target_fd; + attr.attach_bpf_fd = prog_fd; + attr.attach_type = type; + attr.attach_flags = flags; + + return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr)); +} + +int bpf_prog_detach(int target_fd, enum bpf_attach_type type) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.target_fd = target_fd; + attr.attach_type = type; + + return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); +} + +int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.target_fd = target_fd; + attr.attach_bpf_fd = prog_fd; + attr.attach_type = type; + + return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); +} + +int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, + __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt) +{ + union bpf_attr attr; + int ret; + + memset(&attr, 0, sizeof(attr)); + attr.query.target_fd = target_fd; + attr.query.attach_type = type; + attr.query.query_flags = query_flags; + attr.query.prog_cnt = *prog_cnt; + attr.query.prog_ids = ptr_to_u64(prog_ids); + + ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr)); + if (attach_flags) + *attach_flags = attr.query.attach_flags; + *prog_cnt = attr.query.prog_cnt; + return ret; +} + +int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, + void *data_out, __u32 *size_out, __u32 *retval, + __u32 *duration) +{ + union bpf_attr attr; + int ret; + + memset(&attr, 0, sizeof(attr)); + attr.test.prog_fd = prog_fd; + attr.test.data_in = ptr_to_u64(data); + attr.test.data_out = ptr_to_u64(data_out); + attr.test.data_size_in = size; + attr.test.repeat = repeat; + + ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); + if (size_out) + *size_out = attr.test.data_size_out; + if (retval) + *retval = attr.test.retval; + if (duration) + *duration = attr.test.duration; + return ret; +} + +int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr) +{ + union bpf_attr attr; + int ret; + + if (!test_attr->data_out && test_attr->data_size_out > 0) + return -EINVAL; + + memset(&attr, 0, sizeof(attr)); + attr.test.prog_fd = test_attr->prog_fd; + attr.test.data_in = ptr_to_u64(test_attr->data_in); + attr.test.data_out = ptr_to_u64(test_attr->data_out); + attr.test.data_size_in = test_attr->data_size_in; + attr.test.data_size_out = test_attr->data_size_out; + attr.test.ctx_in = ptr_to_u64(test_attr->ctx_in); + attr.test.ctx_out = ptr_to_u64(test_attr->ctx_out); + attr.test.ctx_size_in = test_attr->ctx_size_in; + attr.test.ctx_size_out = test_attr->ctx_size_out; + attr.test.repeat = test_attr->repeat; + + ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); + test_attr->data_size_out = attr.test.data_size_out; + test_attr->ctx_size_out = attr.test.ctx_size_out; + test_attr->retval = attr.test.retval; + test_attr->duration = attr.test.duration; + return ret; +} + +static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd) +{ + union bpf_attr attr; + int err; + + memset(&attr, 0, sizeof(attr)); + attr.start_id = start_id; + + err = sys_bpf(cmd, &attr, sizeof(attr)); + if (!err) + *next_id = attr.next_id; + + return err; +} + +int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id) +{ + return bpf_obj_get_next_id(start_id, next_id, BPF_PROG_GET_NEXT_ID); +} + +int bpf_map_get_next_id(__u32 start_id, __u32 *next_id) +{ + return bpf_obj_get_next_id(start_id, next_id, BPF_MAP_GET_NEXT_ID); +} + +int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id) +{ + return bpf_obj_get_next_id(start_id, next_id, BPF_BTF_GET_NEXT_ID); +} + +int bpf_prog_get_fd_by_id(__u32 id) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.prog_id = id; + + return sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr)); +} + +int bpf_map_get_fd_by_id(__u32 id) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.map_id = id; + + return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr)); +} + +int bpf_btf_get_fd_by_id(__u32 id) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.btf_id = id; + + return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr)); +} + +int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len) +{ + union bpf_attr attr; + int err; + + memset(&attr, 0, sizeof(attr)); + attr.info.bpf_fd = prog_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)); + if (!err) + *info_len = attr.info.info_len; + + return err; +} + +int bpf_raw_tracepoint_open(const char *name, int prog_fd) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.raw_tracepoint.name = ptr_to_u64(name); + attr.raw_tracepoint.prog_fd = prog_fd; + + return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr)); +} + +int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, + bool do_log) +{ + union bpf_attr attr = {}; + int fd; + + attr.btf = ptr_to_u64(btf); + attr.btf_size = btf_size; + +retry: + if (do_log && log_buf && log_buf_size) { + attr.btf_log_level = 1; + attr.btf_log_size = log_buf_size; + attr.btf_log_buf = ptr_to_u64(log_buf); + } + + fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr)); + if (fd == -1 && !do_log && log_buf && log_buf_size) { + do_log = true; + goto retry; + } + + return fd; +} + +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 = {}; + int err; + + 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)); + *buf_len = attr.task_fd_query.buf_len; + *prog_id = attr.task_fd_query.prog_id; + *fd_type = attr.task_fd_query.fd_type; + *probe_offset = attr.task_fd_query.probe_offset; + *probe_addr = attr.task_fd_query.probe_addr; + + return err; +} diff --git a/src/contrib/libbpf/bpf/bpf.h b/src/contrib/libbpf/bpf/bpf.h new file mode 100644 index 0000000..3c791fa --- /dev/null +++ b/src/contrib/libbpf/bpf/bpf.h @@ -0,0 +1,184 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * common eBPF ELF operations. + * + * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> + * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015 Huawei Inc. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; + * version 2.1 of the License (not later!) + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this program; if not, see <http://www.gnu.org/licenses> + */ +#ifndef __LIBBPF_BPF_H +#define __LIBBPF_BPF_H + +#include <linux/bpf.h> +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> + +#ifdef __cplusplus +extern "C" { +#endif + +#ifndef LIBBPF_API +#define LIBBPF_API __attribute__((visibility("default"))) +#endif + +struct bpf_create_map_attr { + const char *name; + enum bpf_map_type map_type; + __u32 map_flags; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 numa_node; + __u32 btf_fd; + __u32 btf_key_type_id; + __u32 btf_value_type_id; + __u32 map_ifindex; + __u32 inner_map_fd; +}; + +LIBBPF_API int +bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); +LIBBPF_API int bpf_create_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, + int max_entries, __u32 map_flags, int node); +LIBBPF_API int bpf_create_map_name(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, + int max_entries, __u32 map_flags); +LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size, + int value_size, int max_entries, __u32 map_flags); +LIBBPF_API int bpf_create_map_in_map_node(enum bpf_map_type map_type, + const char *name, int key_size, + int inner_map_fd, int max_entries, + __u32 map_flags, int node); +LIBBPF_API int bpf_create_map_in_map(enum bpf_map_type map_type, + const char *name, int key_size, + int inner_map_fd, int max_entries, + __u32 map_flags); + +struct bpf_load_program_attr { + enum bpf_prog_type prog_type; + enum bpf_attach_type expected_attach_type; + const char *name; + const struct bpf_insn *insns; + size_t insns_cnt; + const char *license; + union { + __u32 kern_version; + __u32 attach_prog_fd; + }; + union { + __u32 prog_ifindex; + __u32 attach_btf_id; + }; + __u32 prog_btf_fd; + __u32 func_info_rec_size; + const void *func_info; + __u32 func_info_cnt; + __u32 line_info_rec_size; + const void *line_info; + __u32 line_info_cnt; + __u32 log_level; + __u32 prog_flags; +}; + +/* Flags to direct loading requirements */ +#define MAPS_RELAX_COMPAT 0x01 + +/* Recommend log buffer size */ +#define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */ +LIBBPF_API int +bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, + char *log_buf, size_t log_buf_sz); +LIBBPF_API int bpf_load_program(enum bpf_prog_type type, + const struct bpf_insn *insns, size_t insns_cnt, + const char *license, __u32 kern_version, + char *log_buf, size_t log_buf_sz); +LIBBPF_API int bpf_verify_program(enum bpf_prog_type type, + const struct bpf_insn *insns, + size_t insns_cnt, __u32 prog_flags, + const char *license, __u32 kern_version, + char *log_buf, size_t log_buf_sz, + int log_level); + +LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value, + __u64 flags); + +LIBBPF_API int bpf_map_lookup_elem(int fd, const void *key, void *value); +LIBBPF_API int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, + __u64 flags); +LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, + void *value); +LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); +LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); +LIBBPF_API int bpf_map_freeze(int fd); +LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); +LIBBPF_API int bpf_obj_get(const char *pathname); +LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, + enum bpf_attach_type type, unsigned int flags); +LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); +LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd, + enum bpf_attach_type type); + +struct bpf_prog_test_run_attr { + int prog_fd; + int repeat; + const void *data_in; + __u32 data_size_in; + void *data_out; /* optional */ + __u32 data_size_out; /* in: max length of data_out + * out: length of data_out */ + __u32 retval; /* out: return code of the BPF program */ + __u32 duration; /* out: average per repetition in ns */ + const void *ctx_in; /* optional */ + __u32 ctx_size_in; + void *ctx_out; /* optional */ + __u32 ctx_size_out; /* in: max length of ctx_out + * out: length of cxt_out */ +}; + +LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr); + +/* + * bpf_prog_test_run does not check that data_out is large enough. Consider + * using bpf_prog_test_run_xattr instead. + */ +LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data, + __u32 size, void *data_out, __u32 *size_out, + __u32 *retval, __u32 *duration); +LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id); +LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); +LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id); +LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id); +LIBBPF_API int bpf_map_get_fd_by_id(__u32 id); +LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id); +LIBBPF_API int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len); +LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type, + __u32 query_flags, __u32 *attach_flags, + __u32 *prog_ids, __u32 *prog_cnt); +LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd); +LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, + __u32 log_buf_size, bool do_log); +LIBBPF_API 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); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* __LIBBPF_BPF_H */ diff --git a/src/contrib/libbpf/bpf/bpf_core_read.h b/src/contrib/libbpf/bpf/bpf_core_read.h new file mode 100644 index 0000000..7009dc9 --- /dev/null +++ b/src/contrib/libbpf/bpf/bpf_core_read.h @@ -0,0 +1,263 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_CORE_READ_H__ +#define __BPF_CORE_READ_H__ + +/* + * enum bpf_field_info_kind is passed as a second argument into + * __builtin_preserve_field_info() built-in to get a specific aspect of + * a field, captured as a first argument. __builtin_preserve_field_info(field, + * info_kind) returns __u32 integer and produces BTF field relocation, which + * is understood and processed by libbpf during BPF object loading. See + * selftests/bpf for examples. + */ +enum bpf_field_info_kind { + BPF_FIELD_BYTE_OFFSET = 0, /* field byte offset */ + BPF_FIELD_BYTE_SIZE = 1, + BPF_FIELD_EXISTS = 2, /* field existence in target kernel */ + BPF_FIELD_SIGNED = 3, + BPF_FIELD_LSHIFT_U64 = 4, + BPF_FIELD_RSHIFT_U64 = 5, +}; + +#define __CORE_RELO(src, field, info) \ + __builtin_preserve_field_info((src)->field, BPF_FIELD_##info) + +#if __BYTE_ORDER == __LITTLE_ENDIAN +#define __CORE_BITFIELD_PROBE_READ(dst, src, fld) \ + bpf_probe_read((void *)dst, \ + __CORE_RELO(src, fld, BYTE_SIZE), \ + (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET)) +#else +/* semantics of LSHIFT_64 assumes loading values into low-ordered bytes, so + * for big-endian we need to adjust destination pointer accordingly, based on + * field byte size + */ +#define __CORE_BITFIELD_PROBE_READ(dst, src, fld) \ + bpf_probe_read((void *)dst + (8 - __CORE_RELO(src, fld, BYTE_SIZE)), \ + __CORE_RELO(src, fld, BYTE_SIZE), \ + (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET)) +#endif + +/* + * Extract bitfield, identified by s->field, and return its value as u64. + * All this is done in relocatable manner, so bitfield changes such as + * signedness, bit size, offset changes, this will be handled automatically. + * This version of macro is using bpf_probe_read() to read underlying integer + * storage. Macro functions as an expression and its return type is + * bpf_probe_read()'s return value: 0, on success, <0 on error. + */ +#define BPF_CORE_READ_BITFIELD_PROBED(s, field) ({ \ + unsigned long long val = 0; \ + \ + __CORE_BITFIELD_PROBE_READ(&val, s, field); \ + val <<= __CORE_RELO(s, field, LSHIFT_U64); \ + if (__CORE_RELO(s, field, SIGNED)) \ + val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64); \ + else \ + val = val >> __CORE_RELO(s, field, RSHIFT_U64); \ + val; \ +}) + +/* + * Extract bitfield, identified by s->field, and return its value as u64. + * This version of macro is using direct memory reads and should be used from + * BPF program types that support such functionality (e.g., typed raw + * tracepoints). + */ +#define BPF_CORE_READ_BITFIELD(s, field) ({ \ + const void *p = (const void *)s + __CORE_RELO(s, field, BYTE_OFFSET); \ + unsigned long long val; \ + \ + switch (__CORE_RELO(s, field, BYTE_SIZE)) { \ + case 1: val = *(const unsigned char *)p; \ + case 2: val = *(const unsigned short *)p; \ + case 4: val = *(const unsigned int *)p; \ + case 8: val = *(const unsigned long long *)p; \ + } \ + val <<= __CORE_RELO(s, field, LSHIFT_U64); \ + if (__CORE_RELO(s, field, SIGNED)) \ + val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64); \ + else \ + val = val >> __CORE_RELO(s, field, RSHIFT_U64); \ + val; \ +}) + +/* + * Convenience macro to check that field actually exists in target kernel's. + * Returns: + * 1, if matching field is present in target kernel; + * 0, if no matching field found. + */ +#define bpf_core_field_exists(field) \ + __builtin_preserve_field_info(field, BPF_FIELD_EXISTS) + +/* + * Convenience macro to get byte size of a field. Works for integers, + * struct/unions, pointers, arrays, and enums. + */ +#define bpf_core_field_size(field) \ + __builtin_preserve_field_info(field, BPF_FIELD_BYTE_SIZE) + +/* + * bpf_core_read() abstracts away bpf_probe_read() call and captures offset + * relocation for source address using __builtin_preserve_access_index() + * built-in, provided by Clang. + * + * __builtin_preserve_access_index() takes as an argument an expression of + * taking an address of a field within struct/union. It makes compiler emit + * a relocation, which records BTF type ID describing root struct/union and an + * accessor string which describes exact embedded field that was used to take + * an address. See detailed description of this relocation format and + * semantics in comments to struct bpf_field_reloc in libbpf_internal.h. + * + * This relocation allows libbpf to adjust BPF instruction to use correct + * actual field offset, based on target kernel BTF type that matches original + * (local) BTF, used to record relocation. + */ +#define bpf_core_read(dst, sz, src) \ + bpf_probe_read(dst, sz, \ + (const void *)__builtin_preserve_access_index(src)) + +/* + * bpf_core_read_str() is a thin wrapper around bpf_probe_read_str() + * additionally emitting BPF CO-RE field relocation for specified source + * argument. + */ +#define bpf_core_read_str(dst, sz, src) \ + bpf_probe_read_str(dst, sz, \ + (const void *)__builtin_preserve_access_index(src)) + +#define ___concat(a, b) a ## b +#define ___apply(fn, n) ___concat(fn, n) +#define ___nth(_1, _2, _3, _4, _5, _6, _7, _8, _9, _10, __11, N, ...) N + +/* + * return number of provided arguments; used for switch-based variadic macro + * definitions (see ___last, ___arrow, etc below) + */ +#define ___narg(...) ___nth(_, ##__VA_ARGS__, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +/* + * return 0 if no arguments are passed, N - otherwise; used for + * recursively-defined macros to specify termination (0) case, and generic + * (N) case (e.g., ___read_ptrs, ___core_read) + */ +#define ___empty(...) ___nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0) + +#define ___last1(x) x +#define ___last2(a, x) x +#define ___last3(a, b, x) x +#define ___last4(a, b, c, x) x +#define ___last5(a, b, c, d, x) x +#define ___last6(a, b, c, d, e, x) x +#define ___last7(a, b, c, d, e, f, x) x +#define ___last8(a, b, c, d, e, f, g, x) x +#define ___last9(a, b, c, d, e, f, g, h, x) x +#define ___last10(a, b, c, d, e, f, g, h, i, x) x +#define ___last(...) ___apply(___last, ___narg(__VA_ARGS__))(__VA_ARGS__) + +#define ___nolast2(a, _) a +#define ___nolast3(a, b, _) a, b +#define ___nolast4(a, b, c, _) a, b, c +#define ___nolast5(a, b, c, d, _) a, b, c, d +#define ___nolast6(a, b, c, d, e, _) a, b, c, d, e +#define ___nolast7(a, b, c, d, e, f, _) a, b, c, d, e, f +#define ___nolast8(a, b, c, d, e, f, g, _) a, b, c, d, e, f, g +#define ___nolast9(a, b, c, d, e, f, g, h, _) a, b, c, d, e, f, g, h +#define ___nolast10(a, b, c, d, e, f, g, h, i, _) a, b, c, d, e, f, g, h, i +#define ___nolast(...) ___apply(___nolast, ___narg(__VA_ARGS__))(__VA_ARGS__) + +#define ___arrow1(a) a +#define ___arrow2(a, b) a->b +#define ___arrow3(a, b, c) a->b->c +#define ___arrow4(a, b, c, d) a->b->c->d +#define ___arrow5(a, b, c, d, e) a->b->c->d->e +#define ___arrow6(a, b, c, d, e, f) a->b->c->d->e->f +#define ___arrow7(a, b, c, d, e, f, g) a->b->c->d->e->f->g +#define ___arrow8(a, b, c, d, e, f, g, h) a->b->c->d->e->f->g->h +#define ___arrow9(a, b, c, d, e, f, g, h, i) a->b->c->d->e->f->g->h->i +#define ___arrow10(a, b, c, d, e, f, g, h, i, j) a->b->c->d->e->f->g->h->i->j +#define ___arrow(...) ___apply(___arrow, ___narg(__VA_ARGS__))(__VA_ARGS__) + +#define ___type(...) typeof(___arrow(__VA_ARGS__)) + +#define ___read(read_fn, dst, src_type, src, accessor) \ + read_fn((void *)(dst), sizeof(*(dst)), &((src_type)(src))->accessor) + +/* "recursively" read a sequence of inner pointers using local __t var */ +#define ___rd_first(src, a) ___read(bpf_core_read, &__t, ___type(src), src, a); +#define ___rd_last(...) \ + ___read(bpf_core_read, &__t, \ + ___type(___nolast(__VA_ARGS__)), __t, ___last(__VA_ARGS__)); +#define ___rd_p1(...) const void *__t; ___rd_first(__VA_ARGS__) +#define ___rd_p2(...) ___rd_p1(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p3(...) ___rd_p2(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p4(...) ___rd_p3(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p5(...) ___rd_p4(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p6(...) ___rd_p5(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p7(...) ___rd_p6(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p8(...) ___rd_p7(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p9(...) ___rd_p8(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___read_ptrs(src, ...) \ + ___apply(___rd_p, ___narg(__VA_ARGS__))(src, __VA_ARGS__) + +#define ___core_read0(fn, dst, src, a) \ + ___read(fn, dst, ___type(src), src, a); +#define ___core_readN(fn, dst, src, ...) \ + ___read_ptrs(src, ___nolast(__VA_ARGS__)) \ + ___read(fn, dst, ___type(src, ___nolast(__VA_ARGS__)), __t, \ + ___last(__VA_ARGS__)); +#define ___core_read(fn, dst, src, a, ...) \ + ___apply(___core_read, ___empty(__VA_ARGS__))(fn, dst, \ + src, a, ##__VA_ARGS__) + +/* + * BPF_CORE_READ_INTO() is a more performance-conscious variant of + * BPF_CORE_READ(), in which final field is read into user-provided storage. + * See BPF_CORE_READ() below for more details on general usage. + */ +#define BPF_CORE_READ_INTO(dst, src, a, ...) \ + ({ \ + ___core_read(bpf_core_read, dst, src, a, ##__VA_ARGS__) \ + }) + +/* + * BPF_CORE_READ_STR_INTO() does same "pointer chasing" as + * BPF_CORE_READ() for intermediate pointers, but then executes (and returns + * corresponding error code) bpf_core_read_str() for final string read. + */ +#define BPF_CORE_READ_STR_INTO(dst, src, a, ...) \ + ({ \ + ___core_read(bpf_core_read_str, dst, src, a, ##__VA_ARGS__) \ + }) + +/* + * BPF_CORE_READ() is used to simplify BPF CO-RE relocatable read, especially + * when there are few pointer chasing steps. + * E.g., what in non-BPF world (or in BPF w/ BCC) would be something like: + * int x = s->a.b.c->d.e->f->g; + * can be succinctly achieved using BPF_CORE_READ as: + * int x = BPF_CORE_READ(s, a.b.c, d.e, f, g); + * + * BPF_CORE_READ will decompose above statement into 4 bpf_core_read (BPF + * CO-RE relocatable bpf_probe_read() wrapper) calls, logically equivalent to: + * 1. const void *__t = s->a.b.c; + * 2. __t = __t->d.e; + * 3. __t = __t->f; + * 4. return __t->g; + * + * Equivalence is logical, because there is a heavy type casting/preservation + * involved, as well as all the reads are happening through bpf_probe_read() + * calls using __builtin_preserve_access_index() to emit CO-RE relocations. + * + * N.B. Only up to 9 "field accessors" are supported, which should be more + * than enough for any practical purpose. + */ +#define BPF_CORE_READ(src, a, ...) \ + ({ \ + ___type(src, a, ##__VA_ARGS__) __r; \ + BPF_CORE_READ_INTO(&__r, src, a, ##__VA_ARGS__); \ + __r; \ + }) + +#endif + diff --git a/src/contrib/libbpf/bpf/bpf_endian.h b/src/contrib/libbpf/bpf/bpf_endian.h new file mode 100644 index 0000000..fbe2800 --- /dev/null +++ b/src/contrib/libbpf/bpf/bpf_endian.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_ENDIAN__ +#define __BPF_ENDIAN__ + +#include <linux/stddef.h> +#include <linux/swab.h> + +/* LLVM's BPF target selects the endianness of the CPU + * it compiles on, or the user specifies (bpfel/bpfeb), + * respectively. The used __BYTE_ORDER__ is defined by + * the compiler, we cannot rely on __BYTE_ORDER from + * libc headers, since it doesn't reflect the actual + * requested byte order. + * + * Note, LLVM's BPF target has different __builtin_bswapX() + * semantics. It does map to BPF_ALU | BPF_END | BPF_TO_BE + * in bpfel and bpfeb case, which means below, that we map + * to cpu_to_be16(). We could use it unconditionally in BPF + * case, but better not rely on it, so that this header here + * can be used from application and BPF program side, which + * use different targets. + */ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +# define __bpf_ntohs(x) __builtin_bswap16(x) +# define __bpf_htons(x) __builtin_bswap16(x) +# define __bpf_constant_ntohs(x) ___constant_swab16(x) +# define __bpf_constant_htons(x) ___constant_swab16(x) +# define __bpf_ntohl(x) __builtin_bswap32(x) +# define __bpf_htonl(x) __builtin_bswap32(x) +# define __bpf_constant_ntohl(x) ___constant_swab32(x) +# define __bpf_constant_htonl(x) ___constant_swab32(x) +# define __bpf_be64_to_cpu(x) __builtin_bswap64(x) +# define __bpf_cpu_to_be64(x) __builtin_bswap64(x) +# define __bpf_constant_be64_to_cpu(x) ___constant_swab64(x) +# define __bpf_constant_cpu_to_be64(x) ___constant_swab64(x) +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +# define __bpf_ntohs(x) (x) +# define __bpf_htons(x) (x) +# define __bpf_constant_ntohs(x) (x) +# define __bpf_constant_htons(x) (x) +# define __bpf_ntohl(x) (x) +# define __bpf_htonl(x) (x) +# define __bpf_constant_ntohl(x) (x) +# define __bpf_constant_htonl(x) (x) +# define __bpf_be64_to_cpu(x) (x) +# define __bpf_cpu_to_be64(x) (x) +# define __bpf_constant_be64_to_cpu(x) (x) +# define __bpf_constant_cpu_to_be64(x) (x) +#else +# error "Fix your compiler's __BYTE_ORDER__?!" +#endif + +#define bpf_htons(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_htons(x) : __bpf_htons(x)) +#define bpf_ntohs(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_ntohs(x) : __bpf_ntohs(x)) +#define bpf_htonl(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_htonl(x) : __bpf_htonl(x)) +#define bpf_ntohl(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_ntohl(x) : __bpf_ntohl(x)) +#define bpf_cpu_to_be64(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_cpu_to_be64(x) : __bpf_cpu_to_be64(x)) +#define bpf_be64_to_cpu(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_be64_to_cpu(x) : __bpf_be64_to_cpu(x)) + +#endif /* __BPF_ENDIAN__ */ diff --git a/src/contrib/libbpf/bpf/bpf_helper_defs.h b/src/contrib/libbpf/bpf/bpf_helper_defs.h new file mode 100644 index 0000000..1f357f6 --- /dev/null +++ b/src/contrib/libbpf/bpf/bpf_helper_defs.h @@ -0,0 +1,2759 @@ +/* This is auto-generated file. See bpf_helpers_doc.py for details. */ + +/* Forward declarations of BPF structs */ +struct bpf_fib_lookup; +struct bpf_perf_event_data; +struct bpf_perf_event_value; +struct bpf_sock; +struct bpf_sock_addr; +struct bpf_sock_ops; +struct bpf_sock_tuple; +struct bpf_spin_lock; +struct bpf_sysctl; +struct bpf_tcp_sock; +struct bpf_tunnel_key; +struct bpf_xfrm_state; +struct pt_regs; +struct sk_reuseport_md; +struct sockaddr; +struct tcphdr; +struct __sk_buff; +struct sk_msg_md; +struct xdp_md; + +/* + * bpf_map_lookup_elem + * + * Perform a lookup in *map* for an entry associated to *key*. + * + * Returns + * Map value associated to *key*, or **NULL** if no entry was + * found. + */ +static void *(*bpf_map_lookup_elem)(void *map, const void *key) = (void *) 1; + +/* + * bpf_map_update_elem + * + * Add or update the value of the entry associated to *key* in + * *map* with *value*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * Flag value **BPF_NOEXIST** cannot be used for maps of types + * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all + * elements always exist), the helper would return an error. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_map_update_elem)(void *map, const void *key, const void *value, __u64 flags) = (void *) 2; + +/* + * bpf_map_delete_elem + * + * Delete entry with *key* from *map*. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_map_delete_elem)(void *map, const void *key) = (void *) 3; + +/* + * bpf_probe_read + * + * For tracing programs, safely attempt to read *size* bytes from + * kernel space address *unsafe_ptr* and store the data in *dst*. + * + * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel() + * instead. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_probe_read)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 4; + +/* + * bpf_ktime_get_ns + * + * Return the time elapsed since system boot, in nanoseconds. + * + * Returns + * Current *ktime*. + */ +static __u64 (*bpf_ktime_get_ns)(void) = (void *) 5; + +/* + * bpf_trace_printk + * + * This helper is a "printk()-like" facility for debugging. It + * prints a message defined by format *fmt* (of size *fmt_size*) + * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if + * available. It can take up to three additional **u64** + * arguments (as an eBPF helpers, the total number of arguments is + * limited to five). + * + * Each time the helper is called, it appends a line to the trace. + * Lines are discarded while *\/sys/kernel/debug/tracing/trace* is + * open, use *\/sys/kernel/debug/tracing/trace_pipe* to avoid this. + * The format of the trace is customizable, and the exact output + * one will get depends on the options set in + * *\/sys/kernel/debug/tracing/trace_options* (see also the + * *README* file under the same directory). However, it usually + * defaults to something like: + * + * :: + * + * telnet-470 [001] .N.. 419421.045894: 0x00000001: <formatted msg> + * + * In the above: + * + * * ``telnet`` is the name of the current task. + * * ``470`` is the PID of the current task. + * * ``001`` is the CPU number on which the task is + * running. + * * In ``.N..``, each character refers to a set of + * options (whether irqs are enabled, scheduling + * options, whether hard/softirqs are running, level of + * preempt_disabled respectively). **N** means that + * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED** + * are set. + * * ``419421.045894`` is a timestamp. + * * ``0x00000001`` is a fake value used by BPF for the + * instruction pointer register. + * * ``<formatted msg>`` is the message formatted with + * *fmt*. + * + * The conversion specifiers supported by *fmt* are similar, but + * more limited than for printk(). They are **%d**, **%i**, + * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**, + * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size + * of field, padding with zeroes, etc.) is available, and the + * helper will return **-EINVAL** (but print nothing) if it + * encounters an unknown specifier. + * + * Also, note that **bpf_trace_printk**\ () is slow, and should + * only be used for debugging purposes. For this reason, a notice + * bloc (spanning several lines) is printed to kernel logs and + * states that the helper should not be used "for production use" + * the first time this helper is used (or more precisely, when + * **trace_printk**\ () buffers are allocated). For passing values + * to user space, perf events should be preferred. + * + * Returns + * The number of bytes written to the buffer, or a negative error + * in case of failure. + */ +static int (*bpf_trace_printk)(const char *fmt, __u32 fmt_size, ...) = (void *) 6; + +/* + * bpf_get_prandom_u32 + * + * Get a pseudo-random number. + * + * From a security point of view, this helper uses its own + * pseudo-random internal state, and cannot be used to infer the + * seed of other random functions in the kernel. However, it is + * essential to note that the generator used by the helper is not + * cryptographically secure. + * + * Returns + * A random 32-bit unsigned value. + */ +static __u32 (*bpf_get_prandom_u32)(void) = (void *) 7; + +/* + * bpf_get_smp_processor_id + * + * Get the SMP (symmetric multiprocessing) processor id. Note that + * all programs run with preemption disabled, which means that the + * SMP processor id is stable during all the execution of the + * program. + * + * Returns + * The SMP id of the processor running the program. + */ +static __u32 (*bpf_get_smp_processor_id)(void) = (void *) 8; + +/* + * bpf_skb_store_bytes + * + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. *flags* are a combination of + * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the + * checksum for the packet after storing the bytes) and + * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ + * **->swhash** and *skb*\ **->l4hash** to 0). + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_store_bytes)(struct __sk_buff *skb, __u32 offset, const void *from, __u32 len, __u64 flags) = (void *) 9; + +/* + * bpf_l3_csum_replace + * + * Recompute the layer 3 (e.g. IP) checksum for the packet + * associated to *skb*. Computation is incremental, so the helper + * must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored in *size*. + * Alternatively, it is possible to store the difference between + * the previous and the new values of the header field in *to*, by + * setting *from* and *size* to 0. For both methods, *offset* + * indicates the location of the IP checksum within the packet. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_l3_csum_replace)(struct __sk_buff *skb, __u32 offset, __u64 from, __u64 to, __u64 size) = (void *) 10; + +/* + * bpf_l4_csum_replace + * + * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the + * packet associated to *skb*. Computation is incremental, so the + * helper must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored on the lowest + * four bits of *flags*. Alternatively, it is possible to store + * the difference between the previous and the new values of the + * header field in *to*, by setting *from* and the four lowest + * bits of *flags* to 0. For both methods, *offset* indicates the + * location of the IP checksum within the packet. In addition to + * the size of the field, *flags* can be added (bitwise OR) actual + * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left + * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and + * for updates resulting in a null checksum the value is set to + * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates + * the checksum is to be computed against a pseudo-header. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_l4_csum_replace)(struct __sk_buff *skb, __u32 offset, __u64 from, __u64 to, __u64 flags) = (void *) 11; + +/* + * bpf_tail_call + * + * This special helper is used to trigger a "tail call", or in + * other words, to jump into another eBPF program. The same stack + * frame is used (but values on stack and in registers for the + * caller are not accessible to the callee). This mechanism allows + * for program chaining, either for raising the maximum number of + * available eBPF instructions, or to execute given programs in + * conditional blocks. For security reasons, there is an upper + * limit to the number of successive tail calls that can be + * performed. + * + * Upon call of this helper, the program attempts to jump into a + * program referenced at index *index* in *prog_array_map*, a + * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes + * *ctx*, a pointer to the context. + * + * If the call succeeds, the kernel immediately runs the first + * instruction of the new program. This is not a function call, + * and it never returns to the previous program. If the call + * fails, then the helper has no effect, and the caller continues + * to run its subsequent instructions. A call can fail if the + * destination program for the jump does not exist (i.e. *index* + * is superior to the number of entries in *prog_array_map*), or + * if the maximum number of tail calls has been reached for this + * chain of programs. This limit is defined in the kernel by the + * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), + * which is currently set to 32. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_tail_call)(void *ctx, void *prog_array_map, __u32 index) = (void *) 12; + +/* + * bpf_clone_redirect + * + * Clone and redirect the packet associated to *skb* to another + * net device of index *ifindex*. Both ingress and egress + * interfaces can be used for redirection. The **BPF_F_INGRESS** + * value in *flags* is used to make the distinction (ingress path + * is selected if the flag is present, egress path otherwise). + * This is the only flag supported for now. + * + * In comparison with **bpf_redirect**\ () helper, + * **bpf_clone_redirect**\ () has the associated cost of + * duplicating the packet buffer, but this can be executed out of + * the eBPF program. Conversely, **bpf_redirect**\ () is more + * efficient, but it is handled through an action code where the + * redirection happens only after the eBPF program has returned. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_clone_redirect)(struct __sk_buff *skb, __u32 ifindex, __u64 flags) = (void *) 13; + +/* + * bpf_get_current_pid_tgid + * + * + * Returns + * A 64-bit integer containing the current tgid and pid, and + * created as such: + * *current_task*\ **->tgid << 32 \|** + * *current_task*\ **->pid**. + */ +static __u64 (*bpf_get_current_pid_tgid)(void) = (void *) 14; + +/* + * bpf_get_current_uid_gid + * + * + * Returns + * A 64-bit integer containing the current GID and UID, and + * created as such: *current_gid* **<< 32 \|** *current_uid*. + */ +static __u64 (*bpf_get_current_uid_gid)(void) = (void *) 15; + +/* + * bpf_get_current_comm + * + * Copy the **comm** attribute of the current task into *buf* of + * *size_of_buf*. The **comm** attribute contains the name of + * the executable (excluding the path) for the current task. The + * *size_of_buf* must be strictly positive. On success, the + * helper makes sure that the *buf* is NUL-terminated. On failure, + * it is filled with zeroes. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_get_current_comm)(void *buf, __u32 size_of_buf) = (void *) 16; + +/* + * bpf_get_cgroup_classid + * + * Retrieve the classid for the current task, i.e. for the net_cls + * cgroup to which *skb* belongs. + * + * This helper can be used on TC egress path, but not on ingress. + * + * The net_cls cgroup provides an interface to tag network packets + * based on a user-provided identifier for all traffic coming from + * the tasks belonging to the related cgroup. See also the related + * kernel documentation, available from the Linux sources in file + * *Documentation/admin-guide/cgroup-v1/net_cls.rst*. + * + * The Linux kernel has two versions for cgroups: there are + * cgroups v1 and cgroups v2. Both are available to users, who can + * use a mixture of them, but note that the net_cls cgroup is for + * cgroup v1 only. This makes it incompatible with BPF programs + * run on cgroups, which is a cgroup-v2-only feature (a socket can + * only hold data for one version of cgroups at a time). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to + * "**y**" or to "**m**". + * + * Returns + * The classid, or 0 for the default unconfigured classid. + */ +static __u32 (*bpf_get_cgroup_classid)(struct __sk_buff *skb) = (void *) 17; + +/* + * bpf_skb_vlan_push + * + * Push a *vlan_tci* (VLAN tag control information) of protocol + * *vlan_proto* to the packet associated to *skb*, then update + * the checksum. Note that if *vlan_proto* is different from + * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to + * be **ETH_P_8021Q**. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_vlan_push)(struct __sk_buff *skb, __be16 vlan_proto, __u16 vlan_tci) = (void *) 18; + +/* + * bpf_skb_vlan_pop + * + * Pop a VLAN header from the packet associated to *skb*. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_vlan_pop)(struct __sk_buff *skb) = (void *) 19; + +/* + * bpf_skb_get_tunnel_key + * + * Get tunnel metadata. This helper takes a pointer *key* to an + * empty **struct bpf_tunnel_key** of **size**, that will be + * filled with tunnel metadata for the packet associated to *skb*. + * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which + * indicates that the tunnel is based on IPv6 protocol instead of + * IPv4. + * + * The **struct bpf_tunnel_key** is an object that generalizes the + * principal parameters used by various tunneling protocols into a + * single struct. This way, it can be used to easily make a + * decision based on the contents of the encapsulation header, + * "summarized" in this struct. In particular, it holds the IP + * address of the remote end (IPv4 or IPv6, depending on the case) + * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also, + * this struct exposes the *key*\ **->tunnel_id**, which is + * generally mapped to a VNI (Virtual Network Identifier), making + * it programmable together with the **bpf_skb_set_tunnel_key**\ + * () helper. + * + * Let's imagine that the following code is part of a program + * attached to the TC ingress interface, on one end of a GRE + * tunnel, and is supposed to filter out all messages coming from + * remote ends with IPv4 address other than 10.0.0.1: + * + * :: + * + * int ret; + * struct bpf_tunnel_key key = {}; + * + * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + * if (ret < 0) + * return TC_ACT_SHOT; // drop packet + * + * if (key.remote_ipv4 != 0x0a000001) + * return TC_ACT_SHOT; // drop packet + * + * return TC_ACT_OK; // accept packet + * + * This interface can also be used with all encapsulation devices + * that can operate in "collect metadata" mode: instead of having + * one network device per specific configuration, the "collect + * metadata" mode only requires a single device where the + * configuration can be extracted from this helper. + * + * This can be used together with various tunnels such as VXLan, + * Geneve, GRE or IP in IP (IPIP). + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_get_tunnel_key)(struct __sk_buff *skb, struct bpf_tunnel_key *key, __u32 size, __u64 flags) = (void *) 20; + +/* + * bpf_skb_set_tunnel_key + * + * Populate tunnel metadata for packet associated to *skb.* The + * tunnel metadata is set to the contents of *key*, of *size*. The + * *flags* can be set to a combination of the following values: + * + * **BPF_F_TUNINFO_IPV6** + * Indicate that the tunnel is based on IPv6 protocol + * instead of IPv4. + * **BPF_F_ZERO_CSUM_TX** + * For IPv4 packets, add a flag to tunnel metadata + * indicating that checksum computation should be skipped + * and checksum set to zeroes. + * **BPF_F_DONT_FRAGMENT** + * Add a flag to tunnel metadata indicating that the + * packet should not be fragmented. + * **BPF_F_SEQ_NUMBER** + * Add a flag to tunnel metadata indicating that a + * sequence number should be added to tunnel header before + * sending the packet. This flag was added for GRE + * encapsulation, but might be used with other protocols + * as well in the future. + * + * Here is a typical usage on the transmit path: + * + * :: + * + * struct bpf_tunnel_key key; + * populate key ... + * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0); + * + * See also the description of the **bpf_skb_get_tunnel_key**\ () + * helper for additional information. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_set_tunnel_key)(struct __sk_buff *skb, struct bpf_tunnel_key *key, __u32 size, __u64 flags) = (void *) 21; + +/* + * bpf_perf_event_read + * + * Read the value of a perf event counter. This helper relies on a + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of + * the perf event counter is selected when *map* is updated with + * perf event file descriptors. The *map* is an array whose size + * is the number of available CPUs, and each cell contains a value + * relative to one CPU. The value to retrieve is indicated by + * *flags*, that contains the index of the CPU to look up, masked + * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * Note that before Linux 4.13, only hardware perf event can be + * retrieved. + * + * Also, be aware that the newer helper + * **bpf_perf_event_read_value**\ () is recommended over + * **bpf_perf_event_read**\ () in general. The latter has some ABI + * quirks where error and counter value are used as a return code + * (which is wrong to do since ranges may overlap). This issue is + * fixed with **bpf_perf_event_read_value**\ (), which at the same + * time provides more features over the **bpf_perf_event_read**\ + * () interface. Please refer to the description of + * **bpf_perf_event_read_value**\ () for details. + * + * Returns + * The value of the perf event counter read from the map, or a + * negative error code in case of failure. + */ +static __u64 (*bpf_perf_event_read)(void *map, __u64 flags) = (void *) 22; + +/* + * bpf_redirect + * + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_clone_redirect**\ + * (), except that the packet is not cloned, which provides + * increased performance. + * + * Except for XDP, both ingress and egress interfaces can be used + * for redirection. The **BPF_F_INGRESS** value in *flags* is used + * to make the distinction (ingress path is selected if the flag + * is present, egress path otherwise). Currently, XDP only + * supports redirection to the egress interface, and accepts no + * flag at all. + * + * The same effect can be attained with the more generic + * **bpf_redirect_map**\ (), which requires specific maps to be + * used but offers better performance. + * + * Returns + * For XDP, the helper returns **XDP_REDIRECT** on success or + * **XDP_ABORTED** on error. For other program types, the values + * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on + * error. + */ +static int (*bpf_redirect)(__u32 ifindex, __u64 flags) = (void *) 23; + +/* + * bpf_get_route_realm + * + * Retrieve the realm or the route, that is to say the + * **tclassid** field of the destination for the *skb*. The + * indentifier retrieved is a user-provided tag, similar to the + * one used with the net_cls cgroup (see description for + * **bpf_get_cgroup_classid**\ () helper), but here this tag is + * held by a route (a destination entry), not by a task. + * + * Retrieving this identifier works with the clsact TC egress hook + * (see also **tc-bpf(8)**), or alternatively on conventional + * classful egress qdiscs, but not on TC ingress path. In case of + * clsact TC egress hook, this has the advantage that, internally, + * the destination entry has not been dropped yet in the transmit + * path. Therefore, the destination entry does not need to be + * artificially held via **netif_keep_dst**\ () for a classful + * qdisc until the *skb* is freed. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_IP_ROUTE_CLASSID** configuration option. + * + * Returns + * The realm of the route for the packet associated to *skb*, or 0 + * if none was found. + */ +static __u32 (*bpf_get_route_realm)(struct __sk_buff *skb) = (void *) 24; + +/* + * bpf_perf_event_output + * + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * The context of the program *ctx* needs also be passed to the + * helper. + * + * On user space, a program willing to read the values needs to + * call **perf_event_open**\ () on the perf event (either for + * one or for all CPUs) and to store the file descriptor into the + * *map*. This must be done before the eBPF program can send data + * into it. An example is available in file + * *samples/bpf/trace_output_user.c* in the Linux kernel source + * tree (the eBPF program counterpart is in + * *samples/bpf/trace_output_kern.c*). + * + * **bpf_perf_event_output**\ () achieves better performance + * than **bpf_trace_printk**\ () for sharing data with user + * space, and is much better suitable for streaming data from eBPF + * programs. + * + * Note that this helper is not restricted to tracing use cases + * and can be used with programs attached to TC or XDP as well, + * where it allows for passing data to user space listeners. Data + * can be: + * + * * Only custom structs, + * * Only the packet payload, or + * * A combination of both. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_perf_event_output)(void *ctx, void *map, __u64 flags, void *data, __u64 size) = (void *) 25; + +/* + * bpf_skb_load_bytes + * + * This helper was provided as an easy way to load data from a + * packet. It can be used to load *len* bytes from *offset* from + * the packet associated to *skb*, into the buffer pointed by + * *to*. + * + * Since Linux 4.7, usage of this helper has mostly been replaced + * by "direct packet access", enabling packet data to be + * manipulated with *skb*\ **->data** and *skb*\ **->data_end** + * pointing respectively to the first byte of packet data and to + * the byte after the last byte of packet data. However, it + * remains useful if one wishes to read large quantities of data + * at once from a packet into the eBPF stack. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_load_bytes)(const void *skb, __u32 offset, void *to, __u32 len) = (void *) 26; + +/* + * bpf_get_stackid + * + * Walk a user or a kernel stack and return its id. To achieve + * this, the helper needs *ctx*, which is a pointer to the context + * on which the tracing program is executed, and a pointer to a + * *map* of type **BPF_MAP_TYPE_STACK_TRACE**. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * a combination of the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_FAST_STACK_CMP** + * Compare stacks by hash only. + * **BPF_F_REUSE_STACKID** + * If two different stacks hash into the same *stackid*, + * discard the old one. + * + * The stack id retrieved is a 32 bit long integer handle which + * can be further combined with other data (including other stack + * ids) and used as a key into maps. This can be useful for + * generating a variety of graphs (such as flame graphs or off-cpu + * graphs). + * + * For walking a stack, this helper is an improvement over + * **bpf_probe_read**\ (), which can be used with unrolled loops + * but is not efficient and consumes a lot of eBPF instructions. + * Instead, **bpf_get_stackid**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * + * Returns + * The positive or null stack id on success, or a negative error + * in case of failure. + */ +static int (*bpf_get_stackid)(void *ctx, void *map, __u64 flags) = (void *) 27; + +/* + * bpf_csum_diff + * + * Compute a checksum difference, from the raw buffer pointed by + * *from*, of length *from_size* (that must be a multiple of 4), + * towards the raw buffer pointed by *to*, of size *to_size* + * (same remark). An optional *seed* can be added to the value + * (this can be cascaded, the seed may come from a previous call + * to the helper). + * + * This is flexible enough to be used in several ways: + * + * * With *from_size* == 0, *to_size* > 0 and *seed* set to + * checksum, it can be used when pushing new data. + * * With *from_size* > 0, *to_size* == 0 and *seed* set to + * checksum, it can be used when removing data from a packet. + * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it + * can be used to compute a diff. Note that *from_size* and + * *to_size* do not need to be equal. + * + * This helper can be used in combination with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to + * which one can feed in the difference computed with + * **bpf_csum_diff**\ (). + * + * Returns + * The checksum result, or a negative error code in case of + * failure. + */ +static __s64 (*bpf_csum_diff)(__be32 *from, __u32 from_size, __be32 *to, __u32 to_size, __wsum seed) = (void *) 28; + +/* + * bpf_skb_get_tunnel_opt + * + * Retrieve tunnel options metadata for the packet associated to + * *skb*, and store the raw tunnel option data to the buffer *opt* + * of *size*. + * + * This helper can be used with encapsulation devices that can + * operate in "collect metadata" mode (please refer to the related + * note in the description of **bpf_skb_get_tunnel_key**\ () for + * more details). A particular example where this can be used is + * in combination with the Geneve encapsulation protocol, where it + * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper) + * and retrieving arbitrary TLVs (Type-Length-Value headers) from + * the eBPF program. This allows for full customization of these + * headers. + * + * Returns + * The size of the option data retrieved. + */ +static int (*bpf_skb_get_tunnel_opt)(struct __sk_buff *skb, void *opt, __u32 size) = (void *) 29; + +/* + * bpf_skb_set_tunnel_opt + * + * Set tunnel options metadata for the packet associated to *skb* + * to the option data contained in the raw buffer *opt* of *size*. + * + * See also the description of the **bpf_skb_get_tunnel_opt**\ () + * helper for additional information. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_set_tunnel_opt)(struct __sk_buff *skb, void *opt, __u32 size) = (void *) 30; + +/* + * bpf_skb_change_proto + * + * Change the protocol of the *skb* to *proto*. Currently + * supported are transition from IPv4 to IPv6, and from IPv6 to + * IPv4. The helper takes care of the groundwork for the + * transition, including resizing the socket buffer. The eBPF + * program is expected to fill the new headers, if any, via + * **skb_store_bytes**\ () and to recompute the checksums with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ + * (). The main case for this helper is to perform NAT64 + * operations out of an eBPF program. + * + * Internally, the GSO type is marked as dodgy so that headers are + * checked and segments are recalculated by the GSO/GRO engine. + * The size for GSO target is adapted as well. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_change_proto)(struct __sk_buff *skb, __be16 proto, __u64 flags) = (void *) 31; + +/* + * bpf_skb_change_type + * + * Change the packet type for the packet associated to *skb*. This + * comes down to setting *skb*\ **->pkt_type** to *type*, except + * the eBPF program does not have a write access to *skb*\ + * **->pkt_type** beside this helper. Using a helper here allows + * for graceful handling of errors. + * + * The major use case is to change incoming *skb*s to + * **PACKET_HOST** in a programmatic way instead of having to + * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for + * example. + * + * Note that *type* only allows certain values. At this time, they + * are: + * + * **PACKET_HOST** + * Packet is for us. + * **PACKET_BROADCAST** + * Send packet to all. + * **PACKET_MULTICAST** + * Send packet to group. + * **PACKET_OTHERHOST** + * Send packet to someone else. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_change_type)(struct __sk_buff *skb, __u32 type) = (void *) 32; + +/* + * bpf_skb_under_cgroup + * + * Check whether *skb* is a descendant of the cgroup2 held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * + * Returns + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* failed the cgroup2 descendant test. + * * 1, if the *skb* succeeded the cgroup2 descendant test. + * * A negative error code, if an error occurred. + */ +static int (*bpf_skb_under_cgroup)(struct __sk_buff *skb, void *map, __u32 index) = (void *) 33; + +/* + * bpf_get_hash_recalc + * + * Retrieve the hash of the packet, *skb*\ **->hash**. If it is + * not set, in particular if the hash was cleared due to mangling, + * recompute this hash. Later accesses to the hash can be done + * directly with *skb*\ **->hash**. + * + * Calling **bpf_set_hash_invalid**\ (), changing a packet + * prototype with **bpf_skb_change_proto**\ (), or calling + * **bpf_skb_store_bytes**\ () with the + * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear + * the hash and to trigger a new computation for the next call to + * **bpf_get_hash_recalc**\ (). + * + * Returns + * The 32-bit hash. + */ +static __u32 (*bpf_get_hash_recalc)(struct __sk_buff *skb) = (void *) 34; + +/* + * bpf_get_current_task + * + * + * Returns + * A pointer to the current task struct. + */ +static __u64 (*bpf_get_current_task)(void) = (void *) 35; + +/* + * bpf_probe_write_user + * + * Attempt in a safe way to write *len* bytes from the buffer + * *src* to *dst* in memory. It only works for threads that are in + * user context, and *dst* must be a valid user space address. + * + * This helper should not be used to implement any kind of + * security mechanism because of TOC-TOU attacks, but rather to + * debug, divert, and manipulate execution of semi-cooperative + * processes. + * + * Keep in mind that this feature is meant for experiments, and it + * has a risk of crashing the system and running programs. + * Therefore, when an eBPF program using this helper is attached, + * a warning including PID and process name is printed to kernel + * logs. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_probe_write_user)(void *dst, const void *src, __u32 len) = (void *) 36; + +/* + * bpf_current_task_under_cgroup + * + * Check whether the probe is being run is the context of a given + * subset of the cgroup2 hierarchy. The cgroup2 to test is held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * + * Returns + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* task belongs to the cgroup2. + * * 1, if the *skb* task does not belong to the cgroup2. + * * A negative error code, if an error occurred. + */ +static int (*bpf_current_task_under_cgroup)(void *map, __u32 index) = (void *) 37; + +/* + * bpf_skb_change_tail + * + * Resize (trim or grow) the packet associated to *skb* to the + * new *len*. The *flags* are reserved for future usage, and must + * be left at zero. + * + * The basic idea is that the helper performs the needed work to + * change the size of the packet, then the eBPF program rewrites + * the rest via helpers like **bpf_skb_store_bytes**\ (), + * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ () + * and others. This helper is a slow path utility intended for + * replies with control messages. And because it is targeted for + * slow path, the helper itself can afford to be slow: it + * implicitly linearizes, unclones and drops offloads from the + * *skb*. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_change_tail)(struct __sk_buff *skb, __u32 len, __u64 flags) = (void *) 38; + +/* + * bpf_skb_pull_data + * + * Pull in non-linear data in case the *skb* is non-linear and not + * all of *len* are part of the linear section. Make *len* bytes + * from *skb* readable and writable. If a zero value is passed for + * *len*, then the whole length of the *skb* is pulled. + * + * This helper is only needed for reading and writing with direct + * packet access. + * + * For direct packet access, testing that offsets to access + * are within packet boundaries (test on *skb*\ **->data_end**) is + * susceptible to fail if offsets are invalid, or if the requested + * data is in non-linear parts of the *skb*. On failure the + * program can just bail out, or in the case of a non-linear + * buffer, use a helper to make the data available. The + * **bpf_skb_load_bytes**\ () helper is a first solution to access + * the data. Another one consists in using **bpf_skb_pull_data** + * to pull in once the non-linear parts, then retesting and + * eventually access the data. + * + * At the same time, this also makes sure the *skb* is uncloned, + * which is a necessary condition for direct write. As this needs + * to be an invariant for the write part only, the verifier + * detects writes and adds a prologue that is calling + * **bpf_skb_pull_data()** to effectively unclone the *skb* from + * the very beginning in case it is indeed cloned. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_pull_data)(struct __sk_buff *skb, __u32 len) = (void *) 39; + +/* + * bpf_csum_update + * + * Add the checksum *csum* into *skb*\ **->csum** in case the + * driver has supplied a checksum for the entire packet into that + * field. Return an error otherwise. This helper is intended to be + * used in combination with **bpf_csum_diff**\ (), in particular + * when the checksum needs to be updated after data has been + * written into the packet through direct packet access. + * + * Returns + * The checksum on success, or a negative error code in case of + * failure. + */ +static __s64 (*bpf_csum_update)(struct __sk_buff *skb, __wsum csum) = (void *) 40; + +/* + * bpf_set_hash_invalid + * + * Invalidate the current *skb*\ **->hash**. It can be used after + * mangling on headers through direct packet access, in order to + * indicate that the hash is outdated and to trigger a + * recalculation the next time the kernel tries to access this + * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * + */ +static void (*bpf_set_hash_invalid)(struct __sk_buff *skb) = (void *) 41; + +/* + * bpf_get_numa_node_id + * + * Return the id of the current NUMA node. The primary use case + * for this helper is the selection of sockets for the local NUMA + * node, when the program is attached to sockets using the + * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**), + * but the helper is also available to other eBPF program types, + * similarly to **bpf_get_smp_processor_id**\ (). + * + * Returns + * The id of current NUMA node. + */ +static int (*bpf_get_numa_node_id)(void) = (void *) 42; + +/* + * bpf_skb_change_head + * + * Grows headroom of packet associated to *skb* and adjusts the + * offset of the MAC header accordingly, adding *len* bytes of + * space. It automatically extends and reallocates memory as + * required. + * + * This helper can be used on a layer 3 *skb* to push a MAC header + * for redirection into a layer 2 device. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_change_head)(struct __sk_buff *skb, __u32 len, __u64 flags) = (void *) 43; + +/* + * bpf_xdp_adjust_head + * + * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that + * it is possible to use a negative value for *delta*. This helper + * can be used to prepare the packet for pushing or popping + * headers. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_xdp_adjust_head)(struct xdp_md *xdp_md, int delta) = (void *) 44; + +/* + * bpf_probe_read_str + * + * Copy a NUL terminated string from an unsafe kernel address + * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for + * more details. + * + * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str() + * instead. + * + * Returns + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + */ +static int (*bpf_probe_read_str)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 45; + +/* + * bpf_get_socket_cookie + * + * If the **struct sk_buff** pointed by *skb* has a known socket, + * retrieve the cookie (generated by the kernel) of this socket. + * If no cookie has been set yet, generate a new cookie. Once + * generated, the socket cookie remains stable for the life of the + * socket. This helper can be useful for monitoring per socket + * networking traffic statistics as it provides a global socket + * identifier that can be assumed unique. + * + * Returns + * A 8-byte long non-decreasing number on success, or 0 if the + * socket field is missing inside *skb*. + */ +static __u64 (*bpf_get_socket_cookie)(void *ctx) = (void *) 46; + +/* + * bpf_get_socket_uid + * + * + * Returns + * The owner UID of the socket associated to *skb*. If the socket + * is **NULL**, or if it is not a full socket (i.e. if it is a + * time-wait or a request socket instead), **overflowuid** value + * is returned (note that **overflowuid** might also be the actual + * UID value for the socket). + */ +static __u32 (*bpf_get_socket_uid)(struct __sk_buff *skb) = (void *) 47; + +/* + * bpf_set_hash + * + * Set the full hash for *skb* (set the field *skb*\ **->hash**) + * to value *hash*. + * + * Returns + * 0 + */ +static __u32 (*bpf_set_hash)(struct __sk_buff *skb, __u32 hash) = (void *) 48; + +/* + * bpf_setsockopt + * + * Emulate a call to **setsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **setsockopt(2)** for more information. + * The option value of length *optlen* is pointed by *optval*. + * + * This helper actually implements a subset of **setsockopt()**. + * It supports the following *level*\ s: + * + * * **SOL_SOCKET**, which supports the following *optname*\ s: + * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * * **IPPROTO_TCP**, which supports the following *optname*\ s: + * **TCP_CONGESTION**, **TCP_BPF_IW**, + * **TCP_BPF_SNDCWND_CLAMP**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_setsockopt)(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) = (void *) 49; + +/* + * bpf_skb_adjust_room + * + * Grow or shrink the room for data in the packet associated to + * *skb* by *len_diff*, and according to the selected *mode*. + * + * There are two supported modes at this time: + * + * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer + * (room space is added or removed below the layer 2 header). + * + * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer + * (room space is added or removed below the layer 3 header). + * + * The following flags are supported at this time: + * + * * **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size. + * Adjusting mss in this way is not allowed for datagrams. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4**, + * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6**: + * Any new space is reserved to hold a tunnel header. + * Configure skb offsets and other fields accordingly. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L4_GRE**, + * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP**: + * Use with ENCAP_L3 flags to further specify the tunnel type. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L2**\ (*len*): + * Use with ENCAP_L3/L4 flags to further specify the tunnel + * type; *len* is the length of the inner MAC header. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_adjust_room)(struct __sk_buff *skb, __s32 len_diff, __u32 mode, __u64 flags) = (void *) 50; + +/* + * bpf_redirect_map + * + * Redirect the packet to the endpoint referenced by *map* at + * index *key*. Depending on its type, this *map* can contain + * references to net devices (for forwarding packets through other + * ports), or to CPUs (for redirecting XDP frames to another CPU; + * but this is only implemented for native XDP (with driver + * support) as of this writing). + * + * The lower two bits of *flags* are used as the return code if + * the map lookup fails. This is so that the return value can be + * one of the XDP program return codes up to XDP_TX, as chosen by + * the caller. Any higher bits in the *flags* argument must be + * unset. + * + * When used to redirect packets to net devices, this helper + * provides a high performance increase over **bpf_redirect**\ (). + * This is due to various implementation details of the underlying + * mechanisms, one of which is the fact that **bpf_redirect_map**\ + * () tries to send packet as a "bulk" to the device. + * + * Returns + * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + */ +static int (*bpf_redirect_map)(void *map, __u32 key, __u64 flags) = (void *) 51; + +/* + * bpf_sk_redirect_map + * + * Redirect the packet to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * + * Returns + * **SK_PASS** on success, or **SK_DROP** on error. + */ +static int (*bpf_sk_redirect_map)(struct __sk_buff *skb, void *map, __u32 key, __u64 flags) = (void *) 52; + +/* + * bpf_sock_map_update + * + * Add an entry to, or update a *map* referencing sockets. The + * *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_sock_map_update)(struct bpf_sock_ops *skops, void *map, void *key, __u64 flags) = (void *) 53; + +/* + * bpf_xdp_adjust_meta + * + * Adjust the address pointed by *xdp_md*\ **->data_meta** by + * *delta* (which can be positive or negative). Note that this + * operation modifies the address stored in *xdp_md*\ **->data**, + * so the latter must be loaded only after the helper has been + * called. + * + * The use of *xdp_md*\ **->data_meta** is optional and programs + * are not required to use it. The rationale is that when the + * packet is processed with XDP (e.g. as DoS filter), it is + * possible to push further meta data along with it before passing + * to the stack, and to give the guarantee that an ingress eBPF + * program attached as a TC classifier on the same device can pick + * this up for further post-processing. Since TC works with socket + * buffers, it remains possible to set from XDP the **mark** or + * **priority** pointers, or other pointers for the socket buffer. + * Having this scratch space generic and programmable allows for + * more flexibility as the user is free to store whatever meta + * data they need. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_xdp_adjust_meta)(struct xdp_md *xdp_md, int delta) = (void *) 54; + +/* + * bpf_perf_event_read_value + * + * Read the value of a perf event counter, and store it into *buf* + * of size *buf_size*. This helper relies on a *map* of type + * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event + * counter is selected when *map* is updated with perf event file + * descriptors. The *map* is an array whose size is the number of + * available CPUs, and each cell contains a value relative to one + * CPU. The value to retrieve is indicated by *flags*, that + * contains the index of the CPU to look up, masked with + * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * This helper behaves in a way close to + * **bpf_perf_event_read**\ () helper, save that instead of + * just returning the value observed, it fills the *buf* + * structure. This allows for additional data to be retrieved: in + * particular, the enabled and running times (in *buf*\ + * **->enabled** and *buf*\ **->running**, respectively) are + * copied. In general, **bpf_perf_event_read_value**\ () is + * recommended over **bpf_perf_event_read**\ (), which has some + * ABI issues and provides fewer functionalities. + * + * These values are interesting, because hardware PMU (Performance + * Monitoring Unit) counters are limited resources. When there are + * more PMU based perf events opened than available counters, + * kernel will multiplex these events so each event gets certain + * percentage (but not all) of the PMU time. In case that + * multiplexing happens, the number of samples or counter value + * will not reflect the case compared to when no multiplexing + * occurs. This makes comparison between different runs difficult. + * Typically, the counter value should be normalized before + * comparing to other experiments. The usual normalization is done + * as follows. + * + * :: + * + * normalized_counter = counter * t_enabled / t_running + * + * Where t_enabled is the time enabled for event and t_running is + * the time running for event since last normalization. The + * enabled and running times are accumulated since the perf event + * open. To achieve scaling factor between two invocations of an + * eBPF program, users can can use CPU id as the key (which is + * typical for perf array usage model) to remember the previous + * value and do the calculation inside the eBPF program. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_perf_event_read_value)(void *map, __u64 flags, struct bpf_perf_event_value *buf, __u32 buf_size) = (void *) 55; + +/* + * bpf_perf_prog_read_value + * + * For en eBPF program attached to a perf event, retrieve the + * value of the event counter associated to *ctx* and store it in + * the structure pointed by *buf* and of size *buf_size*. Enabled + * and running times are also stored in the structure (see + * description of helper **bpf_perf_event_read_value**\ () for + * more details). + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_perf_prog_read_value)(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, __u32 buf_size) = (void *) 56; + +/* + * bpf_getsockopt + * + * Emulate a call to **getsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **getsockopt(2)** for more information. + * The retrieved value is stored in the structure pointed by + * *opval* and of length *optlen*. + * + * This helper actually implements a subset of **getsockopt()**. + * It supports the following *level*\ s: + * + * * **IPPROTO_TCP**, which supports *optname* + * **TCP_CONGESTION**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_getsockopt)(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) = (void *) 57; + +/* + * bpf_override_return + * + * Used for error injection, this helper uses kprobes to override + * the return value of the probed function, and to set it to *rc*. + * The first argument is the context *regs* on which the kprobe + * works. + * + * This helper works by setting setting the PC (program counter) + * to an override function which is run in place of the original + * probed function. This means the probed function is not run at + * all. The replacement function just returns with the required + * value. + * + * This helper has security implications, and thus is subject to + * restrictions. It is only available if the kernel was compiled + * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration + * option, and in this case it only works on functions tagged with + * **ALLOW_ERROR_INJECTION** in the kernel code. + * + * Also, the helper is only available for the architectures having + * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, + * x86 architecture is the only one to support this feature. + * + * Returns + * 0 + */ +static int (*bpf_override_return)(struct pt_regs *regs, __u64 rc) = (void *) 58; + +/* + * bpf_sock_ops_cb_flags_set + * + * Attempt to set the value of the **bpf_sock_ops_cb_flags** field + * for the full TCP socket associated to *bpf_sock_ops* to + * *argval*. + * + * The primary use of this field is to determine if there should + * be calls to eBPF programs of type + * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP + * code. A program of the same type can change its value, per + * connection and as necessary, when the connection is + * established. This field is directly accessible for reading, but + * this helper must be used for updates in order to return an + * error if an eBPF program tries to set a callback that is not + * supported in the current kernel. + * + * *argval* is a flag array which can combine these flags: + * + * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) + * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) + * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT) + * + * Therefore, this function can be used to clear a callback flag by + * setting the appropriate bit to zero. e.g. to disable the RTO + * callback: + * + * **bpf_sock_ops_cb_flags_set(bpf_sock,** + * **bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)** + * + * Here are some examples of where one could call such eBPF + * program: + * + * * When RTO fires. + * * When a packet is retransmitted. + * * When the connection terminates. + * * When a packet is sent. + * * When a packet is received. + * + * Returns + * Code **-EINVAL** if the socket is not a full TCP socket; + * otherwise, a positive number containing the bits that could not + * be set is returned (which comes down to 0 if all bits were set + * as required). + */ +static int (*bpf_sock_ops_cb_flags_set)(struct bpf_sock_ops *bpf_sock, int argval) = (void *) 59; + +/* + * bpf_msg_redirect_map + * + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * + * Returns + * **SK_PASS** on success, or **SK_DROP** on error. + */ +static int (*bpf_msg_redirect_map)(struct sk_msg_md *msg, void *map, __u32 key, __u64 flags) = (void *) 60; + +/* + * bpf_msg_apply_bytes + * + * For socket policies, apply the verdict of the eBPF program to + * the next *bytes* (number of bytes) of message *msg*. + * + * For example, this helper can be used in the following cases: + * + * * A single **sendmsg**\ () or **sendfile**\ () system call + * contains multiple logical messages that the eBPF program is + * supposed to read and for which it should apply a verdict. + * * An eBPF program only cares to read the first *bytes* of a + * *msg*. If the message has a large payload, then setting up + * and calling the eBPF program repeatedly for all bytes, even + * though the verdict is already known, would create unnecessary + * overhead. + * + * When called from within an eBPF program, the helper sets a + * counter internal to the BPF infrastructure, that is used to + * apply the last verdict to the next *bytes*. If *bytes* is + * smaller than the current data being processed from a + * **sendmsg**\ () or **sendfile**\ () system call, the first + * *bytes* will be sent and the eBPF program will be re-run with + * the pointer for start of data pointing to byte number *bytes* + * **+ 1**. If *bytes* is larger than the current data being + * processed, then the eBPF verdict will be applied to multiple + * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are + * consumed. + * + * Note that if a socket closes with the internal counter holding + * a non-zero value, this is not a problem because data is not + * being buffered for *bytes* and is sent as it is received. + * + * Returns + * 0 + */ +static int (*bpf_msg_apply_bytes)(struct sk_msg_md *msg, __u32 bytes) = (void *) 61; + +/* + * bpf_msg_cork_bytes + * + * For socket policies, prevent the execution of the verdict eBPF + * program for message *msg* until *bytes* (byte number) have been + * accumulated. + * + * This can be used when one needs a specific number of bytes + * before a verdict can be assigned, even if the data spans + * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme + * case would be a user calling **sendmsg**\ () repeatedly with + * 1-byte long message segments. Obviously, this is bad for + * performance, but it is still valid. If the eBPF program needs + * *bytes* bytes to validate a header, this helper can be used to + * prevent the eBPF program to be called again until *bytes* have + * been accumulated. + * + * Returns + * 0 + */ +static int (*bpf_msg_cork_bytes)(struct sk_msg_md *msg, __u32 bytes) = (void *) 62; + +/* + * bpf_msg_pull_data + * + * For socket policies, pull in non-linear data from user space + * for *msg* and set pointers *msg*\ **->data** and *msg*\ + * **->data_end** to *start* and *end* bytes offsets into *msg*, + * respectively. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it can only parse data that the (**data**, **data_end**) + * pointers have already consumed. For **sendmsg**\ () hooks this + * is likely the first scatterlist element. But for calls relying + * on the **sendpage** handler (e.g. **sendfile**\ ()) this will + * be the range (**0**, **0**) because the data is shared with + * user space and by default the objective is to avoid allowing + * user space to modify data while (or after) eBPF verdict is + * being decided. This helper can be used to pull in data and to + * set the start and end pointer to given values. Data will be + * copied if necessary (i.e. if data was not linear and if start + * and end pointers do not point to the same chunk). + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_msg_pull_data)(struct sk_msg_md *msg, __u32 start, __u32 end, __u64 flags) = (void *) 63; + +/* + * bpf_bind + * + * Bind the socket associated to *ctx* to the address pointed by + * *addr*, of length *addr_len*. This allows for making outgoing + * connection from the desired IP address, which can be useful for + * example when all processes inside a cgroup should use one + * single IP address on a host that has multiple IP configured. + * + * This helper works for IPv4 and IPv6, TCP and UDP sockets. The + * domain (*addr*\ **->sa_family**) must be **AF_INET** (or + * **AF_INET6**). Looking for a free port to bind to can be + * expensive, therefore binding to port is not permitted by the + * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively) + * must be set to zero. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_bind)(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) = (void *) 64; + +/* + * bpf_xdp_adjust_tail + * + * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is + * only possible to shrink the packet as of this writing, + * therefore *delta* must be a negative integer. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_xdp_adjust_tail)(struct xdp_md *xdp_md, int delta) = (void *) 65; + +/* + * bpf_skb_get_xfrm_state + * + * Retrieve the XFRM state (IP transform framework, see also + * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*. + * + * The retrieved value is stored in the **struct bpf_xfrm_state** + * pointed by *xfrm_state* and of length *size*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_XFRM** configuration option. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_get_xfrm_state)(struct __sk_buff *skb, __u32 index, struct bpf_xfrm_state *xfrm_state, __u32 size, __u64 flags) = (void *) 66; + +/* + * bpf_get_stack + * + * Return a user or a kernel stack in bpf program provided buffer. + * To achieve this, the helper needs *ctx*, which is a pointer + * to the context on which the tracing program is executed. + * To store the stacktrace, the bpf program provides *buf* with + * a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_USER_BUILD_ID** + * Collect buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **bpf_get_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * + * Returns + * A non-negative value equal to or less than *size* on success, + * or a negative error in case of failure. + */ +static int (*bpf_get_stack)(void *ctx, void *buf, __u32 size, __u64 flags) = (void *) 67; + +/* + * bpf_skb_load_bytes_relative + * + * This helper is similar to **bpf_skb_load_bytes**\ () in that + * it provides an easy way to load *len* bytes from *offset* + * from the packet associated to *skb*, into the buffer pointed + * by *to*. The difference to **bpf_skb_load_bytes**\ () is that + * a fifth argument *start_header* exists in order to select a + * base offset to start from. *start_header* can be one of: + * + * **BPF_HDR_START_MAC** + * Base offset to load data from is *skb*'s mac header. + * **BPF_HDR_START_NET** + * Base offset to load data from is *skb*'s network header. + * + * In general, "direct packet access" is the preferred method to + * access packet data, however, this helper is in particular useful + * in socket filters where *skb*\ **->data** does not always point + * to the start of the mac header and where "direct packet access" + * is not available. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_load_bytes_relative)(const void *skb, __u32 offset, void *to, __u32 len, __u32 start_header) = (void *) 68; + +/* + * bpf_fib_lookup + * + * Do FIB lookup in kernel tables using parameters in *params*. + * If lookup is successful and result shows packet is to be + * forwarded, the neighbor tables are searched for the nexthop. + * If successful (ie., FIB lookup shows forwarding and nexthop + * is resolved), the nexthop address is returned in ipv4_dst + * or ipv6_dst based on family, smac is set to mac address of + * egress device, dmac is set to nexthop mac address, rt_metric + * is set to metric from route (IPv4/IPv6 only), and ifindex + * is set to the device index of the nexthop from the FIB lookup. + * + * *plen* argument is the size of the passed in struct. + * *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_FIB_LOOKUP_DIRECT** + * Do a direct table lookup vs full lookup using FIB + * rules. + * **BPF_FIB_LOOKUP_OUTPUT** + * Perform lookup from an egress perspective (default is + * ingress). + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** tc cls_act programs. + * + * Returns + * * < 0 if any input argument is invalid + * * 0 on success (packet is forwarded, nexthop neighbor exists) + * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the + * packet is not forwarded or needs assist from full stack + */ +static int (*bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params, int plen, __u32 flags) = (void *) 69; + +/* + * bpf_sock_hash_update + * + * Add an entry to, or update a sockhash *map* referencing sockets. + * The *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_sock_hash_update)(struct bpf_sock_ops *skops, void *map, void *key, __u64 flags) = (void *) 70; + +/* + * bpf_msg_redirect_hash + * + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * + * Returns + * **SK_PASS** on success, or **SK_DROP** on error. + */ +static int (*bpf_msg_redirect_hash)(struct sk_msg_md *msg, void *map, void *key, __u64 flags) = (void *) 71; + +/* + * bpf_sk_redirect_hash + * + * This helper is used in programs implementing policies at the + * skb socket level. If the sk_buff *skb* is allowed to pass (i.e. + * if the verdeict eBPF program returns **SK_PASS**), redirect it + * to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress otherwise). This is the only flag supported for now. + * + * Returns + * **SK_PASS** on success, or **SK_DROP** on error. + */ +static int (*bpf_sk_redirect_hash)(struct __sk_buff *skb, void *map, void *key, __u64 flags) = (void *) 72; + +/* + * bpf_lwt_push_encap + * + * Encapsulate the packet associated to *skb* within a Layer 3 + * protocol header. This header is provided in the buffer at + * address *hdr*, with *len* its size in bytes. *type* indicates + * the protocol of the header and can be one of: + * + * **BPF_LWT_ENCAP_SEG6** + * IPv6 encapsulation with Segment Routing Header + * (**struct ipv6_sr_hdr**). *hdr* only contains the SRH, + * the IPv6 header is computed by the kernel. + * **BPF_LWT_ENCAP_SEG6_INLINE** + * Only works if *skb* contains an IPv6 packet. Insert a + * Segment Routing Header (**struct ipv6_sr_hdr**) inside + * the IPv6 header. + * **BPF_LWT_ENCAP_IP** + * IP encapsulation (GRE/GUE/IPIP/etc). The outer header + * must be IPv4 or IPv6, followed by zero or more + * additional headers, up to **LWT_BPF_MAX_HEADROOM** + * total bytes in all prepended headers. Please note that + * if **skb_is_gso**\ (*skb*) is true, no more than two + * headers can be prepended, and the inner header, if + * present, should be either GRE or UDP/GUE. + * + * **BPF_LWT_ENCAP_SEG6**\ \* types can be called by BPF programs + * of type **BPF_PROG_TYPE_LWT_IN**; **BPF_LWT_ENCAP_IP** type can + * be called by bpf programs of types **BPF_PROG_TYPE_LWT_IN** and + * **BPF_PROG_TYPE_LWT_XMIT**. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_lwt_push_encap)(struct __sk_buff *skb, __u32 type, void *hdr, __u32 len) = (void *) 73; + +/* + * bpf_lwt_seg6_store_bytes + * + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. Only the flags, tag and TLVs + * inside the outermost IPv6 Segment Routing Header can be + * modified through this helper. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_lwt_seg6_store_bytes)(struct __sk_buff *skb, __u32 offset, const void *from, __u32 len) = (void *) 74; + +/* + * bpf_lwt_seg6_adjust_srh + * + * Adjust the size allocated to TLVs in the outermost IPv6 + * Segment Routing Header contained in the packet associated to + * *skb*, at position *offset* by *delta* bytes. Only offsets + * after the segments are accepted. *delta* can be as well + * positive (growing) as negative (shrinking). + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_lwt_seg6_adjust_srh)(struct __sk_buff *skb, __u32 offset, __s32 delta) = (void *) 75; + +/* + * bpf_lwt_seg6_action + * + * Apply an IPv6 Segment Routing action of type *action* to the + * packet associated to *skb*. Each action takes a parameter + * contained at address *param*, and of length *param_len* bytes. + * *action* can be one of: + * + * **SEG6_LOCAL_ACTION_END_X** + * End.X action: Endpoint with Layer-3 cross-connect. + * Type of *param*: **struct in6_addr**. + * **SEG6_LOCAL_ACTION_END_T** + * End.T action: Endpoint with specific IPv6 table lookup. + * Type of *param*: **int**. + * **SEG6_LOCAL_ACTION_END_B6** + * End.B6 action: Endpoint bound to an SRv6 policy. + * Type of *param*: **struct ipv6_sr_hdr**. + * **SEG6_LOCAL_ACTION_END_B6_ENCAP** + * End.B6.Encap action: Endpoint bound to an SRv6 + * encapsulation policy. + * Type of *param*: **struct ipv6_sr_hdr**. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_lwt_seg6_action)(struct __sk_buff *skb, __u32 action, void *param, __u32 param_len) = (void *) 76; + +/* + * bpf_rc_repeat + * + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. + * + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Returns + * 0 + */ +static int (*bpf_rc_repeat)(void *ctx) = (void *) 77; + +/* + * bpf_rc_keydown + * + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown**\ () again with the same values, or calling + * **bpf_rc_repeat**\ (). + * + * Some protocols include a toggle bit, in case the button was + * released and pressed again between consecutive scancodes. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Returns + * 0 + */ +static int (*bpf_rc_keydown)(void *ctx, __u32 protocol, __u64 scancode, __u32 toggle) = (void *) 78; + +/* + * bpf_skb_cgroup_id + * + * Return the cgroup v2 id of the socket associated with the *skb*. + * This is roughly similar to the **bpf_get_cgroup_classid**\ () + * helper for cgroup v1 by providing a tag resp. identifier that + * can be matched on or used for map lookups e.g. to implement + * policy. The cgroup v2 id of a given path in the hierarchy is + * exposed in user space through the f_handle API in order to get + * to the same 64-bit id. + * + * This helper can be used on TC egress path, but not on ingress, + * and is available only if the kernel was compiled with the + * **CONFIG_SOCK_CGROUP_DATA** configuration option. + * + * Returns + * The id is returned or 0 in case the id could not be retrieved. + */ +static __u64 (*bpf_skb_cgroup_id)(struct __sk_buff *skb) = (void *) 79; + +/* + * bpf_get_current_cgroup_id + * + * + * Returns + * A 64-bit integer containing the current cgroup id based + * on the cgroup within which the current task is running. + */ +static __u64 (*bpf_get_current_cgroup_id)(void) = (void *) 80; + +/* + * bpf_get_local_storage + * + * Get the pointer to the local storage area. + * The type and the size of the local storage is defined + * by the *map* argument. + * The *flags* meaning is specific for each map type, + * and has to be 0 for cgroup local storage. + * + * Depending on the BPF program type, a local storage area + * can be shared between multiple instances of the BPF program, + * running simultaneously. + * + * A user should care about the synchronization by himself. + * For example, by using the **BPF_STX_XADD** instruction to alter + * the shared data. + * + * Returns + * A pointer to the local storage area. + */ +static void *(*bpf_get_local_storage)(void *map, __u64 flags) = (void *) 81; + +/* + * bpf_sk_select_reuseport + * + * Select a **SO_REUSEPORT** socket from a + * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*. + * It checks the selected socket is matching the incoming + * request in the socket buffer. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_sk_select_reuseport)(struct sk_reuseport_md *reuse, void *map, void *key, __u64 flags) = (void *) 82; + +/* + * bpf_skb_ancestor_cgroup_id + * + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *skb* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *skb*, then return value will be same as that + * of **bpf_skb_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *skb*. + * + * The format of returned id and helper limitations are same as in + * **bpf_skb_cgroup_id**\ (). + * + * Returns + * The id is returned or 0 in case the id could not be retrieved. + */ +static __u64 (*bpf_skb_ancestor_cgroup_id)(struct __sk_buff *skb, int ancestor_level) = (void *) 83; + +/* + * bpf_sk_lookup_tcp + * + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * + * Returns + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + */ +static struct bpf_sock *(*bpf_sk_lookup_tcp)(void *ctx, struct bpf_sock_tuple *tuple, __u32 tuple_size, __u64 netns, __u64 flags) = (void *) 84; + +/* + * bpf_sk_lookup_udp + * + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * + * Returns + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + */ +static struct bpf_sock *(*bpf_sk_lookup_udp)(void *ctx, struct bpf_sock_tuple *tuple, __u32 tuple_size, __u64 netns, __u64 flags) = (void *) 85; + +/* + * bpf_sk_release + * + * Release the reference held by *sock*. *sock* must be a + * non-**NULL** pointer that was returned from + * **bpf_sk_lookup_xxx**\ (). + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_sk_release)(struct bpf_sock *sock) = (void *) 86; + +/* + * bpf_map_push_elem + * + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is + * removed to make room for this. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_map_push_elem)(void *map, const void *value, __u64 flags) = (void *) 87; + +/* + * bpf_map_pop_elem + * + * Pop an element from *map*. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_map_pop_elem)(void *map, void *value) = (void *) 88; + +/* + * bpf_map_peek_elem + * + * Get an element from *map* without removing it. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_map_peek_elem)(void *map, void *value) = (void *) 89; + +/* + * bpf_msg_push_data + * + * For socket policies, insert *len* bytes into *msg* at offset + * *start*. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it may want to insert metadata or options into the *msg*. + * This can later be read and used by any of the lower layer BPF + * hooks. + * + * This helper may fail if under memory pressure (a malloc + * fails) in these cases BPF programs will get an appropriate + * error and BPF programs will need to handle them. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_msg_push_data)(struct sk_msg_md *msg, __u32 start, __u32 len, __u64 flags) = (void *) 90; + +/* + * bpf_msg_pop_data + * + * Will remove *len* bytes from a *msg* starting at byte *start*. + * This may result in **ENOMEM** errors under certain situations if + * an allocation and copy are required due to a full ring buffer. + * However, the helper will try to avoid doing the allocation + * if possible. Other errors can occur if input parameters are + * invalid either due to *start* byte not being valid part of *msg* + * payload and/or *pop* value being to large. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_msg_pop_data)(struct sk_msg_md *msg, __u32 start, __u32 len, __u64 flags) = (void *) 91; + +/* + * bpf_rc_pointer_rel + * + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded pointer movement. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Returns + * 0 + */ +static int (*bpf_rc_pointer_rel)(void *ctx, __s32 rel_x, __s32 rel_y) = (void *) 92; + +/* + * bpf_spin_lock + * + * Acquire a spinlock represented by the pointer *lock*, which is + * stored as part of a value of a map. Taking the lock allows to + * safely update the rest of the fields in that value. The + * spinlock can (and must) later be released with a call to + * **bpf_spin_unlock**\ (\ *lock*\ ). + * + * Spinlocks in BPF programs come with a number of restrictions + * and constraints: + * + * * **bpf_spin_lock** objects are only allowed inside maps of + * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this + * list could be extended in the future). + * * BTF description of the map is mandatory. + * * The BPF program can take ONE lock at a time, since taking two + * or more could cause dead locks. + * * Only one **struct bpf_spin_lock** is allowed per map element. + * * When the lock is taken, calls (either BPF to BPF or helpers) + * are not allowed. + * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not + * allowed inside a spinlock-ed region. + * * The BPF program MUST call **bpf_spin_unlock**\ () to release + * the lock, on all execution paths, before it returns. + * * The BPF program can access **struct bpf_spin_lock** only via + * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ () + * helpers. Loading or storing data into the **struct + * bpf_spin_lock** *lock*\ **;** field of a map is not allowed. + * * To use the **bpf_spin_lock**\ () helper, the BTF description + * of the map value must be a struct and have **struct + * bpf_spin_lock** *anyname*\ **;** field at the top level. + * Nested lock inside another struct is not allowed. + * * The **struct bpf_spin_lock** *lock* field in a map value must + * be aligned on a multiple of 4 bytes in that value. + * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy + * the **bpf_spin_lock** field to user space. + * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from + * a BPF program, do not update the **bpf_spin_lock** field. + * * **bpf_spin_lock** cannot be on the stack or inside a + * networking packet (it can only be inside of a map values). + * * **bpf_spin_lock** is available to root only. + * * Tracing programs and socket filter programs cannot use + * **bpf_spin_lock**\ () due to insufficient preemption checks + * (but this may change in the future). + * * **bpf_spin_lock** is not allowed in inner maps of map-in-map. + * + * Returns + * 0 + */ +static int (*bpf_spin_lock)(struct bpf_spin_lock *lock) = (void *) 93; + +/* + * bpf_spin_unlock + * + * Release the *lock* previously locked by a call to + * **bpf_spin_lock**\ (\ *lock*\ ). + * + * Returns + * 0 + */ +static int (*bpf_spin_unlock)(struct bpf_spin_lock *lock) = (void *) 94; + +/* + * bpf_sk_fullsock + * + * This helper gets a **struct bpf_sock** pointer such + * that all the fields in this **bpf_sock** can be accessed. + * + * Returns + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + */ +static struct bpf_sock *(*bpf_sk_fullsock)(struct bpf_sock *sk) = (void *) 95; + +/* + * bpf_tcp_sock + * + * This helper gets a **struct bpf_tcp_sock** pointer from a + * **struct bpf_sock** pointer. + * + * Returns + * A **struct bpf_tcp_sock** pointer on success, or **NULL** in + * case of failure. + */ +static struct bpf_tcp_sock *(*bpf_tcp_sock)(struct bpf_sock *sk) = (void *) 96; + +/* + * bpf_skb_ecn_set_ce + * + * Set ECN (Explicit Congestion Notification) field of IP header + * to **CE** (Congestion Encountered) if current value is **ECT** + * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6 + * and IPv4. + * + * Returns + * 1 if the **CE** flag is set (either by the current helper call + * or because it was already present), 0 if it is not set. + */ +static int (*bpf_skb_ecn_set_ce)(struct __sk_buff *skb) = (void *) 97; + +/* + * bpf_get_listener_sock + * + * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state. + * **bpf_sk_release**\ () is unnecessary and not allowed. + * + * Returns + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + */ +static struct bpf_sock *(*bpf_get_listener_sock)(struct bpf_sock *sk) = (void *) 98; + +/* + * bpf_skc_lookup_tcp + * + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * This function is identical to **bpf_sk_lookup_tcp**\ (), except + * that it also returns timewait or request sockets. Use + * **bpf_sk_fullsock**\ () or **bpf_tcp_sock**\ () to access the + * full structure. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * + * Returns + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + */ +static struct bpf_sock *(*bpf_skc_lookup_tcp)(void *ctx, struct bpf_sock_tuple *tuple, __u32 tuple_size, __u64 netns, __u64 flags) = (void *) 99; + +/* + * bpf_tcp_check_syncookie + * + * Check whether *iph* and *th* contain a valid SYN cookie ACK for + * the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains **sizeof**\ (**struct tcphdr**). + * + * + * Returns + * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative + * error otherwise. + */ +static int (*bpf_tcp_check_syncookie)(struct bpf_sock *sk, void *iph, __u32 iph_len, struct tcphdr *th, __u32 th_len) = (void *) 100; + +/* + * bpf_sysctl_get_name + * + * Get name of sysctl in /proc/sys/ and copy it into provided by + * program buffer *buf* of size *buf_len*. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * + * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is + * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name + * only (e.g. "tcp_mem"). + * + * Returns + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + */ +static int (*bpf_sysctl_get_name)(struct bpf_sysctl *ctx, char *buf, unsigned long buf_len, __u64 flags) = (void *) 101; + +/* + * bpf_sysctl_get_current_value + * + * Get current value of sysctl as it is presented in /proc/sys + * (incl. newline, etc), and copy it as a string into provided + * by program buffer *buf* of size *buf_len*. + * + * The whole value is copied, no matter what file position user + * space issued e.g. sys_read at. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * + * Returns + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if current value was unavailable, e.g. because + * sysctl is uninitialized and read returns -EIO for it. + */ +static int (*bpf_sysctl_get_current_value)(struct bpf_sysctl *ctx, char *buf, unsigned long buf_len) = (void *) 102; + +/* + * bpf_sysctl_get_new_value + * + * Get new value being written by user space to sysctl (before + * the actual write happens) and copy it as a string into + * provided by program buffer *buf* of size *buf_len*. + * + * User space may write new value at file position > 0. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * + * Returns + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if sysctl is being read. + */ +static int (*bpf_sysctl_get_new_value)(struct bpf_sysctl *ctx, char *buf, unsigned long buf_len) = (void *) 103; + +/* + * bpf_sysctl_set_new_value + * + * Override new value being written by user space to sysctl with + * value provided by program in buffer *buf* of size *buf_len*. + * + * *buf* should contain a string in same form as provided by user + * space on sysctl write. + * + * User space may write new value at file position > 0. To override + * the whole sysctl value file position should be set to zero. + * + * Returns + * 0 on success. + * + * **-E2BIG** if the *buf_len* is too big. + * + * **-EINVAL** if sysctl is being read. + */ +static int (*bpf_sysctl_set_new_value)(struct bpf_sysctl *ctx, const char *buf, unsigned long buf_len) = (void *) 104; + +/* + * bpf_strtol + * + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to a long integer according to the given base + * and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)) followed by a single + * optional '**-**' sign. + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtol**\ (3). + * + * Returns + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + */ +static int (*bpf_strtol)(const char *buf, unsigned long buf_len, __u64 flags, long *res) = (void *) 105; + +/* + * bpf_strtoul + * + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to an unsigned long integer according to the + * given base and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)). + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtoul**\ (3). + * + * Returns + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + */ +static int (*bpf_strtoul)(const char *buf, unsigned long buf_len, __u64 flags, unsigned long *res) = (void *) 106; + +/* + * bpf_sk_storage_get + * + * Get a bpf-local-storage from a *sk*. + * + * Logically, it could be thought of getting the value from + * a *map* with *sk* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *sk*) except this + * helper enforces the key must be a full socket and the map must + * be a **BPF_MAP_TYPE_SK_STORAGE** also. + * + * Underneath, the value is stored locally at *sk* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf-local-storages residing at *sk*. + * + * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf-local-storage will be + * created if one does not exist. *value* can be used + * together with **BPF_SK_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf-local-storage. If *value* is + * **NULL**, the new bpf-local-storage will be zero initialized. + * + * Returns + * A bpf-local-storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf-local-storage. + */ +static void *(*bpf_sk_storage_get)(void *map, struct bpf_sock *sk, void *value, __u64 flags) = (void *) 107; + +/* + * bpf_sk_storage_delete + * + * Delete a bpf-local-storage from a *sk*. + * + * Returns + * 0 on success. + * + * **-ENOENT** if the bpf-local-storage cannot be found. + */ +static int (*bpf_sk_storage_delete)(void *map, struct bpf_sock *sk) = (void *) 108; + +/* + * bpf_send_signal + * + * Send signal *sig* to the current task. + * + * Returns + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. + */ +static int (*bpf_send_signal)(__u32 sig) = (void *) 109; + +/* + * bpf_tcp_gen_syncookie + * + * Try to issue a SYN cookie for the packet with corresponding + * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header. + * + * + * Returns + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** SYN cookie cannot be issued due to error + * + * **-ENOENT** SYN cookie should not be issued (no SYN flood) + * + * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies + * + * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 + */ +static __s64 (*bpf_tcp_gen_syncookie)(struct bpf_sock *sk, void *iph, __u32 iph_len, struct tcphdr *th, __u32 th_len) = (void *) 110; + +/* + * bpf_skb_output + * + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct sk_buff. + * + * This helper is similar to **bpf_perf_event_output**\ () but + * restricted to raw_tracepoint bpf programs. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_skb_output)(void *ctx, void *map, __u64 flags, void *data, __u64 size) = (void *) 111; + +/* + * bpf_probe_read_user + * + * Safely attempt to read *size* bytes from user space address + * *unsafe_ptr* and store the data in *dst*. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_probe_read_user)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 112; + +/* + * bpf_probe_read_kernel + * + * Safely attempt to read *size* bytes from kernel space address + * *unsafe_ptr* and store the data in *dst*. + * + * Returns + * 0 on success, or a negative error in case of failure. + */ +static int (*bpf_probe_read_kernel)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 113; + +/* + * bpf_probe_read_user_str + * + * Copy a NUL terminated string from an unsafe user address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, the length of the copied string is returned. This + * makes this helper useful in tracing programs for reading + * strings, and more importantly to get its length at runtime. See + * the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_user_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read_user()** helper here + * instead to read the string would require to estimate the length + * at compile time, and would often result in copying more memory + * than necessary. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * + * Returns + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + */ +static int (*bpf_probe_read_user_str)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 114; + +/* + * bpf_probe_read_kernel_str + * + * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr* + * to *dst*. Same semantics as with bpf_probe_read_user_str() apply. + * + * Returns + * On success, the strictly positive length of the string, including + * the trailing NUL character. On error, a negative value. + */ +static int (*bpf_probe_read_kernel_str)(void *dst, __u32 size, const void *unsafe_ptr) = (void *) 115; + + diff --git a/src/contrib/libbpf/bpf/bpf_helpers.h b/src/contrib/libbpf/bpf/bpf_helpers.h new file mode 100644 index 0000000..0c7d282 --- /dev/null +++ b/src/contrib/libbpf/bpf/bpf_helpers.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_HELPERS__ +#define __BPF_HELPERS__ + +#include "bpf_helper_defs.h" + +#define __uint(name, val) int (*name)[val] +#define __type(name, val) typeof(val) *name + +/* Helper macro to print out debug messages */ +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +/* + * Helper macro to place programs, maps, license in + * different sections in elf_bpf file. Section names + * are interpreted by elf_bpf loader + */ +#define SEC(NAME) __attribute__((section(NAME), used)) + +#ifndef __always_inline +#define __always_inline __attribute__((always_inline)) +#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; +}; + +enum libbpf_pin_type { + LIBBPF_PIN_NONE, + /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ + LIBBPF_PIN_BY_NAME, +}; + +#endif diff --git a/src/contrib/libbpf/bpf/bpf_prog_linfo.c b/src/contrib/libbpf/bpf/bpf_prog_linfo.c new file mode 100644 index 0000000..3ed1a27 --- /dev/null +++ b/src/contrib/libbpf/bpf/bpf_prog_linfo.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2018 Facebook */ + +#include <string.h> +#include <stdlib.h> +#include <linux/err.h> +#include <linux/bpf.h> +#include "libbpf.h" +#include "libbpf_internal.h" + +struct bpf_prog_linfo { + void *raw_linfo; + void *raw_jited_linfo; + __u32 *nr_jited_linfo_per_func; + __u32 *jited_linfo_func_idx; + __u32 nr_linfo; + __u32 nr_jited_func; + __u32 rec_size; + __u32 jited_rec_size; +}; + +static int dissect_jited_func(struct bpf_prog_linfo *prog_linfo, + const __u64 *ksym_func, const __u32 *ksym_len) +{ + __u32 nr_jited_func, nr_linfo; + const void *raw_jited_linfo; + const __u64 *jited_linfo; + __u64 last_jited_linfo; + /* + * Index to raw_jited_linfo: + * i: Index for searching the next ksym_func + * prev_i: Index to the last found ksym_func + */ + __u32 i, prev_i; + __u32 f; /* Index to ksym_func */ + + raw_jited_linfo = prog_linfo->raw_jited_linfo; + jited_linfo = raw_jited_linfo; + if (ksym_func[0] != *jited_linfo) + goto errout; + + prog_linfo->jited_linfo_func_idx[0] = 0; + nr_jited_func = prog_linfo->nr_jited_func; + nr_linfo = prog_linfo->nr_linfo; + + for (prev_i = 0, i = 1, f = 1; + i < nr_linfo && f < nr_jited_func; + i++) { + raw_jited_linfo += prog_linfo->jited_rec_size; + last_jited_linfo = *jited_linfo; + jited_linfo = raw_jited_linfo; + + if (ksym_func[f] == *jited_linfo) { + prog_linfo->jited_linfo_func_idx[f] = i; + + /* Sanity check */ + if (last_jited_linfo - ksym_func[f - 1] + 1 > + ksym_len[f - 1]) + goto errout; + + prog_linfo->nr_jited_linfo_per_func[f - 1] = + i - prev_i; + prev_i = i; + + /* + * The ksym_func[f] is found in jited_linfo. + * Look for the next one. + */ + f++; + } else if (*jited_linfo <= last_jited_linfo) { + /* Ensure the addr is increasing _within_ a func */ + goto errout; + } + } + + if (f != nr_jited_func) + goto errout; + + prog_linfo->nr_jited_linfo_per_func[nr_jited_func - 1] = + nr_linfo - prev_i; + + return 0; + +errout: + return -EINVAL; +} + +void bpf_prog_linfo__free(struct bpf_prog_linfo *prog_linfo) +{ + if (!prog_linfo) + return; + + free(prog_linfo->raw_linfo); + free(prog_linfo->raw_jited_linfo); + free(prog_linfo->nr_jited_linfo_per_func); + free(prog_linfo->jited_linfo_func_idx); + free(prog_linfo); +} + +struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info) +{ + struct bpf_prog_linfo *prog_linfo; + __u32 nr_linfo, nr_jited_func; + __u64 data_sz; + + nr_linfo = info->nr_line_info; + + if (!nr_linfo) + return NULL; + + /* + * The min size that bpf_prog_linfo has to access for + * searching purpose. + */ + if (info->line_info_rec_size < + offsetof(struct bpf_line_info, file_name_off)) + return NULL; + + prog_linfo = calloc(1, sizeof(*prog_linfo)); + if (!prog_linfo) + return NULL; + + /* Copy xlated line_info */ + prog_linfo->nr_linfo = nr_linfo; + prog_linfo->rec_size = info->line_info_rec_size; + data_sz = (__u64)nr_linfo * prog_linfo->rec_size; + prog_linfo->raw_linfo = malloc(data_sz); + if (!prog_linfo->raw_linfo) + goto err_free; + memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info, data_sz); + + nr_jited_func = info->nr_jited_ksyms; + if (!nr_jited_func || + !info->jited_line_info || + info->nr_jited_line_info != nr_linfo || + info->jited_line_info_rec_size < sizeof(__u64) || + info->nr_jited_func_lens != nr_jited_func || + !info->jited_ksyms || + !info->jited_func_lens) + /* Not enough info to provide jited_line_info */ + return prog_linfo; + + /* Copy jited_line_info */ + prog_linfo->nr_jited_func = nr_jited_func; + prog_linfo->jited_rec_size = info->jited_line_info_rec_size; + data_sz = (__u64)nr_linfo * prog_linfo->jited_rec_size; + prog_linfo->raw_jited_linfo = malloc(data_sz); + if (!prog_linfo->raw_jited_linfo) + goto err_free; + memcpy(prog_linfo->raw_jited_linfo, + (void *)(long)info->jited_line_info, data_sz); + + /* Number of jited_line_info per jited func */ + prog_linfo->nr_jited_linfo_per_func = malloc(nr_jited_func * + sizeof(__u32)); + if (!prog_linfo->nr_jited_linfo_per_func) + goto err_free; + + /* + * For each jited func, + * the start idx to the "linfo" and "jited_linfo" array, + */ + prog_linfo->jited_linfo_func_idx = malloc(nr_jited_func * + sizeof(__u32)); + if (!prog_linfo->jited_linfo_func_idx) + goto err_free; + + if (dissect_jited_func(prog_linfo, + (__u64 *)(long)info->jited_ksyms, + (__u32 *)(long)info->jited_func_lens)) + goto err_free; + + return prog_linfo; + +err_free: + bpf_prog_linfo__free(prog_linfo); + return NULL; +} + +const struct bpf_line_info * +bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo, + __u64 addr, __u32 func_idx, __u32 nr_skip) +{ + __u32 jited_rec_size, rec_size, nr_linfo, start, i; + const void *raw_jited_linfo, *raw_linfo; + const __u64 *jited_linfo; + + if (func_idx >= prog_linfo->nr_jited_func) + return NULL; + + nr_linfo = prog_linfo->nr_jited_linfo_per_func[func_idx]; + if (nr_skip >= nr_linfo) + return NULL; + + start = prog_linfo->jited_linfo_func_idx[func_idx] + nr_skip; + jited_rec_size = prog_linfo->jited_rec_size; + raw_jited_linfo = prog_linfo->raw_jited_linfo + + (start * jited_rec_size); + jited_linfo = raw_jited_linfo; + if (addr < *jited_linfo) + return NULL; + + nr_linfo -= nr_skip; + rec_size = prog_linfo->rec_size; + raw_linfo = prog_linfo->raw_linfo + (start * rec_size); + for (i = 0; i < nr_linfo; i++) { + if (addr < *jited_linfo) + break; + + raw_linfo += rec_size; + raw_jited_linfo += jited_rec_size; + jited_linfo = raw_jited_linfo; + } + + return raw_linfo - rec_size; +} + +const struct bpf_line_info * +bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo, + __u32 insn_off, __u32 nr_skip) +{ + const struct bpf_line_info *linfo; + __u32 rec_size, nr_linfo, i; + const void *raw_linfo; + + nr_linfo = prog_linfo->nr_linfo; + if (nr_skip >= nr_linfo) + return NULL; + + rec_size = prog_linfo->rec_size; + raw_linfo = prog_linfo->raw_linfo + (nr_skip * rec_size); + linfo = raw_linfo; + if (insn_off < linfo->insn_off) + return NULL; + + nr_linfo -= nr_skip; + for (i = 0; i < nr_linfo; i++) { + if (insn_off < linfo->insn_off) + break; + + raw_linfo += rec_size; + linfo = raw_linfo; + } + + return raw_linfo - rec_size; +} diff --git a/src/contrib/libbpf/bpf/bpf_tracing.h b/src/contrib/libbpf/bpf/bpf_tracing.h new file mode 100644 index 0000000..b0dafe8 --- /dev/null +++ b/src/contrib/libbpf/bpf/bpf_tracing.h @@ -0,0 +1,195 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_TRACING_H__ +#define __BPF_TRACING_H__ + +/* Scan the ARCH passed in from ARCH env variable (see Makefile) */ +#if defined(__TARGET_ARCH_x86) + #define bpf_target_x86 + #define bpf_target_defined +#elif defined(__TARGET_ARCH_s390) + #define bpf_target_s390 + #define bpf_target_defined +#elif defined(__TARGET_ARCH_arm) + #define bpf_target_arm + #define bpf_target_defined +#elif defined(__TARGET_ARCH_arm64) + #define bpf_target_arm64 + #define bpf_target_defined +#elif defined(__TARGET_ARCH_mips) + #define bpf_target_mips + #define bpf_target_defined +#elif defined(__TARGET_ARCH_powerpc) + #define bpf_target_powerpc + #define bpf_target_defined +#elif defined(__TARGET_ARCH_sparc) + #define bpf_target_sparc + #define bpf_target_defined +#else + #undef bpf_target_defined +#endif + +/* Fall back to what the compiler says */ +#ifndef bpf_target_defined +#if defined(__x86_64__) + #define bpf_target_x86 +#elif defined(__s390__) + #define bpf_target_s390 +#elif defined(__arm__) + #define bpf_target_arm +#elif defined(__aarch64__) + #define bpf_target_arm64 +#elif defined(__mips__) + #define bpf_target_mips +#elif defined(__powerpc__) + #define bpf_target_powerpc +#elif defined(__sparc__) + #define bpf_target_sparc +#endif +#endif + +#if defined(bpf_target_x86) + +#ifdef __KERNEL__ +#define PT_REGS_PARM1(x) ((x)->di) +#define PT_REGS_PARM2(x) ((x)->si) +#define PT_REGS_PARM3(x) ((x)->dx) +#define PT_REGS_PARM4(x) ((x)->cx) +#define PT_REGS_PARM5(x) ((x)->r8) +#define PT_REGS_RET(x) ((x)->sp) +#define PT_REGS_FP(x) ((x)->bp) +#define PT_REGS_RC(x) ((x)->ax) +#define PT_REGS_SP(x) ((x)->sp) +#define PT_REGS_IP(x) ((x)->ip) +#else +#ifdef __i386__ +/* i386 kernel is built with -mregparm=3 */ +#define PT_REGS_PARM1(x) ((x)->eax) +#define PT_REGS_PARM2(x) ((x)->edx) +#define PT_REGS_PARM3(x) ((x)->ecx) +#define PT_REGS_PARM4(x) 0 +#define PT_REGS_PARM5(x) 0 +#define PT_REGS_RET(x) ((x)->esp) +#define PT_REGS_FP(x) ((x)->ebp) +#define PT_REGS_RC(x) ((x)->eax) +#define PT_REGS_SP(x) ((x)->esp) +#define PT_REGS_IP(x) ((x)->eip) +#else +#define PT_REGS_PARM1(x) ((x)->rdi) +#define PT_REGS_PARM2(x) ((x)->rsi) +#define PT_REGS_PARM3(x) ((x)->rdx) +#define PT_REGS_PARM4(x) ((x)->rcx) +#define PT_REGS_PARM5(x) ((x)->r8) +#define PT_REGS_RET(x) ((x)->rsp) +#define PT_REGS_FP(x) ((x)->rbp) +#define PT_REGS_RC(x) ((x)->rax) +#define PT_REGS_SP(x) ((x)->rsp) +#define PT_REGS_IP(x) ((x)->rip) +#endif +#endif + +#elif defined(bpf_target_s390) + +/* s390 provides user_pt_regs instead of struct pt_regs to userspace */ +struct pt_regs; +#define PT_REGS_S390 const volatile user_pt_regs +#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2]) +#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3]) +#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4]) +#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5]) +#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6]) +#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14]) +/* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11]) +#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2]) +#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15]) +#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr) + +#elif defined(bpf_target_arm) + +#define PT_REGS_PARM1(x) ((x)->uregs[0]) +#define PT_REGS_PARM2(x) ((x)->uregs[1]) +#define PT_REGS_PARM3(x) ((x)->uregs[2]) +#define PT_REGS_PARM4(x) ((x)->uregs[3]) +#define PT_REGS_PARM5(x) ((x)->uregs[4]) +#define PT_REGS_RET(x) ((x)->uregs[14]) +#define PT_REGS_FP(x) ((x)->uregs[11]) /* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_RC(x) ((x)->uregs[0]) +#define PT_REGS_SP(x) ((x)->uregs[13]) +#define PT_REGS_IP(x) ((x)->uregs[12]) + +#elif defined(bpf_target_arm64) + +/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ +struct pt_regs; +#define PT_REGS_ARM64 const volatile struct user_pt_regs +#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0]) +#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1]) +#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2]) +#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3]) +#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4]) +#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30]) +/* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29]) +#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0]) +#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp) +#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc) + +#elif defined(bpf_target_mips) + +#define PT_REGS_PARM1(x) ((x)->regs[4]) +#define PT_REGS_PARM2(x) ((x)->regs[5]) +#define PT_REGS_PARM3(x) ((x)->regs[6]) +#define PT_REGS_PARM4(x) ((x)->regs[7]) +#define PT_REGS_PARM5(x) ((x)->regs[8]) +#define PT_REGS_RET(x) ((x)->regs[31]) +#define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_RC(x) ((x)->regs[1]) +#define PT_REGS_SP(x) ((x)->regs[29]) +#define PT_REGS_IP(x) ((x)->cp0_epc) + +#elif defined(bpf_target_powerpc) + +#define PT_REGS_PARM1(x) ((x)->gpr[3]) +#define PT_REGS_PARM2(x) ((x)->gpr[4]) +#define PT_REGS_PARM3(x) ((x)->gpr[5]) +#define PT_REGS_PARM4(x) ((x)->gpr[6]) +#define PT_REGS_PARM5(x) ((x)->gpr[7]) +#define PT_REGS_RC(x) ((x)->gpr[3]) +#define PT_REGS_SP(x) ((x)->sp) +#define PT_REGS_IP(x) ((x)->nip) + +#elif defined(bpf_target_sparc) + +#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0]) +#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1]) +#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2]) +#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3]) +#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4]) +#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7]) +#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0]) +#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP]) + +/* Should this also be a bpf_target check for the sparc case? */ +#if defined(__arch64__) +#define PT_REGS_IP(x) ((x)->tpc) +#else +#define PT_REGS_IP(x) ((x)->pc) +#endif + +#endif + +#if defined(bpf_target_powerpc) +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) +#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP +#elif defined(bpf_target_sparc) +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) +#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP +#else +#define BPF_KPROBE_READ_RET_IP(ip, ctx) \ + ({ bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); }) +#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) \ + ({ bpf_probe_read(&(ip), sizeof(ip), \ + (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) +#endif + +#endif diff --git a/src/contrib/libbpf/bpf/btf.c b/src/contrib/libbpf/bpf/btf.c new file mode 100644 index 0000000..88efa2b --- /dev/null +++ b/src/contrib/libbpf/bpf/btf.c @@ -0,0 +1,2884 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2018 Facebook */ + +#include <endian.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <fcntl.h> +#include <unistd.h> +#include <errno.h> +#include <linux/err.h> +#include <linux/btf.h> +#include <gelf.h> +#include "btf.h" +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" +#include "hashmap.h" + +#define BTF_MAX_NR_TYPES 0x7fffffff +#define BTF_MAX_STR_OFFSET 0x7fffffff + +static struct btf_type btf_void; + +struct btf { + union { + struct btf_header *hdr; + void *data; + }; + struct btf_type **types; + const char *strings; + void *nohdr_data; + __u32 nr_types; + __u32 types_size; + __u32 data_size; + int fd; +}; + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64) (unsigned long) ptr; +} + +static int btf_add_type(struct btf *btf, struct btf_type *t) +{ + if (btf->types_size - btf->nr_types < 2) { + struct btf_type **new_types; + __u32 expand_by, new_size; + + if (btf->types_size == BTF_MAX_NR_TYPES) + return -E2BIG; + + expand_by = max(btf->types_size >> 2, 16); + new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by); + + new_types = realloc(btf->types, sizeof(*new_types) * new_size); + if (!new_types) + return -ENOMEM; + + if (btf->nr_types == 0) + new_types[0] = &btf_void; + + btf->types = new_types; + btf->types_size = new_size; + } + + btf->types[++(btf->nr_types)] = t; + + return 0; +} + +static int btf_parse_hdr(struct btf *btf) +{ + const struct btf_header *hdr = btf->hdr; + __u32 meta_left; + + if (btf->data_size < sizeof(struct btf_header)) { + pr_debug("BTF header not found\n"); + return -EINVAL; + } + + if (hdr->magic != BTF_MAGIC) { + pr_debug("Invalid BTF magic:%x\n", hdr->magic); + return -EINVAL; + } + + if (hdr->version != BTF_VERSION) { + pr_debug("Unsupported BTF version:%u\n", hdr->version); + return -ENOTSUP; + } + + if (hdr->flags) { + pr_debug("Unsupported BTF flags:%x\n", hdr->flags); + return -ENOTSUP; + } + + meta_left = btf->data_size - sizeof(*hdr); + if (!meta_left) { + pr_debug("BTF has no data\n"); + return -EINVAL; + } + + if (meta_left < hdr->type_off) { + pr_debug("Invalid BTF type section offset:%u\n", hdr->type_off); + return -EINVAL; + } + + if (meta_left < hdr->str_off) { + pr_debug("Invalid BTF string section offset:%u\n", hdr->str_off); + return -EINVAL; + } + + if (hdr->type_off >= hdr->str_off) { + pr_debug("BTF type section offset >= string section offset. No type?\n"); + return -EINVAL; + } + + if (hdr->type_off & 0x02) { + pr_debug("BTF type section is not aligned to 4 bytes\n"); + return -EINVAL; + } + + btf->nohdr_data = btf->hdr + 1; + + return 0; +} + +static int btf_parse_str_sec(struct btf *btf) +{ + const struct btf_header *hdr = btf->hdr; + const char *start = btf->nohdr_data + hdr->str_off; + const char *end = start + btf->hdr->str_len; + + if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_STR_OFFSET || + start[0] || end[-1]) { + pr_debug("Invalid BTF string section\n"); + return -EINVAL; + } + + btf->strings = start; + + return 0; +} + +static int btf_type_size(struct btf_type *t) +{ + int base_size = sizeof(struct btf_type); + __u16 vlen = btf_vlen(t); + + switch (btf_kind(t)) { + case BTF_KIND_FWD: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + return base_size; + case BTF_KIND_INT: + return base_size + sizeof(__u32); + case BTF_KIND_ENUM: + return base_size + vlen * sizeof(struct btf_enum); + case BTF_KIND_ARRAY: + return base_size + sizeof(struct btf_array); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + return base_size + vlen * sizeof(struct btf_member); + case BTF_KIND_FUNC_PROTO: + return base_size + vlen * sizeof(struct btf_param); + case BTF_KIND_VAR: + return base_size + sizeof(struct btf_var); + case BTF_KIND_DATASEC: + return base_size + vlen * sizeof(struct btf_var_secinfo); + default: + pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); + return -EINVAL; + } +} + +static int btf_parse_type_sec(struct btf *btf) +{ + struct btf_header *hdr = btf->hdr; + void *nohdr_data = btf->nohdr_data; + void *next_type = nohdr_data + hdr->type_off; + void *end_type = nohdr_data + hdr->str_off; + + while (next_type < end_type) { + struct btf_type *t = next_type; + int type_size; + int err; + + type_size = btf_type_size(t); + if (type_size < 0) + return type_size; + next_type += type_size; + err = btf_add_type(btf, t); + if (err) + return err; + } + + return 0; +} + +__u32 btf__get_nr_types(const struct btf *btf) +{ + return btf->nr_types; +} + +const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) +{ + if (type_id > btf->nr_types) + return NULL; + + return btf->types[type_id]; +} + +static bool btf_type_is_void(const struct btf_type *t) +{ + return t == &btf_void || btf_is_fwd(t); +} + +static bool btf_type_is_void_or_null(const struct btf_type *t) +{ + return !t || btf_type_is_void(t); +} + +#define MAX_RESOLVE_DEPTH 32 + +__s64 btf__resolve_size(const struct btf *btf, __u32 type_id) +{ + const struct btf_array *array; + const struct btf_type *t; + __u32 nelems = 1; + __s64 size = -1; + int i; + + t = btf__type_by_id(btf, type_id); + for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); + i++) { + switch (btf_kind(t)) { + case BTF_KIND_INT: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + case BTF_KIND_DATASEC: + size = t->size; + goto done; + case BTF_KIND_PTR: + size = sizeof(void *); + goto done; + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_VAR: + type_id = t->type; + break; + case BTF_KIND_ARRAY: + array = btf_array(t); + if (nelems && array->nelems > UINT32_MAX / nelems) + return -E2BIG; + nelems *= array->nelems; + type_id = array->type; + break; + default: + return -EINVAL; + } + + t = btf__type_by_id(btf, type_id); + } + +done: + if (size < 0) + return -EINVAL; + if (nelems && size > UINT32_MAX / nelems) + return -E2BIG; + + return nelems * size; +} + +int btf__resolve_type(const struct btf *btf, __u32 type_id) +{ + const struct btf_type *t; + int depth = 0; + + t = btf__type_by_id(btf, type_id); + while (depth < MAX_RESOLVE_DEPTH && + !btf_type_is_void_or_null(t) && + (btf_is_mod(t) || btf_is_typedef(t) || btf_is_var(t))) { + type_id = t->type; + t = btf__type_by_id(btf, type_id); + depth++; + } + + if (depth == MAX_RESOLVE_DEPTH || btf_type_is_void_or_null(t)) + return -EINVAL; + + return type_id; +} + +__s32 btf__find_by_name(const struct btf *btf, const char *type_name) +{ + __u32 i; + + if (!strcmp(type_name, "void")) + return 0; + + for (i = 1; i <= btf->nr_types; i++) { + const struct btf_type *t = btf->types[i]; + const char *name = btf__name_by_offset(btf, t->name_off); + + if (name && !strcmp(type_name, name)) + return i; + } + + return -ENOENT; +} + +__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, + __u32 kind) +{ + __u32 i; + + if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void")) + return 0; + + for (i = 1; i <= btf->nr_types; i++) { + const struct btf_type *t = btf->types[i]; + const char *name; + + if (btf_kind(t) != kind) + continue; + name = btf__name_by_offset(btf, t->name_off); + if (name && !strcmp(type_name, name)) + return i; + } + + return -ENOENT; +} + +void btf__free(struct btf *btf) +{ + if (!btf) + return; + + if (btf->fd != -1) + close(btf->fd); + + free(btf->data); + free(btf->types); + free(btf); +} + +struct btf *btf__new(__u8 *data, __u32 size) +{ + struct btf *btf; + int err; + + btf = calloc(1, sizeof(struct btf)); + if (!btf) + return ERR_PTR(-ENOMEM); + + btf->fd = -1; + + btf->data = malloc(size); + if (!btf->data) { + err = -ENOMEM; + goto done; + } + + memcpy(btf->data, data, size); + btf->data_size = size; + + err = btf_parse_hdr(btf); + if (err) + goto done; + + err = btf_parse_str_sec(btf); + if (err) + goto done; + + err = btf_parse_type_sec(btf); + +done: + if (err) { + btf__free(btf); + return ERR_PTR(err); + } + + return btf; +} + +static bool btf_check_endianness(const GElf_Ehdr *ehdr) +{ +#if __BYTE_ORDER == __LITTLE_ENDIAN + return ehdr->e_ident[EI_DATA] == ELFDATA2LSB; +#elif __BYTE_ORDER == __BIG_ENDIAN + return ehdr->e_ident[EI_DATA] == ELFDATA2MSB; +#else +# error "Unrecognized __BYTE_ORDER__" +#endif +} + +struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) +{ + Elf_Data *btf_data = NULL, *btf_ext_data = NULL; + int err = 0, fd = -1, idx = 0; + struct btf *btf = NULL; + Elf_Scn *scn = NULL; + Elf *elf = NULL; + GElf_Ehdr ehdr; + + if (elf_version(EV_CURRENT) == EV_NONE) { + pr_warn("failed to init libelf for %s\n", path); + return ERR_PTR(-LIBBPF_ERRNO__LIBELF); + } + + fd = open(path, O_RDONLY); + if (fd < 0) { + err = -errno; + pr_warn("failed to open %s: %s\n", path, strerror(errno)); + return ERR_PTR(err); + } + + err = -LIBBPF_ERRNO__FORMAT; + + elf = elf_begin(fd, ELF_C_READ, NULL); + if (!elf) { + pr_warn("failed to open %s as ELF file\n", path); + goto done; + } + if (!gelf_getehdr(elf, &ehdr)) { + pr_warn("failed to get EHDR from %s\n", path); + goto done; + } + if (!btf_check_endianness(&ehdr)) { + pr_warn("non-native ELF endianness is not supported\n"); + goto done; + } + if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) { + pr_warn("failed to get e_shstrndx from %s\n", path); + goto done; + } + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + GElf_Shdr sh; + char *name; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + pr_warn("failed to get section(%d) header from %s\n", + idx, path); + goto done; + } + name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name); + if (!name) { + pr_warn("failed to get section(%d) name from %s\n", + idx, path); + goto done; + } + if (strcmp(name, BTF_ELF_SEC) == 0) { + btf_data = elf_getdata(scn, 0); + if (!btf_data) { + pr_warn("failed to get section(%d, %s) data from %s\n", + idx, name, path); + goto done; + } + continue; + } else if (btf_ext && strcmp(name, BTF_EXT_ELF_SEC) == 0) { + btf_ext_data = elf_getdata(scn, 0); + if (!btf_ext_data) { + pr_warn("failed to get section(%d, %s) data from %s\n", + idx, name, path); + goto done; + } + continue; + } + } + + err = 0; + + if (!btf_data) { + err = -ENOENT; + goto done; + } + btf = btf__new(btf_data->d_buf, btf_data->d_size); + if (IS_ERR(btf)) + goto done; + + if (btf_ext && btf_ext_data) { + *btf_ext = btf_ext__new(btf_ext_data->d_buf, + btf_ext_data->d_size); + if (IS_ERR(*btf_ext)) + goto done; + } else if (btf_ext) { + *btf_ext = NULL; + } +done: + if (elf) + elf_end(elf); + close(fd); + + if (err) + return ERR_PTR(err); + /* + * btf is always parsed before btf_ext, so no need to clean up + * btf_ext, if btf loading failed + */ + if (IS_ERR(btf)) + return btf; + if (btf_ext && IS_ERR(*btf_ext)) { + btf__free(btf); + err = PTR_ERR(*btf_ext); + return ERR_PTR(err); + } + return btf; +} + +static int compare_vsi_off(const void *_a, const void *_b) +{ + const struct btf_var_secinfo *a = _a; + const struct btf_var_secinfo *b = _b; + + return a->offset - b->offset; +} + +static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, + struct btf_type *t) +{ + __u32 size = 0, off = 0, i, vars = btf_vlen(t); + const char *name = btf__name_by_offset(btf, t->name_off); + const struct btf_type *t_var; + struct btf_var_secinfo *vsi; + const struct btf_var *var; + int ret; + + if (!name) { + pr_debug("No name found in string section for DATASEC kind.\n"); + return -ENOENT; + } + + ret = bpf_object__section_size(obj, name, &size); + if (ret || !size || (t->size && t->size != size)) { + pr_debug("Invalid size for section %s: %u bytes\n", name, size); + return -ENOENT; + } + + t->size = size; + + for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) { + t_var = btf__type_by_id(btf, vsi->type); + var = btf_var(t_var); + + if (!btf_is_var(t_var)) { + pr_debug("Non-VAR type seen in section %s\n", name); + return -EINVAL; + } + + if (var->linkage == BTF_VAR_STATIC) + continue; + + name = btf__name_by_offset(btf, t_var->name_off); + if (!name) { + pr_debug("No name found in string section for VAR kind\n"); + return -ENOENT; + } + + ret = bpf_object__variable_offset(obj, name, &off); + if (ret) { + pr_debug("No offset found in symbol table for VAR %s\n", + name); + return -ENOENT; + } + + vsi->offset = off; + } + + qsort(t + 1, vars, sizeof(*vsi), compare_vsi_off); + return 0; +} + +int btf__finalize_data(struct bpf_object *obj, struct btf *btf) +{ + int err = 0; + __u32 i; + + for (i = 1; i <= btf->nr_types; i++) { + struct btf_type *t = btf->types[i]; + + /* Loader needs to fix up some of the things compiler + * couldn't get its hands on while emitting BTF. This + * is section size and global variable offset. We use + * the info from the ELF itself for this purpose. + */ + if (btf_is_datasec(t)) { + err = btf_fixup_datasec(obj, btf, t); + if (err) + break; + } + } + + return err; +} + +int btf__load(struct btf *btf) +{ + __u32 log_buf_size = BPF_LOG_BUF_SIZE; + char *log_buf = NULL; + int err = 0; + + if (btf->fd >= 0) + return -EEXIST; + + log_buf = malloc(log_buf_size); + if (!log_buf) + return -ENOMEM; + + *log_buf = 0; + + btf->fd = bpf_load_btf(btf->data, btf->data_size, + log_buf, log_buf_size, false); + if (btf->fd < 0) { + err = -errno; + pr_warn("Error loading BTF: %s(%d)\n", strerror(errno), errno); + if (*log_buf) + pr_warn("%s\n", log_buf); + goto done; + } + +done: + free(log_buf); + return err; +} + +int btf__fd(const struct btf *btf) +{ + return btf->fd; +} + +const void *btf__get_raw_data(const struct btf *btf, __u32 *size) +{ + *size = btf->data_size; + return btf->data; +} + +const char *btf__name_by_offset(const struct btf *btf, __u32 offset) +{ + if (offset < btf->hdr->str_len) + return &btf->strings[offset]; + else + return NULL; +} + +int btf__get_from_id(__u32 id, struct btf **btf) +{ + struct bpf_btf_info btf_info = { 0 }; + __u32 len = sizeof(btf_info); + __u32 last_size; + int btf_fd; + void *ptr; + int err; + + err = 0; + *btf = NULL; + btf_fd = bpf_btf_get_fd_by_id(id); + if (btf_fd < 0) + return 0; + + /* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so + * let's start with a sane default - 4KiB here - and resize it only if + * bpf_obj_get_info_by_fd() needs a bigger buffer. + */ + btf_info.btf_size = 4096; + last_size = btf_info.btf_size; + ptr = malloc(last_size); + if (!ptr) { + err = -ENOMEM; + goto exit_free; + } + + memset(ptr, 0, last_size); + btf_info.btf = ptr_to_u64(ptr); + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + + if (!err && btf_info.btf_size > last_size) { + void *temp_ptr; + + last_size = btf_info.btf_size; + temp_ptr = realloc(ptr, last_size); + if (!temp_ptr) { + err = -ENOMEM; + goto exit_free; + } + ptr = temp_ptr; + memset(ptr, 0, last_size); + btf_info.btf = ptr_to_u64(ptr); + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + } + + if (err || btf_info.btf_size > last_size) { + err = errno; + goto exit_free; + } + + *btf = btf__new((__u8 *)(long)btf_info.btf, btf_info.btf_size); + if (IS_ERR(*btf)) { + err = PTR_ERR(*btf); + *btf = NULL; + } + +exit_free: + close(btf_fd); + free(ptr); + + return err; +} + +int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, + __u32 expected_key_size, __u32 expected_value_size, + __u32 *key_type_id, __u32 *value_type_id) +{ + const struct btf_type *container_type; + const struct btf_member *key, *value; + const size_t max_name = 256; + char container_name[max_name]; + __s64 key_size, value_size; + __s32 container_id; + + if (snprintf(container_name, max_name, "____btf_map_%s", map_name) == + max_name) { + pr_warn("map:%s length of '____btf_map_%s' is too long\n", + map_name, map_name); + return -EINVAL; + } + + container_id = btf__find_by_name(btf, container_name); + if (container_id < 0) { + pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n", + map_name, container_name); + return container_id; + } + + container_type = btf__type_by_id(btf, container_id); + if (!container_type) { + pr_warn("map:%s cannot find BTF type for container_id:%u\n", + map_name, container_id); + return -EINVAL; + } + + if (!btf_is_struct(container_type) || btf_vlen(container_type) < 2) { + pr_warn("map:%s container_name:%s is an invalid container struct\n", + map_name, container_name); + return -EINVAL; + } + + key = btf_members(container_type); + value = key + 1; + + key_size = btf__resolve_size(btf, key->type); + if (key_size < 0) { + pr_warn("map:%s invalid BTF key_type_size\n", map_name); + return key_size; + } + + if (expected_key_size != key_size) { + pr_warn("map:%s btf_key_type_size:%u != map_def_key_size:%u\n", + map_name, (__u32)key_size, expected_key_size); + return -EINVAL; + } + + value_size = btf__resolve_size(btf, value->type); + if (value_size < 0) { + pr_warn("map:%s invalid BTF value_type_size\n", map_name); + return value_size; + } + + if (expected_value_size != value_size) { + pr_warn("map:%s btf_value_type_size:%u != map_def_value_size:%u\n", + map_name, (__u32)value_size, expected_value_size); + return -EINVAL; + } + + *key_type_id = key->type; + *value_type_id = value->type; + + return 0; +} + +struct btf_ext_sec_setup_param { + __u32 off; + __u32 len; + __u32 min_rec_size; + struct btf_ext_info *ext_info; + const char *desc; +}; + +static int btf_ext_setup_info(struct btf_ext *btf_ext, + struct btf_ext_sec_setup_param *ext_sec) +{ + const struct btf_ext_info_sec *sinfo; + struct btf_ext_info *ext_info; + __u32 info_left, record_size; + /* The start of the info sec (including the __u32 record_size). */ + void *info; + + if (ext_sec->len == 0) + return 0; + + if (ext_sec->off & 0x03) { + pr_debug(".BTF.ext %s section is not aligned to 4 bytes\n", + ext_sec->desc); + return -EINVAL; + } + + info = btf_ext->data + btf_ext->hdr->hdr_len + ext_sec->off; + info_left = ext_sec->len; + + if (btf_ext->data + btf_ext->data_size < info + ext_sec->len) { + pr_debug("%s section (off:%u len:%u) is beyond the end of the ELF section .BTF.ext\n", + ext_sec->desc, ext_sec->off, ext_sec->len); + return -EINVAL; + } + + /* At least a record size */ + if (info_left < sizeof(__u32)) { + pr_debug(".BTF.ext %s record size not found\n", ext_sec->desc); + return -EINVAL; + } + + /* The record size needs to meet the minimum standard */ + record_size = *(__u32 *)info; + if (record_size < ext_sec->min_rec_size || + record_size & 0x03) { + pr_debug("%s section in .BTF.ext has invalid record size %u\n", + ext_sec->desc, record_size); + return -EINVAL; + } + + sinfo = info + sizeof(__u32); + info_left -= sizeof(__u32); + + /* If no records, return failure now so .BTF.ext won't be used. */ + if (!info_left) { + pr_debug("%s section in .BTF.ext has no records", ext_sec->desc); + return -EINVAL; + } + + while (info_left) { + unsigned int sec_hdrlen = sizeof(struct btf_ext_info_sec); + __u64 total_record_size; + __u32 num_records; + + if (info_left < sec_hdrlen) { + pr_debug("%s section header is not found in .BTF.ext\n", + ext_sec->desc); + return -EINVAL; + } + + num_records = sinfo->num_info; + if (num_records == 0) { + pr_debug("%s section has incorrect num_records in .BTF.ext\n", + ext_sec->desc); + return -EINVAL; + } + + total_record_size = sec_hdrlen + + (__u64)num_records * record_size; + if (info_left < total_record_size) { + pr_debug("%s section has incorrect num_records in .BTF.ext\n", + ext_sec->desc); + return -EINVAL; + } + + info_left -= total_record_size; + sinfo = (void *)sinfo + total_record_size; + } + + ext_info = ext_sec->ext_info; + ext_info->len = ext_sec->len - sizeof(__u32); + ext_info->rec_size = record_size; + ext_info->info = info + sizeof(__u32); + + return 0; +} + +static int btf_ext_setup_func_info(struct btf_ext *btf_ext) +{ + struct btf_ext_sec_setup_param param = { + .off = btf_ext->hdr->func_info_off, + .len = btf_ext->hdr->func_info_len, + .min_rec_size = sizeof(struct bpf_func_info_min), + .ext_info = &btf_ext->func_info, + .desc = "func_info" + }; + + return btf_ext_setup_info(btf_ext, ¶m); +} + +static int btf_ext_setup_line_info(struct btf_ext *btf_ext) +{ + struct btf_ext_sec_setup_param param = { + .off = btf_ext->hdr->line_info_off, + .len = btf_ext->hdr->line_info_len, + .min_rec_size = sizeof(struct bpf_line_info_min), + .ext_info = &btf_ext->line_info, + .desc = "line_info", + }; + + return btf_ext_setup_info(btf_ext, ¶m); +} + +static int btf_ext_setup_field_reloc(struct btf_ext *btf_ext) +{ + struct btf_ext_sec_setup_param param = { + .off = btf_ext->hdr->field_reloc_off, + .len = btf_ext->hdr->field_reloc_len, + .min_rec_size = sizeof(struct bpf_field_reloc), + .ext_info = &btf_ext->field_reloc_info, + .desc = "field_reloc", + }; + + return btf_ext_setup_info(btf_ext, ¶m); +} + +static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) +{ + const struct btf_ext_header *hdr = (struct btf_ext_header *)data; + + if (data_size < offsetofend(struct btf_ext_header, hdr_len) || + data_size < hdr->hdr_len) { + pr_debug("BTF.ext header not found"); + return -EINVAL; + } + + if (hdr->magic != BTF_MAGIC) { + pr_debug("Invalid BTF.ext magic:%x\n", hdr->magic); + return -EINVAL; + } + + if (hdr->version != BTF_VERSION) { + pr_debug("Unsupported BTF.ext version:%u\n", hdr->version); + return -ENOTSUP; + } + + if (hdr->flags) { + pr_debug("Unsupported BTF.ext flags:%x\n", hdr->flags); + return -ENOTSUP; + } + + if (data_size == hdr->hdr_len) { + pr_debug("BTF.ext has no data\n"); + return -EINVAL; + } + + return 0; +} + +void btf_ext__free(struct btf_ext *btf_ext) +{ + if (!btf_ext) + return; + free(btf_ext->data); + free(btf_ext); +} + +struct btf_ext *btf_ext__new(__u8 *data, __u32 size) +{ + struct btf_ext *btf_ext; + int err; + + err = btf_ext_parse_hdr(data, size); + if (err) + return ERR_PTR(err); + + btf_ext = calloc(1, sizeof(struct btf_ext)); + if (!btf_ext) + return ERR_PTR(-ENOMEM); + + btf_ext->data_size = size; + btf_ext->data = malloc(size); + if (!btf_ext->data) { + err = -ENOMEM; + goto done; + } + memcpy(btf_ext->data, data, size); + + if (btf_ext->hdr->hdr_len < + offsetofend(struct btf_ext_header, line_info_len)) + goto done; + err = btf_ext_setup_func_info(btf_ext); + if (err) + goto done; + + err = btf_ext_setup_line_info(btf_ext); + if (err) + goto done; + + if (btf_ext->hdr->hdr_len < + offsetofend(struct btf_ext_header, field_reloc_len)) + goto done; + err = btf_ext_setup_field_reloc(btf_ext); + if (err) + goto done; + +done: + if (err) { + btf_ext__free(btf_ext); + return ERR_PTR(err); + } + + return btf_ext; +} + +const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size) +{ + *size = btf_ext->data_size; + return btf_ext->data; +} + +static int btf_ext_reloc_info(const struct btf *btf, + const struct btf_ext_info *ext_info, + const char *sec_name, __u32 insns_cnt, + void **info, __u32 *cnt) +{ + __u32 sec_hdrlen = sizeof(struct btf_ext_info_sec); + __u32 i, record_size, existing_len, records_len; + struct btf_ext_info_sec *sinfo; + const char *info_sec_name; + __u64 remain_len; + void *data; + + record_size = ext_info->rec_size; + sinfo = ext_info->info; + remain_len = ext_info->len; + while (remain_len > 0) { + records_len = sinfo->num_info * record_size; + info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off); + if (strcmp(info_sec_name, sec_name)) { + remain_len -= sec_hdrlen + records_len; + sinfo = (void *)sinfo + sec_hdrlen + records_len; + continue; + } + + existing_len = (*cnt) * record_size; + data = realloc(*info, existing_len + records_len); + if (!data) + return -ENOMEM; + + memcpy(data + existing_len, sinfo->data, records_len); + /* adjust insn_off only, the rest data will be passed + * to the kernel. + */ + for (i = 0; i < sinfo->num_info; i++) { + __u32 *insn_off; + + insn_off = data + existing_len + (i * record_size); + *insn_off = *insn_off / sizeof(struct bpf_insn) + + insns_cnt; + } + *info = data; + *cnt += sinfo->num_info; + return 0; + } + + return -ENOENT; +} + +int btf_ext__reloc_func_info(const struct btf *btf, + const struct btf_ext *btf_ext, + const char *sec_name, __u32 insns_cnt, + void **func_info, __u32 *cnt) +{ + return btf_ext_reloc_info(btf, &btf_ext->func_info, sec_name, + insns_cnt, func_info, cnt); +} + +int btf_ext__reloc_line_info(const struct btf *btf, + const struct btf_ext *btf_ext, + const char *sec_name, __u32 insns_cnt, + void **line_info, __u32 *cnt) +{ + return btf_ext_reloc_info(btf, &btf_ext->line_info, sec_name, + insns_cnt, line_info, cnt); +} + +__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext) +{ + return btf_ext->func_info.rec_size; +} + +__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext) +{ + return btf_ext->line_info.rec_size; +} + +struct btf_dedup; + +static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, + const struct btf_dedup_opts *opts); +static void btf_dedup_free(struct btf_dedup *d); +static int btf_dedup_strings(struct btf_dedup *d); +static int btf_dedup_prim_types(struct btf_dedup *d); +static int btf_dedup_struct_types(struct btf_dedup *d); +static int btf_dedup_ref_types(struct btf_dedup *d); +static int btf_dedup_compact_types(struct btf_dedup *d); +static int btf_dedup_remap_types(struct btf_dedup *d); + +/* + * Deduplicate BTF types and strings. + * + * BTF dedup algorithm takes as an input `struct btf` representing `.BTF` ELF + * section with all BTF type descriptors and string data. It overwrites that + * memory in-place with deduplicated types and strings without any loss of + * information. If optional `struct btf_ext` representing '.BTF.ext' ELF section + * is provided, all the strings referenced from .BTF.ext section are honored + * and updated to point to the right offsets after deduplication. + * + * If function returns with error, type/string data might be garbled and should + * be discarded. + * + * More verbose and detailed description of both problem btf_dedup is solving, + * as well as solution could be found at: + * https://facebookmicrosites.github.io/bpf/blog/2018/11/14/btf-enhancement.html + * + * Problem description and justification + * ===================================== + * + * BTF type information is typically emitted either as a result of conversion + * from DWARF to BTF or directly by compiler. In both cases, each compilation + * unit contains information about a subset of all the types that are used + * in an application. These subsets are frequently overlapping and contain a lot + * of duplicated information when later concatenated together into a single + * binary. This algorithm ensures that each unique type is represented by single + * BTF type descriptor, greatly reducing resulting size of BTF data. + * + * Compilation unit isolation and subsequent duplication of data is not the only + * problem. The same type hierarchy (e.g., struct and all the type that struct + * references) in different compilation units can be represented in BTF to + * various degrees of completeness (or, rather, incompleteness) due to + * struct/union forward declarations. + * + * Let's take a look at an example, that we'll use to better understand the + * problem (and solution). Suppose we have two compilation units, each using + * same `struct S`, but each of them having incomplete type information about + * struct's fields: + * + * // CU #1: + * struct S; + * struct A { + * int a; + * struct A* self; + * struct S* parent; + * }; + * struct B; + * struct S { + * struct A* a_ptr; + * struct B* b_ptr; + * }; + * + * // CU #2: + * struct S; + * struct A; + * struct B { + * int b; + * struct B* self; + * struct S* parent; + * }; + * struct S { + * struct A* a_ptr; + * struct B* b_ptr; + * }; + * + * In case of CU #1, BTF data will know only that `struct B` exist (but no + * more), but will know the complete type information about `struct A`. While + * for CU #2, it will know full type information about `struct B`, but will + * only know about forward declaration of `struct A` (in BTF terms, it will + * have `BTF_KIND_FWD` type descriptor with name `B`). + * + * This compilation unit isolation means that it's possible that there is no + * single CU with complete type information describing structs `S`, `A`, and + * `B`. Also, we might get tons of duplicated and redundant type information. + * + * Additional complication we need to keep in mind comes from the fact that + * types, in general, can form graphs containing cycles, not just DAGs. + * + * While algorithm does deduplication, it also merges and resolves type + * information (unless disabled throught `struct btf_opts`), whenever possible. + * E.g., in the example above with two compilation units having partial type + * information for structs `A` and `B`, the output of algorithm will emit + * a single copy of each BTF type that describes structs `A`, `B`, and `S` + * (as well as type information for `int` and pointers), as if they were defined + * in a single compilation unit as: + * + * struct A { + * int a; + * struct A* self; + * struct S* parent; + * }; + * struct B { + * int b; + * struct B* self; + * struct S* parent; + * }; + * struct S { + * struct A* a_ptr; + * struct B* b_ptr; + * }; + * + * Algorithm summary + * ================= + * + * Algorithm completes its work in 6 separate passes: + * + * 1. Strings deduplication. + * 2. Primitive types deduplication (int, enum, fwd). + * 3. Struct/union types deduplication. + * 4. Reference types deduplication (pointers, typedefs, arrays, funcs, func + * protos, and const/volatile/restrict modifiers). + * 5. Types compaction. + * 6. Types remapping. + * + * Algorithm determines canonical type descriptor, which is a single + * representative type for each truly unique type. This canonical type is the + * one that will go into final deduplicated BTF type information. For + * struct/unions, it is also the type that algorithm will merge additional type + * information into (while resolving FWDs), as it discovers it from data in + * other CUs. Each input BTF type eventually gets either mapped to itself, if + * that type is canonical, or to some other type, if that type is equivalent + * and was chosen as canonical representative. This mapping is stored in + * `btf_dedup->map` array. This map is also used to record STRUCT/UNION that + * FWD type got resolved to. + * + * To facilitate fast discovery of canonical types, we also maintain canonical + * index (`btf_dedup->dedup_table`), which maps type descriptor's signature hash + * (i.e., hashed kind, name, size, fields, etc) into a list of canonical types + * that match that signature. With sufficiently good choice of type signature + * hashing function, we can limit number of canonical types for each unique type + * signature to a very small number, allowing to find canonical type for any + * duplicated type very quickly. + * + * Struct/union deduplication is the most critical part and algorithm for + * deduplicating structs/unions is described in greater details in comments for + * `btf_dedup_is_equiv` function. + */ +int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, + const struct btf_dedup_opts *opts) +{ + struct btf_dedup *d = btf_dedup_new(btf, btf_ext, opts); + int err; + + if (IS_ERR(d)) { + pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d)); + return -EINVAL; + } + + err = btf_dedup_strings(d); + if (err < 0) { + pr_debug("btf_dedup_strings failed:%d\n", err); + goto done; + } + err = btf_dedup_prim_types(d); + if (err < 0) { + pr_debug("btf_dedup_prim_types failed:%d\n", err); + goto done; + } + err = btf_dedup_struct_types(d); + if (err < 0) { + pr_debug("btf_dedup_struct_types failed:%d\n", err); + goto done; + } + err = btf_dedup_ref_types(d); + if (err < 0) { + pr_debug("btf_dedup_ref_types failed:%d\n", err); + goto done; + } + err = btf_dedup_compact_types(d); + if (err < 0) { + pr_debug("btf_dedup_compact_types failed:%d\n", err); + goto done; + } + err = btf_dedup_remap_types(d); + if (err < 0) { + pr_debug("btf_dedup_remap_types failed:%d\n", err); + goto done; + } + +done: + btf_dedup_free(d); + return err; +} + +#define BTF_UNPROCESSED_ID ((__u32)-1) +#define BTF_IN_PROGRESS_ID ((__u32)-2) + +struct btf_dedup { + /* .BTF section to be deduped in-place */ + struct btf *btf; + /* + * Optional .BTF.ext section. When provided, any strings referenced + * from it will be taken into account when deduping strings + */ + struct btf_ext *btf_ext; + /* + * This is a map from any type's signature hash to a list of possible + * canonical representative type candidates. Hash collisions are + * ignored, so even types of various kinds can share same list of + * candidates, which is fine because we rely on subsequent + * btf_xxx_equal() checks to authoritatively verify type equality. + */ + struct hashmap *dedup_table; + /* Canonical types map */ + __u32 *map; + /* Hypothetical mapping, used during type graph equivalence checks */ + __u32 *hypot_map; + __u32 *hypot_list; + size_t hypot_cnt; + size_t hypot_cap; + /* Various option modifying behavior of algorithm */ + struct btf_dedup_opts opts; +}; + +struct btf_str_ptr { + const char *str; + __u32 new_off; + bool used; +}; + +struct btf_str_ptrs { + struct btf_str_ptr *ptrs; + const char *data; + __u32 cnt; + __u32 cap; +}; + +static long hash_combine(long h, long value) +{ + return h * 31 + value; +} + +#define for_each_dedup_cand(d, node, hash) \ + hashmap__for_each_key_entry(d->dedup_table, node, (void *)hash) + +static int btf_dedup_table_add(struct btf_dedup *d, long hash, __u32 type_id) +{ + return hashmap__append(d->dedup_table, + (void *)hash, (void *)(long)type_id); +} + +static int btf_dedup_hypot_map_add(struct btf_dedup *d, + __u32 from_id, __u32 to_id) +{ + if (d->hypot_cnt == d->hypot_cap) { + __u32 *new_list; + + d->hypot_cap += max(16, d->hypot_cap / 2); + new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap); + if (!new_list) + return -ENOMEM; + d->hypot_list = new_list; + } + d->hypot_list[d->hypot_cnt++] = from_id; + d->hypot_map[from_id] = to_id; + return 0; +} + +static void btf_dedup_clear_hypot_map(struct btf_dedup *d) +{ + int i; + + for (i = 0; i < d->hypot_cnt; i++) + d->hypot_map[d->hypot_list[i]] = BTF_UNPROCESSED_ID; + d->hypot_cnt = 0; +} + +static void btf_dedup_free(struct btf_dedup *d) +{ + hashmap__free(d->dedup_table); + d->dedup_table = NULL; + + free(d->map); + d->map = NULL; + + free(d->hypot_map); + d->hypot_map = NULL; + + free(d->hypot_list); + d->hypot_list = NULL; + + free(d); +} + +static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx) +{ + return (size_t)key; +} + +static size_t btf_dedup_collision_hash_fn(const void *key, void *ctx) +{ + return 0; +} + +static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx) +{ + return k1 == k2; +} + +static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, + const struct btf_dedup_opts *opts) +{ + struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup)); + hashmap_hash_fn hash_fn = btf_dedup_identity_hash_fn; + int i, err = 0; + + if (!d) + return ERR_PTR(-ENOMEM); + + d->opts.dont_resolve_fwds = opts && opts->dont_resolve_fwds; + /* dedup_table_size is now used only to force collisions in tests */ + if (opts && opts->dedup_table_size == 1) + hash_fn = btf_dedup_collision_hash_fn; + + d->btf = btf; + d->btf_ext = btf_ext; + + d->dedup_table = hashmap__new(hash_fn, btf_dedup_equal_fn, NULL); + if (IS_ERR(d->dedup_table)) { + err = PTR_ERR(d->dedup_table); + d->dedup_table = NULL; + goto done; + } + + d->map = malloc(sizeof(__u32) * (1 + btf->nr_types)); + if (!d->map) { + err = -ENOMEM; + goto done; + } + /* special BTF "void" type is made canonical immediately */ + d->map[0] = 0; + for (i = 1; i <= btf->nr_types; i++) { + struct btf_type *t = d->btf->types[i]; + + /* VAR and DATASEC are never deduped and are self-canonical */ + if (btf_is_var(t) || btf_is_datasec(t)) + d->map[i] = i; + else + d->map[i] = BTF_UNPROCESSED_ID; + } + + d->hypot_map = malloc(sizeof(__u32) * (1 + btf->nr_types)); + if (!d->hypot_map) { + err = -ENOMEM; + goto done; + } + for (i = 0; i <= btf->nr_types; i++) + d->hypot_map[i] = BTF_UNPROCESSED_ID; + +done: + if (err) { + btf_dedup_free(d); + return ERR_PTR(err); + } + + return d; +} + +typedef int (*str_off_fn_t)(__u32 *str_off_ptr, void *ctx); + +/* + * Iterate over all possible places in .BTF and .BTF.ext that can reference + * string and pass pointer to it to a provided callback `fn`. + */ +static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) +{ + void *line_data_cur, *line_data_end; + int i, j, r, rec_size; + struct btf_type *t; + + for (i = 1; i <= d->btf->nr_types; i++) { + t = d->btf->types[i]; + r = fn(&t->name_off, ctx); + if (r) + return r; + + switch (btf_kind(t)) { + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); + + for (j = 0; j < vlen; j++) { + r = fn(&m->name_off, ctx); + if (r) + return r; + m++; + } + break; + } + case BTF_KIND_ENUM: { + struct btf_enum *m = btf_enum(t); + __u16 vlen = btf_vlen(t); + + for (j = 0; j < vlen; j++) { + r = fn(&m->name_off, ctx); + if (r) + return r; + m++; + } + break; + } + case BTF_KIND_FUNC_PROTO: { + struct btf_param *m = btf_params(t); + __u16 vlen = btf_vlen(t); + + for (j = 0; j < vlen; j++) { + r = fn(&m->name_off, ctx); + if (r) + return r; + m++; + } + break; + } + default: + break; + } + } + + if (!d->btf_ext) + return 0; + + line_data_cur = d->btf_ext->line_info.info; + line_data_end = d->btf_ext->line_info.info + d->btf_ext->line_info.len; + rec_size = d->btf_ext->line_info.rec_size; + + while (line_data_cur < line_data_end) { + struct btf_ext_info_sec *sec = line_data_cur; + struct bpf_line_info_min *line_info; + __u32 num_info = sec->num_info; + + r = fn(&sec->sec_name_off, ctx); + if (r) + return r; + + line_data_cur += sizeof(struct btf_ext_info_sec); + for (i = 0; i < num_info; i++) { + line_info = line_data_cur; + r = fn(&line_info->file_name_off, ctx); + if (r) + return r; + r = fn(&line_info->line_off, ctx); + if (r) + return r; + line_data_cur += rec_size; + } + } + + return 0; +} + +static int str_sort_by_content(const void *a1, const void *a2) +{ + const struct btf_str_ptr *p1 = a1; + const struct btf_str_ptr *p2 = a2; + + return strcmp(p1->str, p2->str); +} + +static int str_sort_by_offset(const void *a1, const void *a2) +{ + const struct btf_str_ptr *p1 = a1; + const struct btf_str_ptr *p2 = a2; + + if (p1->str != p2->str) + return p1->str < p2->str ? -1 : 1; + return 0; +} + +static int btf_dedup_str_ptr_cmp(const void *str_ptr, const void *pelem) +{ + const struct btf_str_ptr *p = pelem; + + if (str_ptr != p->str) + return (const char *)str_ptr < p->str ? -1 : 1; + return 0; +} + +static int btf_str_mark_as_used(__u32 *str_off_ptr, void *ctx) +{ + struct btf_str_ptrs *strs; + struct btf_str_ptr *s; + + if (*str_off_ptr == 0) + return 0; + + strs = ctx; + s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt, + sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp); + if (!s) + return -EINVAL; + s->used = true; + return 0; +} + +static int btf_str_remap_offset(__u32 *str_off_ptr, void *ctx) +{ + struct btf_str_ptrs *strs; + struct btf_str_ptr *s; + + if (*str_off_ptr == 0) + return 0; + + strs = ctx; + s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt, + sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp); + if (!s) + return -EINVAL; + *str_off_ptr = s->new_off; + return 0; +} + +/* + * Dedup string and filter out those that are not referenced from either .BTF + * or .BTF.ext (if provided) sections. + * + * This is done by building index of all strings in BTF's string section, + * then iterating over all entities that can reference strings (e.g., type + * names, struct field names, .BTF.ext line info, etc) and marking corresponding + * strings as used. After that all used strings are deduped and compacted into + * sequential blob of memory and new offsets are calculated. Then all the string + * references are iterated again and rewritten using new offsets. + */ +static int btf_dedup_strings(struct btf_dedup *d) +{ + const struct btf_header *hdr = d->btf->hdr; + char *start = (char *)d->btf->nohdr_data + hdr->str_off; + char *end = start + d->btf->hdr->str_len; + char *p = start, *tmp_strs = NULL; + struct btf_str_ptrs strs = { + .cnt = 0, + .cap = 0, + .ptrs = NULL, + .data = start, + }; + int i, j, err = 0, grp_idx; + bool grp_used; + + /* build index of all strings */ + while (p < end) { + if (strs.cnt + 1 > strs.cap) { + struct btf_str_ptr *new_ptrs; + + strs.cap += max(strs.cnt / 2, 16); + new_ptrs = realloc(strs.ptrs, + sizeof(strs.ptrs[0]) * strs.cap); + if (!new_ptrs) { + err = -ENOMEM; + goto done; + } + strs.ptrs = new_ptrs; + } + + strs.ptrs[strs.cnt].str = p; + strs.ptrs[strs.cnt].used = false; + + p += strlen(p) + 1; + strs.cnt++; + } + + /* temporary storage for deduplicated strings */ + tmp_strs = malloc(d->btf->hdr->str_len); + if (!tmp_strs) { + err = -ENOMEM; + goto done; + } + + /* mark all used strings */ + strs.ptrs[0].used = true; + err = btf_for_each_str_off(d, btf_str_mark_as_used, &strs); + if (err) + goto done; + + /* sort strings by context, so that we can identify duplicates */ + qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_content); + + /* + * iterate groups of equal strings and if any instance in a group was + * referenced, emit single instance and remember new offset + */ + p = tmp_strs; + grp_idx = 0; + grp_used = strs.ptrs[0].used; + /* iterate past end to avoid code duplication after loop */ + for (i = 1; i <= strs.cnt; i++) { + /* + * when i == strs.cnt, we want to skip string comparison and go + * straight to handling last group of strings (otherwise we'd + * need to handle last group after the loop w/ duplicated code) + */ + if (i < strs.cnt && + !strcmp(strs.ptrs[i].str, strs.ptrs[grp_idx].str)) { + grp_used = grp_used || strs.ptrs[i].used; + continue; + } + + /* + * this check would have been required after the loop to handle + * last group of strings, but due to <= condition in a loop + * we avoid that duplication + */ + if (grp_used) { + int new_off = p - tmp_strs; + __u32 len = strlen(strs.ptrs[grp_idx].str); + + memmove(p, strs.ptrs[grp_idx].str, len + 1); + for (j = grp_idx; j < i; j++) + strs.ptrs[j].new_off = new_off; + p += len + 1; + } + + if (i < strs.cnt) { + grp_idx = i; + grp_used = strs.ptrs[i].used; + } + } + + /* replace original strings with deduped ones */ + d->btf->hdr->str_len = p - tmp_strs; + memmove(start, tmp_strs, d->btf->hdr->str_len); + end = start + d->btf->hdr->str_len; + + /* restore original order for further binary search lookups */ + qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_offset); + + /* remap string offsets */ + err = btf_for_each_str_off(d, btf_str_remap_offset, &strs); + if (err) + goto done; + + d->btf->hdr->str_len = end - start; + +done: + free(tmp_strs); + free(strs.ptrs); + return err; +} + +static long btf_hash_common(struct btf_type *t) +{ + long h; + + h = hash_combine(0, t->name_off); + h = hash_combine(h, t->info); + h = hash_combine(h, t->size); + return h; +} + +static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2) +{ + return t1->name_off == t2->name_off && + t1->info == t2->info && + t1->size == t2->size; +} + +/* Calculate type signature hash of INT. */ +static long btf_hash_int(struct btf_type *t) +{ + __u32 info = *(__u32 *)(t + 1); + long h; + + h = btf_hash_common(t); + h = hash_combine(h, info); + return h; +} + +/* Check structural equality of two INTs. */ +static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2) +{ + __u32 info1, info2; + + if (!btf_equal_common(t1, t2)) + return false; + info1 = *(__u32 *)(t1 + 1); + info2 = *(__u32 *)(t2 + 1); + return info1 == info2; +} + +/* Calculate type signature hash of ENUM. */ +static long btf_hash_enum(struct btf_type *t) +{ + long h; + + /* don't hash vlen and enum members to support enum fwd resolving */ + h = hash_combine(0, t->name_off); + h = hash_combine(h, t->info & ~0xffff); + h = hash_combine(h, t->size); + return h; +} + +/* Check structural equality of two ENUMs. */ +static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) +{ + const struct btf_enum *m1, *m2; + __u16 vlen; + int i; + + if (!btf_equal_common(t1, t2)) + return false; + + vlen = btf_vlen(t1); + m1 = btf_enum(t1); + m2 = btf_enum(t2); + for (i = 0; i < vlen; i++) { + if (m1->name_off != m2->name_off || m1->val != m2->val) + return false; + m1++; + m2++; + } + return true; +} + +static inline bool btf_is_enum_fwd(struct btf_type *t) +{ + return btf_is_enum(t) && btf_vlen(t) == 0; +} + +static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) +{ + if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2)) + return btf_equal_enum(t1, t2); + /* ignore vlen when comparing */ + return t1->name_off == t2->name_off && + (t1->info & ~0xffff) == (t2->info & ~0xffff) && + t1->size == t2->size; +} + +/* + * Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs, + * as referenced type IDs equivalence is established separately during type + * graph equivalence check algorithm. + */ +static long btf_hash_struct(struct btf_type *t) +{ + const struct btf_member *member = btf_members(t); + __u32 vlen = btf_vlen(t); + long h = btf_hash_common(t); + int i; + + for (i = 0; i < vlen; i++) { + h = hash_combine(h, member->name_off); + h = hash_combine(h, member->offset); + /* no hashing of referenced type ID, it can be unresolved yet */ + member++; + } + return h; +} + +/* + * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type + * IDs. This check is performed during type graph equivalence check and + * referenced types equivalence is checked separately. + */ +static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2) +{ + const struct btf_member *m1, *m2; + __u16 vlen; + int i; + + if (!btf_equal_common(t1, t2)) + return false; + + vlen = btf_vlen(t1); + m1 = btf_members(t1); + m2 = btf_members(t2); + for (i = 0; i < vlen; i++) { + if (m1->name_off != m2->name_off || m1->offset != m2->offset) + return false; + m1++; + m2++; + } + return true; +} + +/* + * Calculate type signature hash of ARRAY, including referenced type IDs, + * under assumption that they were already resolved to canonical type IDs and + * are not going to change. + */ +static long btf_hash_array(struct btf_type *t) +{ + const struct btf_array *info = btf_array(t); + long h = btf_hash_common(t); + + h = hash_combine(h, info->type); + h = hash_combine(h, info->index_type); + h = hash_combine(h, info->nelems); + return h; +} + +/* + * Check exact equality of two ARRAYs, taking into account referenced + * type IDs, under assumption that they were already resolved to canonical + * type IDs and are not going to change. + * This function is called during reference types deduplication to compare + * ARRAY to potential canonical representative. + */ +static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2) +{ + const struct btf_array *info1, *info2; + + if (!btf_equal_common(t1, t2)) + return false; + + info1 = btf_array(t1); + info2 = btf_array(t2); + return info1->type == info2->type && + info1->index_type == info2->index_type && + info1->nelems == info2->nelems; +} + +/* + * Check structural compatibility of two ARRAYs, ignoring referenced type + * IDs. This check is performed during type graph equivalence check and + * referenced types equivalence is checked separately. + */ +static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2) +{ + if (!btf_equal_common(t1, t2)) + return false; + + return btf_array(t1)->nelems == btf_array(t2)->nelems; +} + +/* + * Calculate type signature hash of FUNC_PROTO, including referenced type IDs, + * under assumption that they were already resolved to canonical type IDs and + * are not going to change. + */ +static long btf_hash_fnproto(struct btf_type *t) +{ + const struct btf_param *member = btf_params(t); + __u16 vlen = btf_vlen(t); + long h = btf_hash_common(t); + int i; + + for (i = 0; i < vlen; i++) { + h = hash_combine(h, member->name_off); + h = hash_combine(h, member->type); + member++; + } + return h; +} + +/* + * Check exact equality of two FUNC_PROTOs, taking into account referenced + * type IDs, under assumption that they were already resolved to canonical + * type IDs and are not going to change. + * This function is called during reference types deduplication to compare + * FUNC_PROTO to potential canonical representative. + */ +static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2) +{ + const struct btf_param *m1, *m2; + __u16 vlen; + int i; + + if (!btf_equal_common(t1, t2)) + return false; + + vlen = btf_vlen(t1); + m1 = btf_params(t1); + m2 = btf_params(t2); + for (i = 0; i < vlen; i++) { + if (m1->name_off != m2->name_off || m1->type != m2->type) + return false; + m1++; + m2++; + } + return true; +} + +/* + * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type + * IDs. This check is performed during type graph equivalence check and + * referenced types equivalence is checked separately. + */ +static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) +{ + const struct btf_param *m1, *m2; + __u16 vlen; + int i; + + /* skip return type ID */ + if (t1->name_off != t2->name_off || t1->info != t2->info) + return false; + + vlen = btf_vlen(t1); + m1 = btf_params(t1); + m2 = btf_params(t2); + for (i = 0; i < vlen; i++) { + if (m1->name_off != m2->name_off) + return false; + m1++; + m2++; + } + return true; +} + +/* + * Deduplicate primitive types, that can't reference other types, by calculating + * their type signature hash and comparing them with any possible canonical + * candidate. If no canonical candidate matches, type itself is marked as + * canonical and is added into `btf_dedup->dedup_table` as another candidate. + */ +static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) +{ + struct btf_type *t = d->btf->types[type_id]; + struct hashmap_entry *hash_entry; + struct btf_type *cand; + /* if we don't find equivalent type, then we are canonical */ + __u32 new_id = type_id; + __u32 cand_id; + long h; + + switch (btf_kind(t)) { + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_ARRAY: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_FUNC: + case BTF_KIND_FUNC_PROTO: + case BTF_KIND_VAR: + case BTF_KIND_DATASEC: + return 0; + + case BTF_KIND_INT: + h = btf_hash_int(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = d->btf->types[cand_id]; + if (btf_equal_int(t, cand)) { + new_id = cand_id; + break; + } + } + break; + + case BTF_KIND_ENUM: + h = btf_hash_enum(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = d->btf->types[cand_id]; + if (btf_equal_enum(t, cand)) { + new_id = cand_id; + break; + } + if (d->opts.dont_resolve_fwds) + continue; + if (btf_compat_enum(t, cand)) { + if (btf_is_enum_fwd(t)) { + /* resolve fwd to full enum */ + new_id = cand_id; + break; + } + /* resolve canonical enum fwd to full enum */ + d->map[cand_id] = type_id; + } + } + break; + + case BTF_KIND_FWD: + h = btf_hash_common(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = d->btf->types[cand_id]; + if (btf_equal_common(t, cand)) { + new_id = cand_id; + break; + } + } + break; + + default: + return -EINVAL; + } + + d->map[type_id] = new_id; + if (type_id == new_id && btf_dedup_table_add(d, h, type_id)) + return -ENOMEM; + + return 0; +} + +static int btf_dedup_prim_types(struct btf_dedup *d) +{ + int i, err; + + for (i = 1; i <= d->btf->nr_types; i++) { + err = btf_dedup_prim_type(d, i); + if (err) + return err; + } + return 0; +} + +/* + * Check whether type is already mapped into canonical one (could be to itself). + */ +static inline bool is_type_mapped(struct btf_dedup *d, uint32_t type_id) +{ + return d->map[type_id] <= BTF_MAX_NR_TYPES; +} + +/* + * Resolve type ID into its canonical type ID, if any; otherwise return original + * type ID. If type is FWD and is resolved into STRUCT/UNION already, follow + * STRUCT/UNION link and resolve it into canonical type ID as well. + */ +static inline __u32 resolve_type_id(struct btf_dedup *d, __u32 type_id) +{ + while (is_type_mapped(d, type_id) && d->map[type_id] != type_id) + type_id = d->map[type_id]; + return type_id; +} + +/* + * Resolve FWD to underlying STRUCT/UNION, if any; otherwise return original + * type ID. + */ +static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id) +{ + __u32 orig_type_id = type_id; + + if (!btf_is_fwd(d->btf->types[type_id])) + return type_id; + + while (is_type_mapped(d, type_id) && d->map[type_id] != type_id) + type_id = d->map[type_id]; + + if (!btf_is_fwd(d->btf->types[type_id])) + return type_id; + + return orig_type_id; +} + + +static inline __u16 btf_fwd_kind(struct btf_type *t) +{ + return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT; +} + +/* + * Check equivalence of BTF type graph formed by candidate struct/union (we'll + * call it "candidate graph" in this description for brevity) to a type graph + * formed by (potential) canonical struct/union ("canonical graph" for brevity + * here, though keep in mind that not all types in canonical graph are + * necessarily canonical representatives themselves, some of them might be + * duplicates or its uniqueness might not have been established yet). + * Returns: + * - >0, if type graphs are equivalent; + * - 0, if not equivalent; + * - <0, on error. + * + * Algorithm performs side-by-side DFS traversal of both type graphs and checks + * equivalence of BTF types at each step. If at any point BTF types in candidate + * and canonical graphs are not compatible structurally, whole graphs are + * incompatible. If types are structurally equivalent (i.e., all information + * except referenced type IDs is exactly the same), a mapping from `canon_id` to + * a `cand_id` is recored in hypothetical mapping (`btf_dedup->hypot_map`). + * If a type references other types, then those referenced types are checked + * for equivalence recursively. + * + * During DFS traversal, if we find that for current `canon_id` type we + * already have some mapping in hypothetical map, we check for two possible + * situations: + * - `canon_id` is mapped to exactly the same type as `cand_id`. This will + * happen when type graphs have cycles. In this case we assume those two + * types are equivalent. + * - `canon_id` is mapped to different type. This is contradiction in our + * hypothetical mapping, because same graph in canonical graph corresponds + * to two different types in candidate graph, which for equivalent type + * graphs shouldn't happen. This condition terminates equivalence check + * with negative result. + * + * If type graphs traversal exhausts types to check and find no contradiction, + * then type graphs are equivalent. + * + * When checking types for equivalence, there is one special case: FWD types. + * If FWD type resolution is allowed and one of the types (either from canonical + * or candidate graph) is FWD and other is STRUCT/UNION (depending on FWD's kind + * flag) and their names match, hypothetical mapping is updated to point from + * FWD to STRUCT/UNION. If graphs will be determined as equivalent successfully, + * this mapping will be used to record FWD -> STRUCT/UNION mapping permanently. + * + * Technically, this could lead to incorrect FWD to STRUCT/UNION resolution, + * if there are two exactly named (or anonymous) structs/unions that are + * compatible structurally, one of which has FWD field, while other is concrete + * STRUCT/UNION, but according to C sources they are different structs/unions + * that are referencing different types with the same name. This is extremely + * unlikely to happen, but btf_dedup API allows to disable FWD resolution if + * this logic is causing problems. + * + * Doing FWD resolution means that both candidate and/or canonical graphs can + * consists of portions of the graph that come from multiple compilation units. + * This is due to the fact that types within single compilation unit are always + * deduplicated and FWDs are already resolved, if referenced struct/union + * definiton is available. So, if we had unresolved FWD and found corresponding + * STRUCT/UNION, they will be from different compilation units. This + * consequently means that when we "link" FWD to corresponding STRUCT/UNION, + * type graph will likely have at least two different BTF types that describe + * same type (e.g., most probably there will be two different BTF types for the + * same 'int' primitive type) and could even have "overlapping" parts of type + * graph that describe same subset of types. + * + * This in turn means that our assumption that each type in canonical graph + * must correspond to exactly one type in candidate graph might not hold + * anymore and will make it harder to detect contradictions using hypothetical + * map. To handle this problem, we allow to follow FWD -> STRUCT/UNION + * resolution only in canonical graph. FWDs in candidate graphs are never + * resolved. To see why it's OK, let's check all possible situations w.r.t. FWDs + * that can occur: + * - Both types in canonical and candidate graphs are FWDs. If they are + * structurally equivalent, then they can either be both resolved to the + * same STRUCT/UNION or not resolved at all. In both cases they are + * equivalent and there is no need to resolve FWD on candidate side. + * - Both types in canonical and candidate graphs are concrete STRUCT/UNION, + * so nothing to resolve as well, algorithm will check equivalence anyway. + * - Type in canonical graph is FWD, while type in candidate is concrete + * STRUCT/UNION. In this case candidate graph comes from single compilation + * unit, so there is exactly one BTF type for each unique C type. After + * resolving FWD into STRUCT/UNION, there might be more than one BTF type + * in canonical graph mapping to single BTF type in candidate graph, but + * because hypothetical mapping maps from canonical to candidate types, it's + * alright, and we still maintain the property of having single `canon_id` + * mapping to single `cand_id` (there could be two different `canon_id` + * mapped to the same `cand_id`, but it's not contradictory). + * - Type in canonical graph is concrete STRUCT/UNION, while type in candidate + * graph is FWD. In this case we are just going to check compatibility of + * STRUCT/UNION and corresponding FWD, and if they are compatible, we'll + * assume that whatever STRUCT/UNION FWD resolves to must be equivalent to + * a concrete STRUCT/UNION from canonical graph. If the rest of type graphs + * turn out equivalent, we'll re-resolve FWD to concrete STRUCT/UNION from + * canonical graph. + */ +static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, + __u32 canon_id) +{ + struct btf_type *cand_type; + struct btf_type *canon_type; + __u32 hypot_type_id; + __u16 cand_kind; + __u16 canon_kind; + int i, eq; + + /* if both resolve to the same canonical, they must be equivalent */ + if (resolve_type_id(d, cand_id) == resolve_type_id(d, canon_id)) + return 1; + + canon_id = resolve_fwd_id(d, canon_id); + + hypot_type_id = d->hypot_map[canon_id]; + if (hypot_type_id <= BTF_MAX_NR_TYPES) + return hypot_type_id == cand_id; + + if (btf_dedup_hypot_map_add(d, canon_id, cand_id)) + return -ENOMEM; + + cand_type = d->btf->types[cand_id]; + canon_type = d->btf->types[canon_id]; + cand_kind = btf_kind(cand_type); + canon_kind = btf_kind(canon_type); + + if (cand_type->name_off != canon_type->name_off) + return 0; + + /* FWD <--> STRUCT/UNION equivalence check, if enabled */ + if (!d->opts.dont_resolve_fwds + && (cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD) + && cand_kind != canon_kind) { + __u16 real_kind; + __u16 fwd_kind; + + if (cand_kind == BTF_KIND_FWD) { + real_kind = canon_kind; + fwd_kind = btf_fwd_kind(cand_type); + } else { + real_kind = cand_kind; + fwd_kind = btf_fwd_kind(canon_type); + } + return fwd_kind == real_kind; + } + + if (cand_kind != canon_kind) + return 0; + + switch (cand_kind) { + case BTF_KIND_INT: + return btf_equal_int(cand_type, canon_type); + + case BTF_KIND_ENUM: + if (d->opts.dont_resolve_fwds) + return btf_equal_enum(cand_type, canon_type); + else + return btf_compat_enum(cand_type, canon_type); + + case BTF_KIND_FWD: + return btf_equal_common(cand_type, canon_type); + + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + if (cand_type->info != canon_type->info) + return 0; + return btf_dedup_is_equiv(d, cand_type->type, canon_type->type); + + case BTF_KIND_ARRAY: { + const struct btf_array *cand_arr, *canon_arr; + + if (!btf_compat_array(cand_type, canon_type)) + return 0; + cand_arr = btf_array(cand_type); + canon_arr = btf_array(canon_type); + eq = btf_dedup_is_equiv(d, + cand_arr->index_type, canon_arr->index_type); + if (eq <= 0) + return eq; + return btf_dedup_is_equiv(d, cand_arr->type, canon_arr->type); + } + + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *cand_m, *canon_m; + __u16 vlen; + + if (!btf_shallow_equal_struct(cand_type, canon_type)) + return 0; + vlen = btf_vlen(cand_type); + cand_m = btf_members(cand_type); + canon_m = btf_members(canon_type); + for (i = 0; i < vlen; i++) { + eq = btf_dedup_is_equiv(d, cand_m->type, canon_m->type); + if (eq <= 0) + return eq; + cand_m++; + canon_m++; + } + + return 1; + } + + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *cand_p, *canon_p; + __u16 vlen; + + if (!btf_compat_fnproto(cand_type, canon_type)) + return 0; + eq = btf_dedup_is_equiv(d, cand_type->type, canon_type->type); + if (eq <= 0) + return eq; + vlen = btf_vlen(cand_type); + cand_p = btf_params(cand_type); + canon_p = btf_params(canon_type); + for (i = 0; i < vlen; i++) { + eq = btf_dedup_is_equiv(d, cand_p->type, canon_p->type); + if (eq <= 0) + return eq; + cand_p++; + canon_p++; + } + return 1; + } + + default: + return -EINVAL; + } + return 0; +} + +/* + * Use hypothetical mapping, produced by successful type graph equivalence + * check, to augment existing struct/union canonical mapping, where possible. + * + * If BTF_KIND_FWD resolution is allowed, this mapping is also used to record + * FWD -> STRUCT/UNION correspondence as well. FWD resolution is bidirectional: + * it doesn't matter if FWD type was part of canonical graph or candidate one, + * we are recording the mapping anyway. As opposed to carefulness required + * for struct/union correspondence mapping (described below), for FWD resolution + * it's not important, as by the time that FWD type (reference type) will be + * deduplicated all structs/unions will be deduped already anyway. + * + * Recording STRUCT/UNION mapping is purely a performance optimization and is + * not required for correctness. It needs to be done carefully to ensure that + * struct/union from candidate's type graph is not mapped into corresponding + * struct/union from canonical type graph that itself hasn't been resolved into + * canonical representative. The only guarantee we have is that canonical + * struct/union was determined as canonical and that won't change. But any + * types referenced through that struct/union fields could have been not yet + * resolved, so in case like that it's too early to establish any kind of + * correspondence between structs/unions. + * + * No canonical correspondence is derived for primitive types (they are already + * deduplicated completely already anyway) or reference types (they rely on + * stability of struct/union canonical relationship for equivalence checks). + */ +static void btf_dedup_merge_hypot_map(struct btf_dedup *d) +{ + __u32 cand_type_id, targ_type_id; + __u16 t_kind, c_kind; + __u32 t_id, c_id; + int i; + + for (i = 0; i < d->hypot_cnt; i++) { + cand_type_id = d->hypot_list[i]; + targ_type_id = d->hypot_map[cand_type_id]; + t_id = resolve_type_id(d, targ_type_id); + c_id = resolve_type_id(d, cand_type_id); + t_kind = btf_kind(d->btf->types[t_id]); + c_kind = btf_kind(d->btf->types[c_id]); + /* + * Resolve FWD into STRUCT/UNION. + * It's ok to resolve FWD into STRUCT/UNION that's not yet + * mapped to canonical representative (as opposed to + * STRUCT/UNION <--> STRUCT/UNION mapping logic below), because + * eventually that struct is going to be mapped and all resolved + * FWDs will automatically resolve to correct canonical + * representative. This will happen before ref type deduping, + * which critically depends on stability of these mapping. This + * stability is not a requirement for STRUCT/UNION equivalence + * checks, though. + */ + if (t_kind != BTF_KIND_FWD && c_kind == BTF_KIND_FWD) + d->map[c_id] = t_id; + else if (t_kind == BTF_KIND_FWD && c_kind != BTF_KIND_FWD) + d->map[t_id] = c_id; + + if ((t_kind == BTF_KIND_STRUCT || t_kind == BTF_KIND_UNION) && + c_kind != BTF_KIND_FWD && + is_type_mapped(d, c_id) && + !is_type_mapped(d, t_id)) { + /* + * as a perf optimization, we can map struct/union + * that's part of type graph we just verified for + * equivalence. We can do that for struct/union that has + * canonical representative only, though. + */ + d->map[t_id] = c_id; + } + } +} + +/* + * Deduplicate struct/union types. + * + * For each struct/union type its type signature hash is calculated, taking + * into account type's name, size, number, order and names of fields, but + * ignoring type ID's referenced from fields, because they might not be deduped + * completely until after reference types deduplication phase. This type hash + * is used to iterate over all potential canonical types, sharing same hash. + * For each canonical candidate we check whether type graphs that they form + * (through referenced types in fields and so on) are equivalent using algorithm + * implemented in `btf_dedup_is_equiv`. If such equivalence is found and + * BTF_KIND_FWD resolution is allowed, then hypothetical mapping + * (btf_dedup->hypot_map) produced by aforementioned type graph equivalence + * algorithm is used to record FWD -> STRUCT/UNION mapping. It's also used to + * potentially map other structs/unions to their canonical representatives, + * if such relationship hasn't yet been established. This speeds up algorithm + * by eliminating some of the duplicate work. + * + * If no matching canonical representative was found, struct/union is marked + * as canonical for itself and is added into btf_dedup->dedup_table hash map + * for further look ups. + */ +static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) +{ + struct btf_type *cand_type, *t; + struct hashmap_entry *hash_entry; + /* if we don't find equivalent type, then we are canonical */ + __u32 new_id = type_id; + __u16 kind; + long h; + + /* already deduped or is in process of deduping (loop detected) */ + if (d->map[type_id] <= BTF_MAX_NR_TYPES) + return 0; + + t = d->btf->types[type_id]; + kind = btf_kind(t); + + if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION) + return 0; + + h = btf_hash_struct(t); + for_each_dedup_cand(d, hash_entry, h) { + __u32 cand_id = (__u32)(long)hash_entry->value; + int eq; + + /* + * Even though btf_dedup_is_equiv() checks for + * btf_shallow_equal_struct() internally when checking two + * structs (unions) for equivalence, we need to guard here + * from picking matching FWD type as a dedup candidate. + * This can happen due to hash collision. In such case just + * relying on btf_dedup_is_equiv() would lead to potentially + * creating a loop (FWD -> STRUCT and STRUCT -> FWD), because + * FWD and compatible STRUCT/UNION are considered equivalent. + */ + cand_type = d->btf->types[cand_id]; + if (!btf_shallow_equal_struct(t, cand_type)) + continue; + + btf_dedup_clear_hypot_map(d); + eq = btf_dedup_is_equiv(d, type_id, cand_id); + if (eq < 0) + return eq; + if (!eq) + continue; + new_id = cand_id; + btf_dedup_merge_hypot_map(d); + break; + } + + d->map[type_id] = new_id; + if (type_id == new_id && btf_dedup_table_add(d, h, type_id)) + return -ENOMEM; + + return 0; +} + +static int btf_dedup_struct_types(struct btf_dedup *d) +{ + int i, err; + + for (i = 1; i <= d->btf->nr_types; i++) { + err = btf_dedup_struct_type(d, i); + if (err) + return err; + } + return 0; +} + +/* + * Deduplicate reference type. + * + * Once all primitive and struct/union types got deduplicated, we can easily + * deduplicate all other (reference) BTF types. This is done in two steps: + * + * 1. Resolve all referenced type IDs into their canonical type IDs. This + * resolution can be done either immediately for primitive or struct/union types + * (because they were deduped in previous two phases) or recursively for + * reference types. Recursion will always terminate at either primitive or + * struct/union type, at which point we can "unwind" chain of reference types + * one by one. There is no danger of encountering cycles because in C type + * system the only way to form type cycle is through struct/union, so any chain + * of reference types, even those taking part in a type cycle, will inevitably + * reach struct/union at some point. + * + * 2. Once all referenced type IDs are resolved into canonical ones, BTF type + * becomes "stable", in the sense that no further deduplication will cause + * any changes to it. With that, it's now possible to calculate type's signature + * hash (this time taking into account referenced type IDs) and loop over all + * potential canonical representatives. If no match was found, current type + * will become canonical representative of itself and will be added into + * btf_dedup->dedup_table as another possible canonical representative. + */ +static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) +{ + struct hashmap_entry *hash_entry; + __u32 new_id = type_id, cand_id; + struct btf_type *t, *cand; + /* if we don't find equivalent type, then we are representative type */ + int ref_type_id; + long h; + + if (d->map[type_id] == BTF_IN_PROGRESS_ID) + return -ELOOP; + if (d->map[type_id] <= BTF_MAX_NR_TYPES) + return resolve_type_id(d, type_id); + + t = d->btf->types[type_id]; + d->map[type_id] = BTF_IN_PROGRESS_ID; + + switch (btf_kind(t)) { + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + ref_type_id = btf_dedup_ref_type(d, t->type); + if (ref_type_id < 0) + return ref_type_id; + t->type = ref_type_id; + + h = btf_hash_common(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = d->btf->types[cand_id]; + if (btf_equal_common(t, cand)) { + new_id = cand_id; + break; + } + } + break; + + case BTF_KIND_ARRAY: { + struct btf_array *info = btf_array(t); + + ref_type_id = btf_dedup_ref_type(d, info->type); + if (ref_type_id < 0) + return ref_type_id; + info->type = ref_type_id; + + ref_type_id = btf_dedup_ref_type(d, info->index_type); + if (ref_type_id < 0) + return ref_type_id; + info->index_type = ref_type_id; + + h = btf_hash_array(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = d->btf->types[cand_id]; + if (btf_equal_array(t, cand)) { + new_id = cand_id; + break; + } + } + break; + } + + case BTF_KIND_FUNC_PROTO: { + struct btf_param *param; + __u16 vlen; + int i; + + ref_type_id = btf_dedup_ref_type(d, t->type); + if (ref_type_id < 0) + return ref_type_id; + t->type = ref_type_id; + + vlen = btf_vlen(t); + param = btf_params(t); + for (i = 0; i < vlen; i++) { + ref_type_id = btf_dedup_ref_type(d, param->type); + if (ref_type_id < 0) + return ref_type_id; + param->type = ref_type_id; + param++; + } + + h = btf_hash_fnproto(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = d->btf->types[cand_id]; + if (btf_equal_fnproto(t, cand)) { + new_id = cand_id; + break; + } + } + break; + } + + default: + return -EINVAL; + } + + d->map[type_id] = new_id; + if (type_id == new_id && btf_dedup_table_add(d, h, type_id)) + return -ENOMEM; + + return new_id; +} + +static int btf_dedup_ref_types(struct btf_dedup *d) +{ + int i, err; + + for (i = 1; i <= d->btf->nr_types; i++) { + err = btf_dedup_ref_type(d, i); + if (err < 0) + return err; + } + /* we won't need d->dedup_table anymore */ + hashmap__free(d->dedup_table); + d->dedup_table = NULL; + return 0; +} + +/* + * Compact types. + * + * After we established for each type its corresponding canonical representative + * type, we now can eliminate types that are not canonical and leave only + * canonical ones layed out sequentially in memory by copying them over + * duplicates. During compaction btf_dedup->hypot_map array is reused to store + * a map from original type ID to a new compacted type ID, which will be used + * during next phase to "fix up" type IDs, referenced from struct/union and + * reference types. + */ +static int btf_dedup_compact_types(struct btf_dedup *d) +{ + struct btf_type **new_types; + __u32 next_type_id = 1; + char *types_start, *p; + int i, len; + + /* we are going to reuse hypot_map to store compaction remapping */ + d->hypot_map[0] = 0; + for (i = 1; i <= d->btf->nr_types; i++) + d->hypot_map[i] = BTF_UNPROCESSED_ID; + + types_start = d->btf->nohdr_data + d->btf->hdr->type_off; + p = types_start; + + for (i = 1; i <= d->btf->nr_types; i++) { + if (d->map[i] != i) + continue; + + len = btf_type_size(d->btf->types[i]); + if (len < 0) + return len; + + memmove(p, d->btf->types[i], len); + d->hypot_map[i] = next_type_id; + d->btf->types[next_type_id] = (struct btf_type *)p; + p += len; + next_type_id++; + } + + /* shrink struct btf's internal types index and update btf_header */ + d->btf->nr_types = next_type_id - 1; + d->btf->types_size = d->btf->nr_types; + d->btf->hdr->type_len = p - types_start; + new_types = realloc(d->btf->types, + (1 + d->btf->nr_types) * sizeof(struct btf_type *)); + if (!new_types) + return -ENOMEM; + d->btf->types = new_types; + + /* make sure string section follows type information without gaps */ + d->btf->hdr->str_off = p - (char *)d->btf->nohdr_data; + memmove(p, d->btf->strings, d->btf->hdr->str_len); + d->btf->strings = p; + p += d->btf->hdr->str_len; + + d->btf->data_size = p - (char *)d->btf->data; + return 0; +} + +/* + * Figure out final (deduplicated and compacted) type ID for provided original + * `type_id` by first resolving it into corresponding canonical type ID and + * then mapping it to a deduplicated type ID, stored in btf_dedup->hypot_map, + * which is populated during compaction phase. + */ +static int btf_dedup_remap_type_id(struct btf_dedup *d, __u32 type_id) +{ + __u32 resolved_type_id, new_type_id; + + resolved_type_id = resolve_type_id(d, type_id); + new_type_id = d->hypot_map[resolved_type_id]; + if (new_type_id > BTF_MAX_NR_TYPES) + return -EINVAL; + return new_type_id; +} + +/* + * Remap referenced type IDs into deduped type IDs. + * + * After BTF types are deduplicated and compacted, their final type IDs may + * differ from original ones. The map from original to a corresponding + * deduped type ID is stored in btf_dedup->hypot_map and is populated during + * compaction phase. During remapping phase we are rewriting all type IDs + * referenced from any BTF type (e.g., struct fields, func proto args, etc) to + * their final deduped type IDs. + */ +static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) +{ + struct btf_type *t = d->btf->types[type_id]; + int i, r; + + switch (btf_kind(t)) { + case BTF_KIND_INT: + case BTF_KIND_ENUM: + break; + + case BTF_KIND_FWD: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_VAR: + r = btf_dedup_remap_type_id(d, t->type); + if (r < 0) + return r; + t->type = r; + break; + + case BTF_KIND_ARRAY: { + struct btf_array *arr_info = btf_array(t); + + r = btf_dedup_remap_type_id(d, arr_info->type); + if (r < 0) + return r; + arr_info->type = r; + r = btf_dedup_remap_type_id(d, arr_info->index_type); + if (r < 0) + return r; + arr_info->index_type = r; + break; + } + + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + struct btf_member *member = btf_members(t); + __u16 vlen = btf_vlen(t); + + for (i = 0; i < vlen; i++) { + r = btf_dedup_remap_type_id(d, member->type); + if (r < 0) + return r; + member->type = r; + member++; + } + break; + } + + case BTF_KIND_FUNC_PROTO: { + struct btf_param *param = btf_params(t); + __u16 vlen = btf_vlen(t); + + r = btf_dedup_remap_type_id(d, t->type); + if (r < 0) + return r; + t->type = r; + + for (i = 0; i < vlen; i++) { + r = btf_dedup_remap_type_id(d, param->type); + if (r < 0) + return r; + param->type = r; + param++; + } + break; + } + + case BTF_KIND_DATASEC: { + struct btf_var_secinfo *var = btf_var_secinfos(t); + __u16 vlen = btf_vlen(t); + + for (i = 0; i < vlen; i++) { + r = btf_dedup_remap_type_id(d, var->type); + if (r < 0) + return r; + var->type = r; + var++; + } + break; + } + + default: + return -EINVAL; + } + + return 0; +} + +static int btf_dedup_remap_types(struct btf_dedup *d) +{ + int i, r; + + for (i = 1; i <= d->btf->nr_types; i++) { + r = btf_dedup_remap_type(d, i); + if (r < 0) + return r; + } + return 0; +} diff --git a/src/contrib/libbpf/bpf/btf.h b/src/contrib/libbpf/bpf/btf.h new file mode 100644 index 0000000..d9ac73a --- /dev/null +++ b/src/contrib/libbpf/bpf/btf.h @@ -0,0 +1,311 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2018 Facebook */ + +#ifndef __LIBBPF_BTF_H +#define __LIBBPF_BTF_H + +#include <stdarg.h> +#include <linux/btf.h> +#include <linux/types.h> + +#ifdef __cplusplus +extern "C" { +#endif + +#ifndef LIBBPF_API +#define LIBBPF_API __attribute__((visibility("default"))) +#endif + +#define BTF_ELF_SEC ".BTF" +#define BTF_EXT_ELF_SEC ".BTF.ext" +#define MAPS_ELF_SEC ".maps" + +struct btf; +struct btf_ext; +struct btf_type; + +struct bpf_object; + +/* + * The .BTF.ext ELF section layout defined as + * struct btf_ext_header + * func_info subsection + * + * The func_info subsection layout: + * record size for struct bpf_func_info in the func_info subsection + * struct btf_sec_func_info for section #1 + * a list of bpf_func_info records for section #1 + * where struct bpf_func_info mimics one in include/uapi/linux/bpf.h + * but may not be identical + * struct btf_sec_func_info for section #2 + * a list of bpf_func_info records for section #2 + * ...... + * + * Note that the bpf_func_info record size in .BTF.ext may not + * be the same as the one defined in include/uapi/linux/bpf.h. + * The loader should ensure that record_size meets minimum + * requirement and pass the record as is to the kernel. The + * kernel will handle the func_info properly based on its contents. + */ +struct btf_ext_header { + __u16 magic; + __u8 version; + __u8 flags; + __u32 hdr_len; + + /* All offsets are in bytes relative to the end of this header */ + __u32 func_info_off; + __u32 func_info_len; + __u32 line_info_off; + __u32 line_info_len; + + /* optional part of .BTF.ext header */ + __u32 field_reloc_off; + __u32 field_reloc_len; +}; + +LIBBPF_API void btf__free(struct btf *btf); +LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size); +LIBBPF_API struct btf *btf__parse_elf(const char *path, + struct btf_ext **btf_ext); +LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf); +LIBBPF_API int btf__load(struct btf *btf); +LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, + const char *type_name); +LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf, + const char *type_name, __u32 kind); +LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf); +LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, + __u32 id); +LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id); +LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); +LIBBPF_API int btf__fd(const struct btf *btf); +LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); +LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); +LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf); +LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, + __u32 expected_key_size, + __u32 expected_value_size, + __u32 *key_type_id, __u32 *value_type_id); + +LIBBPF_API struct btf_ext *btf_ext__new(__u8 *data, __u32 size); +LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext); +LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, + __u32 *size); +LIBBPF_API int btf_ext__reloc_func_info(const struct btf *btf, + const struct btf_ext *btf_ext, + const char *sec_name, __u32 insns_cnt, + void **func_info, __u32 *cnt); +LIBBPF_API int btf_ext__reloc_line_info(const struct btf *btf, + const struct btf_ext *btf_ext, + const char *sec_name, __u32 insns_cnt, + void **line_info, __u32 *cnt); +LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext); +LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext); + +struct btf_dedup_opts { + unsigned int dedup_table_size; + bool dont_resolve_fwds; +}; + +LIBBPF_API int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, + const struct btf_dedup_opts *opts); + +struct btf_dump; + +struct btf_dump_opts { + void *ctx; +}; + +typedef void (*btf_dump_printf_fn_t)(void *ctx, const char *fmt, va_list args); + +LIBBPF_API struct btf_dump *btf_dump__new(const struct btf *btf, + const struct btf_ext *btf_ext, + const struct btf_dump_opts *opts, + btf_dump_printf_fn_t printf_fn); +LIBBPF_API void btf_dump__free(struct btf_dump *d); + +LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); + +/* + * A set of helpers for easier BTF types handling + */ +static inline __u16 btf_kind(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info); +} + +static inline __u16 btf_vlen(const struct btf_type *t) +{ + return BTF_INFO_VLEN(t->info); +} + +static inline bool btf_kflag(const struct btf_type *t) +{ + return BTF_INFO_KFLAG(t->info); +} + +static inline bool btf_is_int(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_INT; +} + +static inline bool btf_is_ptr(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_PTR; +} + +static inline bool btf_is_array(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ARRAY; +} + +static inline bool btf_is_struct(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_STRUCT; +} + +static inline bool btf_is_union(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_UNION; +} + +static inline bool btf_is_composite(const struct btf_type *t) +{ + __u16 kind = btf_kind(t); + + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; +} + +static inline bool btf_is_enum(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM; +} + +static inline bool btf_is_fwd(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FWD; +} + +static inline bool btf_is_typedef(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_TYPEDEF; +} + +static inline bool btf_is_volatile(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_VOLATILE; +} + +static inline bool btf_is_const(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_CONST; +} + +static inline bool btf_is_restrict(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_RESTRICT; +} + +static inline bool btf_is_mod(const struct btf_type *t) +{ + __u16 kind = btf_kind(t); + + return kind == BTF_KIND_VOLATILE || + kind == BTF_KIND_CONST || + kind == BTF_KIND_RESTRICT; +} + +static inline bool btf_is_func(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FUNC; +} + +static inline bool btf_is_func_proto(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FUNC_PROTO; +} + +static inline bool btf_is_var(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_VAR; +} + +static inline bool btf_is_datasec(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_DATASEC; +} + +static inline __u8 btf_int_encoding(const struct btf_type *t) +{ + return BTF_INT_ENCODING(*(__u32 *)(t + 1)); +} + +static inline __u8 btf_int_offset(const struct btf_type *t) +{ + return BTF_INT_OFFSET(*(__u32 *)(t + 1)); +} + +static inline __u8 btf_int_bits(const struct btf_type *t) +{ + return BTF_INT_BITS(*(__u32 *)(t + 1)); +} + +static inline struct btf_array *btf_array(const struct btf_type *t) +{ + return (struct btf_array *)(t + 1); +} + +static inline struct btf_enum *btf_enum(const struct btf_type *t) +{ + return (struct btf_enum *)(t + 1); +} + +static inline struct btf_member *btf_members(const struct btf_type *t) +{ + return (struct btf_member *)(t + 1); +} + +/* Get bit offset of a member with specified index. */ +static inline __u32 btf_member_bit_offset(const struct btf_type *t, + __u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + bool kflag = btf_kflag(t); + + return kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset; +} +/* + * Get bitfield size of a member, assuming t is BTF_KIND_STRUCT or + * BTF_KIND_UNION. If member is not a bitfield, zero is returned. + */ +static inline __u32 btf_member_bitfield_size(const struct btf_type *t, + __u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + bool kflag = btf_kflag(t); + + return kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; +} + +static inline struct btf_param *btf_params(const struct btf_type *t) +{ + return (struct btf_param *)(t + 1); +} + +static inline struct btf_var *btf_var(const struct btf_type *t) +{ + return (struct btf_var *)(t + 1); +} + +static inline struct btf_var_secinfo * +btf_var_secinfos(const struct btf_type *t) +{ + return (struct btf_var_secinfo *)(t + 1); +} + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* __LIBBPF_BTF_H */ diff --git a/src/contrib/libbpf/bpf/btf_dump.c b/src/contrib/libbpf/bpf/btf_dump.c new file mode 100644 index 0000000..cb126d8 --- /dev/null +++ b/src/contrib/libbpf/bpf/btf_dump.c @@ -0,0 +1,1386 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C type converter. + * + * Copyright (c) 2019 Facebook + */ + +#include <stdbool.h> +#include <stddef.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <linux/err.h> +#include <linux/btf.h> +#include "btf.h" +#include "hashmap.h" +#include "libbpf.h" +#include "libbpf_internal.h" + +static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t"; +static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1; + +static const char *pfx(int lvl) +{ + return lvl >= PREFIX_CNT ? PREFIXES : &PREFIXES[PREFIX_CNT - lvl]; +} + +enum btf_dump_type_order_state { + NOT_ORDERED, + ORDERING, + ORDERED, +}; + +enum btf_dump_type_emit_state { + NOT_EMITTED, + EMITTING, + EMITTED, +}; + +/* per-type auxiliary state */ +struct btf_dump_type_aux_state { + /* topological sorting state */ + enum btf_dump_type_order_state order_state: 2; + /* emitting state used to determine the need for forward declaration */ + enum btf_dump_type_emit_state emit_state: 2; + /* whether forward declaration was already emitted */ + __u8 fwd_emitted: 1; + /* whether unique non-duplicate name was already assigned */ + __u8 name_resolved: 1; + /* whether type is referenced from any other type */ + __u8 referenced: 1; +}; + +struct btf_dump { + const struct btf *btf; + const struct btf_ext *btf_ext; + btf_dump_printf_fn_t printf_fn; + struct btf_dump_opts opts; + + /* per-type auxiliary state */ + struct btf_dump_type_aux_state *type_states; + /* per-type optional cached unique name, must be freed, if present */ + const char **cached_names; + + /* topo-sorted list of dependent type definitions */ + __u32 *emit_queue; + int emit_queue_cap; + int emit_queue_cnt; + + /* + * stack of type declarations (e.g., chain of modifiers, arrays, + * funcs, etc) + */ + __u32 *decl_stack; + int decl_stack_cap; + int decl_stack_cnt; + + /* maps struct/union/enum name to a number of name occurrences */ + struct hashmap *type_names; + /* + * maps typedef identifiers and enum value names to a number of such + * name occurrences + */ + struct hashmap *ident_names; +}; + +static size_t str_hash_fn(const void *key, void *ctx) +{ + const char *s = key; + size_t h = 0; + + while (*s) { + h = h * 31 + *s; + s++; + } + return h; +} + +static bool str_equal_fn(const void *a, const void *b, void *ctx) +{ + return strcmp(a, b) == 0; +} + +static const char *btf_name_of(const struct btf_dump *d, __u32 name_off) +{ + return btf__name_by_offset(d->btf, name_off); +} + +static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + d->printf_fn(d->opts.ctx, fmt, args); + va_end(args); +} + +struct btf_dump *btf_dump__new(const struct btf *btf, + const struct btf_ext *btf_ext, + const struct btf_dump_opts *opts, + btf_dump_printf_fn_t printf_fn) +{ + struct btf_dump *d; + int err; + + d = calloc(1, sizeof(struct btf_dump)); + if (!d) + return ERR_PTR(-ENOMEM); + + d->btf = btf; + d->btf_ext = btf_ext; + d->printf_fn = printf_fn; + d->opts.ctx = opts ? opts->ctx : NULL; + + d->type_names = hashmap__new(str_hash_fn, str_equal_fn, NULL); + if (IS_ERR(d->type_names)) { + err = PTR_ERR(d->type_names); + d->type_names = NULL; + btf_dump__free(d); + return ERR_PTR(err); + } + d->ident_names = hashmap__new(str_hash_fn, str_equal_fn, NULL); + if (IS_ERR(d->ident_names)) { + err = PTR_ERR(d->ident_names); + d->ident_names = NULL; + btf_dump__free(d); + return ERR_PTR(err); + } + + return d; +} + +void btf_dump__free(struct btf_dump *d) +{ + int i, cnt; + + if (!d) + return; + + free(d->type_states); + if (d->cached_names) { + /* any set cached name is owned by us and should be freed */ + for (i = 0, cnt = btf__get_nr_types(d->btf); i <= cnt; i++) { + if (d->cached_names[i]) + free((void *)d->cached_names[i]); + } + } + free(d->cached_names); + free(d->emit_queue); + free(d->decl_stack); + hashmap__free(d->type_names); + hashmap__free(d->ident_names); + + free(d); +} + +static int btf_dump_mark_referenced(struct btf_dump *d); +static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr); +static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id); + +/* + * Dump BTF type in a compilable C syntax, including all the necessary + * dependent types, necessary for compilation. If some of the dependent types + * were already emitted as part of previous btf_dump__dump_type() invocation + * for another type, they won't be emitted again. This API allows callers to + * filter out BTF types according to user-defined criterias and emitted only + * minimal subset of types, necessary to compile everything. Full struct/union + * definitions will still be emitted, even if the only usage is through + * pointer and could be satisfied with just a forward declaration. + * + * Dumping is done in two high-level passes: + * 1. Topologically sort type definitions to satisfy C rules of compilation. + * 2. Emit type definitions in C syntax. + * + * Returns 0 on success; <0, otherwise. + */ +int btf_dump__dump_type(struct btf_dump *d, __u32 id) +{ + int err, i; + + if (id > btf__get_nr_types(d->btf)) + return -EINVAL; + + /* type states are lazily allocated, as they might not be needed */ + if (!d->type_states) { + d->type_states = calloc(1 + btf__get_nr_types(d->btf), + sizeof(d->type_states[0])); + if (!d->type_states) + return -ENOMEM; + d->cached_names = calloc(1 + btf__get_nr_types(d->btf), + sizeof(d->cached_names[0])); + if (!d->cached_names) + return -ENOMEM; + + /* VOID is special */ + d->type_states[0].order_state = ORDERED; + d->type_states[0].emit_state = EMITTED; + + /* eagerly determine referenced types for anon enums */ + err = btf_dump_mark_referenced(d); + if (err) + return err; + } + + d->emit_queue_cnt = 0; + err = btf_dump_order_type(d, id, false); + if (err < 0) + return err; + + for (i = 0; i < d->emit_queue_cnt; i++) + btf_dump_emit_type(d, d->emit_queue[i], 0 /*top-level*/); + + return 0; +} + +/* + * Mark all types that are referenced from any other type. This is used to + * determine top-level anonymous enums that need to be emitted as an + * independent type declarations. + * Anonymous enums come in two flavors: either embedded in a struct's field + * definition, in which case they have to be declared inline as part of field + * type declaration; or as a top-level anonymous enum, typically used for + * declaring global constants. It's impossible to distinguish between two + * without knowning whether given enum type was referenced from other type: + * top-level anonymous enum won't be referenced by anything, while embedded + * one will. + */ +static int btf_dump_mark_referenced(struct btf_dump *d) +{ + int i, j, n = btf__get_nr_types(d->btf); + const struct btf_type *t; + __u16 vlen; + + for (i = 1; i <= n; i++) { + t = btf__type_by_id(d->btf, i); + vlen = btf_vlen(t); + + switch (btf_kind(t)) { + case BTF_KIND_INT: + case BTF_KIND_ENUM: + case BTF_KIND_FWD: + break; + + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_VAR: + d->type_states[t->type].referenced = 1; + break; + + case BTF_KIND_ARRAY: { + const struct btf_array *a = btf_array(t); + + d->type_states[a->index_type].referenced = 1; + d->type_states[a->type].referenced = 1; + break; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = btf_members(t); + + for (j = 0; j < vlen; j++, m++) + d->type_states[m->type].referenced = 1; + break; + } + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = btf_params(t); + + for (j = 0; j < vlen; j++, p++) + d->type_states[p->type].referenced = 1; + break; + } + case BTF_KIND_DATASEC: { + const struct btf_var_secinfo *v = btf_var_secinfos(t); + + for (j = 0; j < vlen; j++, v++) + d->type_states[v->type].referenced = 1; + break; + } + default: + return -EINVAL; + } + } + return 0; +} +static int btf_dump_add_emit_queue_id(struct btf_dump *d, __u32 id) +{ + __u32 *new_queue; + size_t new_cap; + + if (d->emit_queue_cnt >= d->emit_queue_cap) { + new_cap = max(16, d->emit_queue_cap * 3 / 2); + new_queue = realloc(d->emit_queue, + new_cap * sizeof(new_queue[0])); + if (!new_queue) + return -ENOMEM; + d->emit_queue = new_queue; + d->emit_queue_cap = new_cap; + } + + d->emit_queue[d->emit_queue_cnt++] = id; + return 0; +} + +/* + * Determine order of emitting dependent types and specified type to satisfy + * C compilation rules. This is done through topological sorting with an + * additional complication which comes from C rules. The main idea for C is + * that if some type is "embedded" into a struct/union, it's size needs to be + * known at the time of definition of containing type. E.g., for: + * + * struct A {}; + * struct B { struct A x; } + * + * struct A *HAS* to be defined before struct B, because it's "embedded", + * i.e., it is part of struct B layout. But in the following case: + * + * struct A; + * struct B { struct A *x; } + * struct A {}; + * + * it's enough to just have a forward declaration of struct A at the time of + * struct B definition, as struct B has a pointer to struct A, so the size of + * field x is known without knowing struct A size: it's sizeof(void *). + * + * Unfortunately, there are some trickier cases we need to handle, e.g.: + * + * struct A {}; // if this was forward-declaration: compilation error + * struct B { + * struct { // anonymous struct + * struct A y; + * } *x; + * }; + * + * In this case, struct B's field x is a pointer, so it's size is known + * regardless of the size of (anonymous) struct it points to. But because this + * struct is anonymous and thus defined inline inside struct B, *and* it + * embeds struct A, compiler requires full definition of struct A to be known + * before struct B can be defined. This creates a transitive dependency + * between struct A and struct B. If struct A was forward-declared before + * struct B definition and fully defined after struct B definition, that would + * trigger compilation error. + * + * All this means that while we are doing topological sorting on BTF type + * graph, we need to determine relationships between different types (graph + * nodes): + * - weak link (relationship) between X and Y, if Y *CAN* be + * forward-declared at the point of X definition; + * - strong link, if Y *HAS* to be fully-defined before X can be defined. + * + * The rule is as follows. Given a chain of BTF types from X to Y, if there is + * BTF_KIND_PTR type in the chain and at least one non-anonymous type + * Z (excluding X, including Y), then link is weak. Otherwise, it's strong. + * Weak/strong relationship is determined recursively during DFS traversal and + * is returned as a result from btf_dump_order_type(). + * + * btf_dump_order_type() is trying to avoid unnecessary forward declarations, + * but it is not guaranteeing that no extraneous forward declarations will be + * emitted. + * + * To avoid extra work, algorithm marks some of BTF types as ORDERED, when + * it's done with them, but not for all (e.g., VOLATILE, CONST, RESTRICT, + * ARRAY, FUNC_PROTO), as weak/strong semantics for those depends on the + * entire graph path, so depending where from one came to that BTF type, it + * might cause weak or strong ordering. For types like STRUCT/UNION/INT/ENUM, + * once they are processed, there is no need to do it again, so they are + * marked as ORDERED. We can mark PTR as ORDERED as well, as it semi-forces + * weak link, unless subsequent referenced STRUCT/UNION/ENUM is anonymous. But + * in any case, once those are processed, no need to do it again, as the + * result won't change. + * + * Returns: + * - 1, if type is part of strong link (so there is strong topological + * ordering requirements); + * - 0, if type is part of weak link (so can be satisfied through forward + * declaration); + * - <0, on error (e.g., unsatisfiable type loop detected). + */ +static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) +{ + /* + * Order state is used to detect strong link cycles, but only for BTF + * kinds that are or could be an independent definition (i.e., + * stand-alone fwd decl, enum, typedef, struct, union). Ptrs, arrays, + * func_protos, modifiers are just means to get to these definitions. + * Int/void don't need definitions, they are assumed to be always + * properly defined. We also ignore datasec, var, and funcs for now. + * So for all non-defining kinds, we never even set ordering state, + * for defining kinds we set ORDERING and subsequently ORDERED if it + * forms a strong link. + */ + struct btf_dump_type_aux_state *tstate = &d->type_states[id]; + const struct btf_type *t; + __u16 vlen; + int err, i; + + /* return true, letting typedefs know that it's ok to be emitted */ + if (tstate->order_state == ORDERED) + return 1; + + t = btf__type_by_id(d->btf, id); + + if (tstate->order_state == ORDERING) { + /* type loop, but resolvable through fwd declaration */ + if (btf_is_composite(t) && through_ptr && t->name_off != 0) + return 0; + pr_warn("unsatisfiable type cycle, id:[%u]\n", id); + return -ELOOP; + } + + switch (btf_kind(t)) { + case BTF_KIND_INT: + tstate->order_state = ORDERED; + return 0; + + case BTF_KIND_PTR: + err = btf_dump_order_type(d, t->type, true); + tstate->order_state = ORDERED; + return err; + + case BTF_KIND_ARRAY: + return btf_dump_order_type(d, btf_array(t)->type, through_ptr); + + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = btf_members(t); + /* + * struct/union is part of strong link, only if it's embedded + * (so no ptr in a path) or it's anonymous (so has to be + * defined inline, even if declared through ptr) + */ + if (through_ptr && t->name_off != 0) + return 0; + + tstate->order_state = ORDERING; + + vlen = btf_vlen(t); + for (i = 0; i < vlen; i++, m++) { + err = btf_dump_order_type(d, m->type, false); + if (err < 0) + return err; + } + + if (t->name_off != 0) { + err = btf_dump_add_emit_queue_id(d, id); + if (err < 0) + return err; + } + + tstate->order_state = ORDERED; + return 1; + } + case BTF_KIND_ENUM: + case BTF_KIND_FWD: + /* + * non-anonymous or non-referenced enums are top-level + * declarations and should be emitted. Same logic can be + * applied to FWDs, it won't hurt anyways. + */ + if (t->name_off != 0 || !tstate->referenced) { + err = btf_dump_add_emit_queue_id(d, id); + if (err) + return err; + } + tstate->order_state = ORDERED; + return 1; + + case BTF_KIND_TYPEDEF: { + int is_strong; + + is_strong = btf_dump_order_type(d, t->type, through_ptr); + if (is_strong < 0) + return is_strong; + + /* typedef is similar to struct/union w.r.t. fwd-decls */ + if (through_ptr && !is_strong) + return 0; + + /* typedef is always a named definition */ + err = btf_dump_add_emit_queue_id(d, id); + if (err) + return err; + + d->type_states[id].order_state = ORDERED; + return 1; + } + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + return btf_dump_order_type(d, t->type, through_ptr); + + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = btf_params(t); + bool is_strong; + + err = btf_dump_order_type(d, t->type, through_ptr); + if (err < 0) + return err; + is_strong = err > 0; + + vlen = btf_vlen(t); + for (i = 0; i < vlen; i++, p++) { + err = btf_dump_order_type(d, p->type, through_ptr); + if (err < 0) + return err; + if (err > 0) + is_strong = true; + } + return is_strong; + } + case BTF_KIND_FUNC: + case BTF_KIND_VAR: + case BTF_KIND_DATASEC: + d->type_states[id].order_state = ORDERED; + return 0; + + default: + return -EINVAL; + } +} + +static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id, + const struct btf_type *t); +static void btf_dump_emit_struct_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, int lvl); + +static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id, + const struct btf_type *t); +static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, int lvl); + +static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, + const struct btf_type *t); + +static void btf_dump_emit_typedef_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, int lvl); + +/* a local view into a shared stack */ +struct id_stack { + const __u32 *ids; + int cnt; +}; + +static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, + const char *fname, int lvl); +static void btf_dump_emit_type_chain(struct btf_dump *d, + struct id_stack *decl_stack, + const char *fname, int lvl); + +static const char *btf_dump_type_name(struct btf_dump *d, __u32 id); +static const char *btf_dump_ident_name(struct btf_dump *d, __u32 id); +static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map, + const char *orig_name); + +static bool btf_dump_is_blacklisted(struct btf_dump *d, __u32 id) +{ + const struct btf_type *t = btf__type_by_id(d->btf, id); + + /* __builtin_va_list is a compiler built-in, which causes compilation + * errors, when compiling w/ different compiler, then used to compile + * original code (e.g., GCC to compile kernel, Clang to use generated + * C header from BTF). As it is built-in, it should be already defined + * properly internally in compiler. + */ + if (t->name_off == 0) + return false; + return strcmp(btf_name_of(d, t->name_off), "__builtin_va_list") == 0; +} + +/* + * Emit C-syntax definitions of types from chains of BTF types. + * + * High-level handling of determining necessary forward declarations are handled + * by btf_dump_emit_type() itself, but all nitty-gritty details of emitting type + * declarations/definitions in C syntax are handled by a combo of + * btf_dump_emit_type_decl()/btf_dump_emit_type_chain() w/ delegation to + * corresponding btf_dump_emit_*_{def,fwd}() functions. + * + * We also keep track of "containing struct/union type ID" to determine when + * we reference it from inside and thus can avoid emitting unnecessary forward + * declaration. + * + * This algorithm is designed in such a way, that even if some error occurs + * (either technical, e.g., out of memory, or logical, i.e., malformed BTF + * that doesn't comply to C rules completely), algorithm will try to proceed + * and produce as much meaningful output as possible. + */ +static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) +{ + struct btf_dump_type_aux_state *tstate = &d->type_states[id]; + bool top_level_def = cont_id == 0; + const struct btf_type *t; + __u16 kind; + + if (tstate->emit_state == EMITTED) + return; + + t = btf__type_by_id(d->btf, id); + kind = btf_kind(t); + + if (tstate->emit_state == EMITTING) { + if (tstate->fwd_emitted) + return; + + switch (kind) { + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + /* + * if we are referencing a struct/union that we are + * part of - then no need for fwd declaration + */ + if (id == cont_id) + return; + if (t->name_off == 0) { + pr_warn("anonymous struct/union loop, id:[%u]\n", + id); + return; + } + btf_dump_emit_struct_fwd(d, id, t); + btf_dump_printf(d, ";\n\n"); + tstate->fwd_emitted = 1; + break; + case BTF_KIND_TYPEDEF: + /* + * for typedef fwd_emitted means typedef definition + * was emitted, but it can be used only for "weak" + * references through pointer only, not for embedding + */ + if (!btf_dump_is_blacklisted(d, id)) { + btf_dump_emit_typedef_def(d, id, t, 0); + btf_dump_printf(d, ";\n\n"); + }; + tstate->fwd_emitted = 1; + break; + default: + break; + } + + return; + } + + switch (kind) { + case BTF_KIND_INT: + tstate->emit_state = EMITTED; + break; + case BTF_KIND_ENUM: + if (top_level_def) { + btf_dump_emit_enum_def(d, id, t, 0); + btf_dump_printf(d, ";\n\n"); + } + tstate->emit_state = EMITTED; + break; + case BTF_KIND_PTR: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + btf_dump_emit_type(d, t->type, cont_id); + break; + case BTF_KIND_ARRAY: + btf_dump_emit_type(d, btf_array(t)->type, cont_id); + break; + case BTF_KIND_FWD: + btf_dump_emit_fwd_def(d, id, t); + btf_dump_printf(d, ";\n\n"); + tstate->emit_state = EMITTED; + break; + case BTF_KIND_TYPEDEF: + tstate->emit_state = EMITTING; + btf_dump_emit_type(d, t->type, id); + /* + * typedef can server as both definition and forward + * declaration; at this stage someone depends on + * typedef as a forward declaration (refers to it + * through pointer), so unless we already did it, + * emit typedef as a forward declaration + */ + if (!tstate->fwd_emitted && !btf_dump_is_blacklisted(d, id)) { + btf_dump_emit_typedef_def(d, id, t, 0); + btf_dump_printf(d, ";\n\n"); + } + tstate->emit_state = EMITTED; + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + tstate->emit_state = EMITTING; + /* if it's a top-level struct/union definition or struct/union + * is anonymous, then in C we'll be emitting all fields and + * their types (as opposed to just `struct X`), so we need to + * make sure that all types, referenced from struct/union + * members have necessary forward-declarations, where + * applicable + */ + if (top_level_def || t->name_off == 0) { + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); + int i, new_cont_id; + + new_cont_id = t->name_off == 0 ? cont_id : id; + for (i = 0; i < vlen; i++, m++) + btf_dump_emit_type(d, m->type, new_cont_id); + } else if (!tstate->fwd_emitted && id != cont_id) { + btf_dump_emit_struct_fwd(d, id, t); + btf_dump_printf(d, ";\n\n"); + tstate->fwd_emitted = 1; + } + + if (top_level_def) { + btf_dump_emit_struct_def(d, id, t, 0); + btf_dump_printf(d, ";\n\n"); + tstate->emit_state = EMITTED; + } else { + tstate->emit_state = NOT_EMITTED; + } + break; + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = btf_params(t); + __u16 vlen = btf_vlen(t); + int i; + + btf_dump_emit_type(d, t->type, cont_id); + for (i = 0; i < vlen; i++, p++) + btf_dump_emit_type(d, p->type, cont_id); + + break; + } + default: + break; + } +} + +static int btf_align_of(const struct btf *btf, __u32 id) +{ + const struct btf_type *t = btf__type_by_id(btf, id); + __u16 kind = btf_kind(t); + + switch (kind) { + case BTF_KIND_INT: + case BTF_KIND_ENUM: + return min(sizeof(void *), t->size); + case BTF_KIND_PTR: + return sizeof(void *); + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + return btf_align_of(btf, t->type); + case BTF_KIND_ARRAY: + return btf_align_of(btf, btf_array(t)->type); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); + int i, align = 1; + + for (i = 0; i < vlen; i++, m++) + align = max(align, btf_align_of(btf, m->type)); + + return align; + } + default: + pr_warn("unsupported BTF_KIND:%u\n", btf_kind(t)); + return 1; + } +} + +static bool btf_is_struct_packed(const struct btf *btf, __u32 id, + const struct btf_type *t) +{ + const struct btf_member *m; + int align, i, bit_sz; + __u16 vlen; + + align = btf_align_of(btf, id); + /* size of a non-packed struct has to be a multiple of its alignment*/ + if (t->size % align) + return true; + + m = btf_members(t); + vlen = btf_vlen(t); + /* all non-bitfield fields have to be naturally aligned */ + for (i = 0; i < vlen; i++, m++) { + align = btf_align_of(btf, m->type); + bit_sz = btf_member_bitfield_size(t, i); + if (bit_sz == 0 && m->offset % (8 * align) != 0) + return true; + } + + /* + * if original struct was marked as packed, but its layout is + * naturally aligned, we'll detect that it's not packed + */ + return false; +} + +static int chip_away_bits(int total, int at_most) +{ + return total % at_most ? : at_most; +} + +static void btf_dump_emit_bit_padding(const struct btf_dump *d, + int cur_off, int m_off, int m_bit_sz, + int align, int lvl) +{ + int off_diff = m_off - cur_off; + int ptr_bits = sizeof(void *) * 8; + + if (off_diff <= 0) + /* no gap */ + return; + if (m_bit_sz == 0 && off_diff < align * 8) + /* natural padding will take care of a gap */ + return; + + while (off_diff > 0) { + const char *pad_type; + int pad_bits; + + if (ptr_bits > 32 && off_diff > 32) { + pad_type = "long"; + pad_bits = chip_away_bits(off_diff, ptr_bits); + } else if (off_diff > 16) { + pad_type = "int"; + pad_bits = chip_away_bits(off_diff, 32); + } else if (off_diff > 8) { + pad_type = "short"; + pad_bits = chip_away_bits(off_diff, 16); + } else { + pad_type = "char"; + pad_bits = chip_away_bits(off_diff, 8); + } + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits); + off_diff -= pad_bits; + } +} + +static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id, + const struct btf_type *t) +{ + btf_dump_printf(d, "%s %s", + btf_is_struct(t) ? "struct" : "union", + btf_dump_type_name(d, id)); +} + +static void btf_dump_emit_struct_def(struct btf_dump *d, + __u32 id, + const struct btf_type *t, + int lvl) +{ + const struct btf_member *m = btf_members(t); + bool is_struct = btf_is_struct(t); + int align, i, packed, off = 0; + __u16 vlen = btf_vlen(t); + + packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0; + + btf_dump_printf(d, "%s%s%s {", + is_struct ? "struct" : "union", + t->name_off ? " " : "", + btf_dump_type_name(d, id)); + + for (i = 0; i < vlen; i++, m++) { + const char *fname; + int m_off, m_sz; + + fname = btf_name_of(d, m->name_off); + m_sz = btf_member_bitfield_size(t, i); + m_off = btf_member_bit_offset(t, i); + align = packed ? 1 : btf_align_of(d->btf, m->type); + + btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1); + btf_dump_printf(d, "\n%s", pfx(lvl + 1)); + btf_dump_emit_type_decl(d, m->type, fname, lvl + 1); + + if (m_sz) { + btf_dump_printf(d, ": %d", m_sz); + off = m_off + m_sz; + } else { + m_sz = max(0, btf__resolve_size(d->btf, m->type)); + off = m_off + m_sz * 8; + } + btf_dump_printf(d, ";"); + } + + /* pad at the end, if necessary */ + if (is_struct) { + align = packed ? 1 : btf_align_of(d->btf, id); + btf_dump_emit_bit_padding(d, off, t->size * 8, 0, align, + lvl + 1); + } + + if (vlen) + btf_dump_printf(d, "\n"); + btf_dump_printf(d, "%s}", pfx(lvl)); + if (packed) + btf_dump_printf(d, " __attribute__((packed))"); +} + +static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id, + const struct btf_type *t) +{ + btf_dump_printf(d, "enum %s", btf_dump_type_name(d, id)); +} + +static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, + int lvl) +{ + const struct btf_enum *v = btf_enum(t); + __u16 vlen = btf_vlen(t); + const char *name; + size_t dup_cnt; + int i; + + btf_dump_printf(d, "enum%s%s", + t->name_off ? " " : "", + btf_dump_type_name(d, id)); + + if (vlen) { + btf_dump_printf(d, " {"); + for (i = 0; i < vlen; i++, v++) { + name = btf_name_of(d, v->name_off); + /* enumerators share namespace with typedef idents */ + dup_cnt = btf_dump_name_dups(d, d->ident_names, name); + if (dup_cnt > 1) { + btf_dump_printf(d, "\n%s%s___%zu = %d,", + pfx(lvl + 1), name, dup_cnt, + (__s32)v->val); + } else { + btf_dump_printf(d, "\n%s%s = %d,", + pfx(lvl + 1), name, + (__s32)v->val); + } + } + btf_dump_printf(d, "\n%s}", pfx(lvl)); + } +} + +static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, + const struct btf_type *t) +{ + const char *name = btf_dump_type_name(d, id); + + if (btf_kflag(t)) + btf_dump_printf(d, "union %s", name); + else + btf_dump_printf(d, "struct %s", name); +} + +static void btf_dump_emit_typedef_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, int lvl) +{ + const char *name = btf_dump_ident_name(d, id); + + /* + * Old GCC versions are emitting invalid typedef for __gnuc_va_list + * pointing to VOID. This generates warnings from btf_dump() and + * results in uncompilable header file, so we are fixing it up here + * with valid typedef into __builtin_va_list. + */ + if (t->type == 0 && strcmp(name, "__gnuc_va_list") == 0) { + btf_dump_printf(d, "typedef __builtin_va_list __gnuc_va_list"); + return; + } + + btf_dump_printf(d, "typedef "); + btf_dump_emit_type_decl(d, t->type, name, lvl); +} + +static int btf_dump_push_decl_stack_id(struct btf_dump *d, __u32 id) +{ + __u32 *new_stack; + size_t new_cap; + + if (d->decl_stack_cnt >= d->decl_stack_cap) { + new_cap = max(16, d->decl_stack_cap * 3 / 2); + new_stack = realloc(d->decl_stack, + new_cap * sizeof(new_stack[0])); + if (!new_stack) + return -ENOMEM; + d->decl_stack = new_stack; + d->decl_stack_cap = new_cap; + } + + d->decl_stack[d->decl_stack_cnt++] = id; + + return 0; +} + +/* + * Emit type declaration (e.g., field type declaration in a struct or argument + * declaration in function prototype) in correct C syntax. + * + * For most types it's trivial, but there are few quirky type declaration + * cases worth mentioning: + * - function prototypes (especially nesting of function prototypes); + * - arrays; + * - const/volatile/restrict for pointers vs other types. + * + * For a good discussion of *PARSING* C syntax (as a human), see + * Peter van der Linden's "Expert C Programming: Deep C Secrets", + * Ch.3 "Unscrambling Declarations in C". + * + * It won't help with BTF to C conversion much, though, as it's an opposite + * problem. So we came up with this algorithm in reverse to van der Linden's + * parsing algorithm. It goes from structured BTF representation of type + * declaration to a valid compilable C syntax. + * + * For instance, consider this C typedef: + * typedef const int * const * arr[10] arr_t; + * It will be represented in BTF with this chain of BTF types: + * [typedef] -> [array] -> [ptr] -> [const] -> [ptr] -> [const] -> [int] + * + * Notice how [const] modifier always goes before type it modifies in BTF type + * graph, but in C syntax, const/volatile/restrict modifiers are written to + * the right of pointers, but to the left of other types. There are also other + * quirks, like function pointers, arrays of them, functions returning other + * functions, etc. + * + * We handle that by pushing all the types to a stack, until we hit "terminal" + * type (int/enum/struct/union/fwd). Then depending on the kind of a type on + * top of a stack, modifiers are handled differently. Array/function pointers + * have also wildly different syntax and how nesting of them are done. See + * code for authoritative definition. + * + * To avoid allocating new stack for each independent chain of BTF types, we + * share one bigger stack, with each chain working only on its own local view + * of a stack frame. Some care is required to "pop" stack frames after + * processing type declaration chain. + */ +static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, + const char *fname, int lvl) +{ + struct id_stack decl_stack; + const struct btf_type *t; + int err, stack_start; + + stack_start = d->decl_stack_cnt; + for (;;) { + err = btf_dump_push_decl_stack_id(d, id); + if (err < 0) { + /* + * if we don't have enough memory for entire type decl + * chain, restore stack, emit warning, and try to + * proceed nevertheless + */ + pr_warn("not enough memory for decl stack:%d", err); + d->decl_stack_cnt = stack_start; + return; + } + + /* VOID */ + if (id == 0) + break; + + t = btf__type_by_id(d->btf, id); + switch (btf_kind(t)) { + case BTF_KIND_PTR: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_FUNC_PROTO: + id = t->type; + break; + case BTF_KIND_ARRAY: + id = btf_array(t)->type; + break; + case BTF_KIND_INT: + case BTF_KIND_ENUM: + case BTF_KIND_FWD: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_TYPEDEF: + goto done; + default: + pr_warn("unexpected type in decl chain, kind:%u, id:[%u]\n", + btf_kind(t), id); + goto done; + } + } +done: + /* + * We might be inside a chain of declarations (e.g., array of function + * pointers returning anonymous (so inlined) structs, having another + * array field). Each of those needs its own "stack frame" to handle + * emitting of declarations. Those stack frames are non-overlapping + * portions of shared btf_dump->decl_stack. To make it a bit nicer to + * handle this set of nested stacks, we create a view corresponding to + * our own "stack frame" and work with it as an independent stack. + * We'll need to clean up after emit_type_chain() returns, though. + */ + decl_stack.ids = d->decl_stack + stack_start; + decl_stack.cnt = d->decl_stack_cnt - stack_start; + btf_dump_emit_type_chain(d, &decl_stack, fname, lvl); + /* + * emit_type_chain() guarantees that it will pop its entire decl_stack + * frame before returning. But it works with a read-only view into + * decl_stack, so it doesn't actually pop anything from the + * perspective of shared btf_dump->decl_stack, per se. We need to + * reset decl_stack state to how it was before us to avoid it growing + * all the time. + */ + d->decl_stack_cnt = stack_start; +} + +static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack) +{ + const struct btf_type *t; + __u32 id; + + while (decl_stack->cnt) { + id = decl_stack->ids[decl_stack->cnt - 1]; + t = btf__type_by_id(d->btf, id); + + switch (btf_kind(t)) { + case BTF_KIND_VOLATILE: + btf_dump_printf(d, "volatile "); + break; + case BTF_KIND_CONST: + btf_dump_printf(d, "const "); + break; + case BTF_KIND_RESTRICT: + btf_dump_printf(d, "restrict "); + break; + default: + return; + } + decl_stack->cnt--; + } +} + +static void btf_dump_emit_name(const struct btf_dump *d, + const char *name, bool last_was_ptr) +{ + bool separate = name[0] && !last_was_ptr; + + btf_dump_printf(d, "%s%s", separate ? " " : "", name); +} + +static void btf_dump_emit_type_chain(struct btf_dump *d, + struct id_stack *decls, + const char *fname, int lvl) +{ + /* + * last_was_ptr is used to determine if we need to separate pointer + * asterisk (*) from previous part of type signature with space, so + * that we get `int ***`, instead of `int * * *`. We default to true + * for cases where we have single pointer in a chain. E.g., in ptr -> + * func_proto case. func_proto will start a new emit_type_chain call + * with just ptr, which should be emitted as (*) or (*<fname>), so we + * don't want to prepend space for that last pointer. + */ + bool last_was_ptr = true; + const struct btf_type *t; + const char *name; + __u16 kind; + __u32 id; + + while (decls->cnt) { + id = decls->ids[--decls->cnt]; + if (id == 0) { + /* VOID is a special snowflake */ + btf_dump_emit_mods(d, decls); + btf_dump_printf(d, "void"); + last_was_ptr = false; + continue; + } + + t = btf__type_by_id(d->btf, id); + kind = btf_kind(t); + + switch (kind) { + case BTF_KIND_INT: + btf_dump_emit_mods(d, decls); + name = btf_name_of(d, t->name_off); + btf_dump_printf(d, "%s", name); + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + btf_dump_emit_mods(d, decls); + /* inline anonymous struct/union */ + if (t->name_off == 0) + btf_dump_emit_struct_def(d, id, t, lvl); + else + btf_dump_emit_struct_fwd(d, id, t); + break; + case BTF_KIND_ENUM: + btf_dump_emit_mods(d, decls); + /* inline anonymous enum */ + if (t->name_off == 0) + btf_dump_emit_enum_def(d, id, t, lvl); + else + btf_dump_emit_enum_fwd(d, id, t); + break; + case BTF_KIND_FWD: + btf_dump_emit_mods(d, decls); + btf_dump_emit_fwd_def(d, id, t); + break; + case BTF_KIND_TYPEDEF: + btf_dump_emit_mods(d, decls); + btf_dump_printf(d, "%s", btf_dump_ident_name(d, id)); + break; + case BTF_KIND_PTR: + btf_dump_printf(d, "%s", last_was_ptr ? "*" : " *"); + break; + case BTF_KIND_VOLATILE: + btf_dump_printf(d, " volatile"); + break; + case BTF_KIND_CONST: + btf_dump_printf(d, " const"); + break; + case BTF_KIND_RESTRICT: + btf_dump_printf(d, " restrict"); + break; + case BTF_KIND_ARRAY: { + const struct btf_array *a = btf_array(t); + const struct btf_type *next_t; + __u32 next_id; + bool multidim; + /* + * GCC has a bug + * (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=8354) + * which causes it to emit extra const/volatile + * modifiers for an array, if array's element type has + * const/volatile modifiers. Clang doesn't do that. + * In general, it doesn't seem very meaningful to have + * a const/volatile modifier for array, so we are + * going to silently skip them here. + */ + while (decls->cnt) { + next_id = decls->ids[decls->cnt - 1]; + next_t = btf__type_by_id(d->btf, next_id); + if (btf_is_mod(next_t)) + decls->cnt--; + else + break; + } + + if (decls->cnt == 0) { + btf_dump_emit_name(d, fname, last_was_ptr); + btf_dump_printf(d, "[%u]", a->nelems); + return; + } + + next_id = decls->ids[decls->cnt - 1]; + next_t = btf__type_by_id(d->btf, next_id); + multidim = btf_is_array(next_t); + /* we need space if we have named non-pointer */ + if (fname[0] && !last_was_ptr) + btf_dump_printf(d, " "); + /* no parentheses for multi-dimensional array */ + if (!multidim) + btf_dump_printf(d, "("); + btf_dump_emit_type_chain(d, decls, fname, lvl); + if (!multidim) + btf_dump_printf(d, ")"); + btf_dump_printf(d, "[%u]", a->nelems); + return; + } + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = btf_params(t); + __u16 vlen = btf_vlen(t); + int i; + + btf_dump_emit_mods(d, decls); + if (decls->cnt) { + btf_dump_printf(d, " ("); + btf_dump_emit_type_chain(d, decls, fname, lvl); + btf_dump_printf(d, ")"); + } else { + btf_dump_emit_name(d, fname, last_was_ptr); + } + btf_dump_printf(d, "("); + /* + * Clang for BPF target generates func_proto with no + * args as a func_proto with a single void arg (e.g., + * `int (*f)(void)` vs just `int (*f)()`). We are + * going to pretend there are no args for such case. + */ + if (vlen == 1 && p->type == 0) { + btf_dump_printf(d, ")"); + return; + } + + for (i = 0; i < vlen; i++, p++) { + if (i > 0) + btf_dump_printf(d, ", "); + + /* last arg of type void is vararg */ + if (i == vlen - 1 && p->type == 0) { + btf_dump_printf(d, "..."); + break; + } + + name = btf_name_of(d, p->name_off); + btf_dump_emit_type_decl(d, p->type, name, lvl); + } + + btf_dump_printf(d, ")"); + return; + } + default: + pr_warn("unexpected type in decl chain, kind:%u, id:[%u]\n", + kind, id); + return; + } + + last_was_ptr = kind == BTF_KIND_PTR; + } + + btf_dump_emit_name(d, fname, last_was_ptr); +} + +/* return number of duplicates (occurrences) of a given name */ +static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map, + const char *orig_name) +{ + size_t dup_cnt = 0; + + hashmap__find(name_map, orig_name, (void **)&dup_cnt); + dup_cnt++; + hashmap__set(name_map, orig_name, (void *)dup_cnt, NULL, NULL); + + return dup_cnt; +} + +static const char *btf_dump_resolve_name(struct btf_dump *d, __u32 id, + struct hashmap *name_map) +{ + struct btf_dump_type_aux_state *s = &d->type_states[id]; + const struct btf_type *t = btf__type_by_id(d->btf, id); + const char *orig_name = btf_name_of(d, t->name_off); + const char **cached_name = &d->cached_names[id]; + size_t dup_cnt; + + if (t->name_off == 0) + return ""; + + if (s->name_resolved) + return *cached_name ? *cached_name : orig_name; + + dup_cnt = btf_dump_name_dups(d, name_map, orig_name); + if (dup_cnt > 1) { + const size_t max_len = 256; + char new_name[max_len]; + + snprintf(new_name, max_len, "%s___%zu", orig_name, dup_cnt); + *cached_name = strdup(new_name); + } + + s->name_resolved = 1; + return *cached_name ? *cached_name : orig_name; +} + +static const char *btf_dump_type_name(struct btf_dump *d, __u32 id) +{ + return btf_dump_resolve_name(d, id, d->type_names); +} + +static const char *btf_dump_ident_name(struct btf_dump *d, __u32 id) +{ + return btf_dump_resolve_name(d, id, d->ident_names); +} diff --git a/src/contrib/libbpf/bpf/hashmap.c b/src/contrib/libbpf/bpf/hashmap.c new file mode 100644 index 0000000..6122272 --- /dev/null +++ b/src/contrib/libbpf/bpf/hashmap.c @@ -0,0 +1,229 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * Generic non-thread safe hash map implementation. + * + * Copyright (c) 2019 Facebook + */ +#include <stdint.h> +#include <stdlib.h> +#include <stdio.h> +#include <errno.h> +#include <linux/err.h> +#include "hashmap.h" + +/* start with 4 buckets */ +#define HASHMAP_MIN_CAP_BITS 2 + +static void hashmap_add_entry(struct hashmap_entry **pprev, + struct hashmap_entry *entry) +{ + entry->next = *pprev; + *pprev = entry; +} + +static void hashmap_del_entry(struct hashmap_entry **pprev, + struct hashmap_entry *entry) +{ + *pprev = entry->next; + entry->next = NULL; +} + +void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn, + hashmap_equal_fn equal_fn, void *ctx) +{ + map->hash_fn = hash_fn; + map->equal_fn = equal_fn; + map->ctx = ctx; + + map->buckets = NULL; + map->cap = 0; + map->cap_bits = 0; + map->sz = 0; +} + +struct hashmap *hashmap__new(hashmap_hash_fn hash_fn, + hashmap_equal_fn equal_fn, + void *ctx) +{ + struct hashmap *map = malloc(sizeof(struct hashmap)); + + if (!map) + return ERR_PTR(-ENOMEM); + hashmap__init(map, hash_fn, equal_fn, ctx); + return map; +} + +void hashmap__clear(struct hashmap *map) +{ + free(map->buckets); + map->cap = map->cap_bits = map->sz = 0; +} + +void hashmap__free(struct hashmap *map) +{ + if (!map) + return; + + hashmap__clear(map); + free(map); +} + +size_t hashmap__size(const struct hashmap *map) +{ + return map->sz; +} + +size_t hashmap__capacity(const struct hashmap *map) +{ + return map->cap; +} + +static bool hashmap_needs_to_grow(struct hashmap *map) +{ + /* grow if empty or more than 75% filled */ + return (map->cap == 0) || ((map->sz + 1) * 4 / 3 > map->cap); +} + +static int hashmap_grow(struct hashmap *map) +{ + struct hashmap_entry **new_buckets; + struct hashmap_entry *cur, *tmp; + size_t new_cap_bits, new_cap; + size_t h; + int bkt; + + new_cap_bits = map->cap_bits + 1; + if (new_cap_bits < HASHMAP_MIN_CAP_BITS) + new_cap_bits = HASHMAP_MIN_CAP_BITS; + + new_cap = 1UL << new_cap_bits; + new_buckets = calloc(new_cap, sizeof(new_buckets[0])); + if (!new_buckets) + return -ENOMEM; + + hashmap__for_each_entry_safe(map, cur, tmp, bkt) { + h = hash_bits(map->hash_fn(cur->key, map->ctx), new_cap_bits); + hashmap_add_entry(&new_buckets[h], cur); + } + + map->cap = new_cap; + map->cap_bits = new_cap_bits; + free(map->buckets); + map->buckets = new_buckets; + + return 0; +} + +static bool hashmap_find_entry(const struct hashmap *map, + const void *key, size_t hash, + struct hashmap_entry ***pprev, + struct hashmap_entry **entry) +{ + struct hashmap_entry *cur, **prev_ptr; + + if (!map->buckets) + return false; + + for (prev_ptr = &map->buckets[hash], cur = *prev_ptr; + cur; + prev_ptr = &cur->next, cur = cur->next) { + if (map->equal_fn(cur->key, key, map->ctx)) { + if (pprev) + *pprev = prev_ptr; + *entry = cur; + return true; + } + } + + return false; +} + +int hashmap__insert(struct hashmap *map, const void *key, void *value, + enum hashmap_insert_strategy strategy, + const void **old_key, void **old_value) +{ + struct hashmap_entry *entry; + size_t h; + int err; + + if (old_key) + *old_key = NULL; + if (old_value) + *old_value = NULL; + + h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits); + if (strategy != HASHMAP_APPEND && + hashmap_find_entry(map, key, h, NULL, &entry)) { + if (old_key) + *old_key = entry->key; + if (old_value) + *old_value = entry->value; + + if (strategy == HASHMAP_SET || strategy == HASHMAP_UPDATE) { + entry->key = key; + entry->value = value; + return 0; + } else if (strategy == HASHMAP_ADD) { + return -EEXIST; + } + } + + if (strategy == HASHMAP_UPDATE) + return -ENOENT; + + if (hashmap_needs_to_grow(map)) { + err = hashmap_grow(map); + if (err) + return err; + h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits); + } + + entry = malloc(sizeof(struct hashmap_entry)); + if (!entry) + return -ENOMEM; + + entry->key = key; + entry->value = value; + hashmap_add_entry(&map->buckets[h], entry); + map->sz++; + + return 0; +} + +bool hashmap__find(const struct hashmap *map, const void *key, void **value) +{ + struct hashmap_entry *entry; + size_t h; + + h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits); + if (!hashmap_find_entry(map, key, h, NULL, &entry)) + return false; + + if (value) + *value = entry->value; + return true; +} + +bool hashmap__delete(struct hashmap *map, const void *key, + const void **old_key, void **old_value) +{ + struct hashmap_entry **pprev, *entry; + size_t h; + + h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits); + if (!hashmap_find_entry(map, key, h, &pprev, &entry)) + return false; + + if (old_key) + *old_key = entry->key; + if (old_value) + *old_value = entry->value; + + hashmap_del_entry(pprev, entry); + free(entry); + map->sz--; + + return true; +} + diff --git a/src/contrib/libbpf/bpf/hashmap.h b/src/contrib/libbpf/bpf/hashmap.h new file mode 100644 index 0000000..bae8879 --- /dev/null +++ b/src/contrib/libbpf/bpf/hashmap.h @@ -0,0 +1,178 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Generic non-thread safe hash map implementation. + * + * Copyright (c) 2019 Facebook + */ +#ifndef __LIBBPF_HASHMAP_H +#define __LIBBPF_HASHMAP_H + +#include <stdbool.h> +#include <stddef.h> +#ifdef __GLIBC__ +#include <bits/wordsize.h> +#else +#include <bits/reg.h> +#endif +#include "libbpf_internal.h" + +static inline size_t hash_bits(size_t h, int bits) +{ + /* shuffle bits and return requested number of upper bits */ + return (h * 11400714819323198485llu) >> (__WORDSIZE - bits); +} + +typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx); +typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx); + +struct hashmap_entry { + const void *key; + void *value; + struct hashmap_entry *next; +}; + +struct hashmap { + hashmap_hash_fn hash_fn; + hashmap_equal_fn equal_fn; + void *ctx; + + struct hashmap_entry **buckets; + size_t cap; + size_t cap_bits; + size_t sz; +}; + +#define HASHMAP_INIT(hash_fn, equal_fn, ctx) { \ + .hash_fn = (hash_fn), \ + .equal_fn = (equal_fn), \ + .ctx = (ctx), \ + .buckets = NULL, \ + .cap = 0, \ + .cap_bits = 0, \ + .sz = 0, \ +} + +void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn, + hashmap_equal_fn equal_fn, void *ctx); +struct hashmap *hashmap__new(hashmap_hash_fn hash_fn, + hashmap_equal_fn equal_fn, + void *ctx); +void hashmap__clear(struct hashmap *map); +void hashmap__free(struct hashmap *map); + +size_t hashmap__size(const struct hashmap *map); +size_t hashmap__capacity(const struct hashmap *map); + +/* + * Hashmap insertion strategy: + * - HASHMAP_ADD - only add key/value if key doesn't exist yet; + * - HASHMAP_SET - add key/value pair if key doesn't exist yet; otherwise, + * update value; + * - HASHMAP_UPDATE - update value, if key already exists; otherwise, do + * nothing and return -ENOENT; + * - HASHMAP_APPEND - always add key/value pair, even if key already exists. + * This turns hashmap into a multimap by allowing multiple values to be + * associated with the same key. Most useful read API for such hashmap is + * hashmap__for_each_key_entry() iteration. If hashmap__find() is still + * used, it will return last inserted key/value entry (first in a bucket + * chain). + */ +enum hashmap_insert_strategy { + HASHMAP_ADD, + HASHMAP_SET, + HASHMAP_UPDATE, + HASHMAP_APPEND, +}; + +/* + * hashmap__insert() adds key/value entry w/ various semantics, depending on + * provided strategy value. If a given key/value pair replaced already + * existing key/value pair, both old key and old value will be returned + * through old_key and old_value to allow calling code do proper memory + * management. + */ +int hashmap__insert(struct hashmap *map, const void *key, void *value, + enum hashmap_insert_strategy strategy, + const void **old_key, void **old_value); + +static inline int hashmap__add(struct hashmap *map, + const void *key, void *value) +{ + return hashmap__insert(map, key, value, HASHMAP_ADD, NULL, NULL); +} + +static inline int hashmap__set(struct hashmap *map, + const void *key, void *value, + const void **old_key, void **old_value) +{ + return hashmap__insert(map, key, value, HASHMAP_SET, + old_key, old_value); +} + +static inline int hashmap__update(struct hashmap *map, + const void *key, void *value, + const void **old_key, void **old_value) +{ + return hashmap__insert(map, key, value, HASHMAP_UPDATE, + old_key, old_value); +} + +static inline int hashmap__append(struct hashmap *map, + const void *key, void *value) +{ + return hashmap__insert(map, key, value, HASHMAP_APPEND, NULL, NULL); +} + +bool hashmap__delete(struct hashmap *map, const void *key, + const void **old_key, void **old_value); + +bool hashmap__find(const struct hashmap *map, const void *key, void **value); + +/* + * hashmap__for_each_entry - iterate over all entries in hashmap + * @map: hashmap to iterate + * @cur: struct hashmap_entry * used as a loop cursor + * @bkt: integer used as a bucket loop cursor + */ +#define hashmap__for_each_entry(map, cur, bkt) \ + for (bkt = 0; bkt < map->cap; bkt++) \ + for (cur = map->buckets[bkt]; cur; cur = cur->next) + +/* + * hashmap__for_each_entry_safe - iterate over all entries in hashmap, safe + * against removals + * @map: hashmap to iterate + * @cur: struct hashmap_entry * used as a loop cursor + * @tmp: struct hashmap_entry * used as a temporary next cursor storage + * @bkt: integer used as a bucket loop cursor + */ +#define hashmap__for_each_entry_safe(map, cur, tmp, bkt) \ + for (bkt = 0; bkt < map->cap; bkt++) \ + for (cur = map->buckets[bkt]; \ + cur && ({tmp = cur->next; true; }); \ + cur = tmp) + +/* + * hashmap__for_each_key_entry - iterate over entries associated with given key + * @map: hashmap to iterate + * @cur: struct hashmap_entry * used as a loop cursor + * @key: key to iterate entries for + */ +#define hashmap__for_each_key_entry(map, cur, _key) \ + for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ + map->cap_bits); \ + map->buckets ? map->buckets[bkt] : NULL; }); \ + cur; \ + cur = cur->next) \ + if (map->equal_fn(cur->key, (_key), map->ctx)) + +#define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ + for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ + map->cap_bits); \ + cur = map->buckets ? map->buckets[bkt] : NULL; }); \ + cur && ({ tmp = cur->next; true; }); \ + cur = tmp) \ + if (map->equal_fn(cur->key, (_key), map->ctx)) + +#endif /* __LIBBPF_HASHMAP_H */ diff --git a/src/contrib/libbpf/bpf/libbpf.c b/src/contrib/libbpf/bpf/libbpf.c new file mode 100644 index 0000000..29d8d03 --- /dev/null +++ b/src/contrib/libbpf/bpf/libbpf.c @@ -0,0 +1,6581 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * Common eBPF ELF object loading operations. + * + * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> + * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015 Huawei Inc. + * Copyright (C) 2017 Nicira, Inc. + * Copyright (C) 2019 Isovalent, Inc. + */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <stdlib.h> +#include <stdio.h> +#include <stdarg.h> +#include <libgen.h> +#include <inttypes.h> +#include <string.h> +#include <unistd.h> +#include <endian.h> +#include <fcntl.h> +#include <errno.h> +#include <asm/unistd.h> +#include <linux/err.h> +#include <linux/kernel.h> +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/filter.h> +#include <linux/list.h> +#include <linux/limits.h> +#include <linux/perf_event.h> +#include <linux/ring_buffer.h> +#include <linux/version.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> +#include <sys/utsname.h> +#include <libelf.h> +#include <gelf.h> + +#include "libbpf.h" +#include "bpf.h" +#include "btf.h" +#include "str_error.h" +#include "libbpf_internal.h" +#include "hashmap.h" + +#ifndef EM_BPF +#define EM_BPF 247 +#endif + +#ifndef BPF_FS_MAGIC +#define BPF_FS_MAGIC 0xcafe4a11 +#endif + +/* vsprintf() in __base_pr() uses nonliteral format string. It may break + * compilation if user enables corresponding warning. Disable it explicitly. + */ +#pragma GCC diagnostic ignored "-Wformat-nonliteral" + +#define __printf(a, b) __attribute__((format(printf, a, b))) + +static int __base_pr(enum libbpf_print_level level, const char *format, + va_list args) +{ + if (level == LIBBPF_DEBUG) + return 0; + + return vfprintf(stderr, format, args); +} + +static libbpf_print_fn_t __libbpf_pr = __base_pr; + +libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn) +{ + libbpf_print_fn_t old_print_fn = __libbpf_pr; + + __libbpf_pr = fn; + return old_print_fn; +} + +__printf(2, 3) +void libbpf_print(enum libbpf_print_level level, const char *format, ...) +{ + va_list args; + + if (!__libbpf_pr) + return; + + va_start(args, format); + __libbpf_pr(level, format, args); + va_end(args); +} + +#define STRERR_BUFSIZE 128 + +#define CHECK_ERR(action, err, out) do { \ + err = action; \ + if (err) \ + goto out; \ +} while (0) + + +/* Copied from tools/perf/util/util.h */ +#ifndef zfree +# define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) +#endif + +#ifndef zclose +# define zclose(fd) ({ \ + int ___err = 0; \ + if ((fd) >= 0) \ + ___err = close((fd)); \ + fd = -1; \ + ___err; }) +#endif + +#ifdef HAVE_LIBELF_MMAP_SUPPORT +# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ_MMAP +#else +# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ +#endif + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64) (unsigned long) ptr; +} + +struct bpf_capabilities { + /* v4.14: kernel support for program & map names. */ + __u32 name:1; + /* v5.2: kernel support for global data sections. */ + __u32 global_data:1; + /* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */ + __u32 btf_func:1; + /* BTF_KIND_VAR and BTF_KIND_DATASEC support */ + __u32 btf_datasec:1; + /* BPF_F_MMAPABLE is supported for arrays */ + __u32 array_mmap:1; +}; + +/* + * bpf_prog should be a better name but it has been used in + * linux/filter.h. + */ +struct bpf_program { + /* Index in elf obj file, for relocation use. */ + int idx; + char *name; + int prog_ifindex; + char *section_name; + /* section_name with / replaced by _; makes recursive pinning + * in bpf_object__pin_programs easier + */ + char *pin_name; + struct bpf_insn *insns; + size_t insns_cnt, main_prog_cnt; + enum bpf_prog_type type; + + struct reloc_desc { + enum { + RELO_LD64, + RELO_CALL, + RELO_DATA, + } type; + int insn_idx; + int map_idx; + int sym_off; + } *reloc_desc; + int nr_reloc; + int log_level; + + struct { + int nr; + int *fds; + } instances; + bpf_program_prep_t preprocessor; + + struct bpf_object *obj; + void *priv; + bpf_program_clear_priv_t clear_priv; + + enum bpf_attach_type expected_attach_type; + __u32 attach_btf_id; + __u32 attach_prog_fd; + void *func_info; + __u32 func_info_rec_size; + __u32 func_info_cnt; + + struct bpf_capabilities *caps; + + void *line_info; + __u32 line_info_rec_size; + __u32 line_info_cnt; + __u32 prog_flags; +}; + +enum libbpf_map_type { + LIBBPF_MAP_UNSPEC, + LIBBPF_MAP_DATA, + LIBBPF_MAP_BSS, + LIBBPF_MAP_RODATA, +}; + +static const char * const libbpf_type_to_btf_name[] = { + [LIBBPF_MAP_DATA] = ".data", + [LIBBPF_MAP_BSS] = ".bss", + [LIBBPF_MAP_RODATA] = ".rodata", +}; + +struct bpf_map { + int fd; + char *name; + int sec_idx; + size_t sec_offset; + int map_ifindex; + int inner_map_fd; + struct bpf_map_def def; + __u32 btf_key_type_id; + __u32 btf_value_type_id; + void *priv; + bpf_map_clear_priv_t clear_priv; + enum libbpf_map_type libbpf_type; + char *pin_path; + bool pinned; + bool reused; +}; + +struct bpf_secdata { + void *rodata; + void *data; +}; + +static LIST_HEAD(bpf_objects_list); + +struct bpf_object { + char name[BPF_OBJ_NAME_LEN]; + char license[64]; + __u32 kern_version; + + struct bpf_program *programs; + size_t nr_programs; + struct bpf_map *maps; + size_t nr_maps; + size_t maps_cap; + struct bpf_secdata sections; + + bool loaded; + bool has_pseudo_calls; + bool relaxed_core_relocs; + + /* + * Information when doing elf related work. Only valid if fd + * is valid. + */ + struct { + int fd; + const void *obj_buf; + size_t obj_buf_sz; + Elf *elf; + GElf_Ehdr ehdr; + Elf_Data *symbols; + Elf_Data *data; + Elf_Data *rodata; + Elf_Data *bss; + size_t strtabidx; + struct { + GElf_Shdr shdr; + Elf_Data *data; + } *reloc_sects; + int nr_reloc_sects; + int maps_shndx; + int btf_maps_shndx; + int text_shndx; + int data_shndx; + int rodata_shndx; + int bss_shndx; + } efile; + /* + * All loaded bpf_object is linked in a list, which is + * hidden to caller. bpf_objects__<func> handlers deal with + * all objects. + */ + struct list_head list; + + struct btf *btf; + struct btf_ext *btf_ext; + + void *priv; + bpf_object_clear_priv_t clear_priv; + + struct bpf_capabilities caps; + + char path[]; +}; +#define obj_elf_valid(o) ((o)->efile.elf) + +void bpf_program__unload(struct bpf_program *prog) +{ + int i; + + if (!prog) + return; + + /* + * If the object is opened but the program was never loaded, + * it is possible that prog->instances.nr == -1. + */ + if (prog->instances.nr > 0) { + for (i = 0; i < prog->instances.nr; i++) + zclose(prog->instances.fds[i]); + } else if (prog->instances.nr != -1) { + pr_warn("Internal error: instances.nr is %d\n", + prog->instances.nr); + } + + prog->instances.nr = -1; + zfree(&prog->instances.fds); + + zfree(&prog->func_info); + zfree(&prog->line_info); +} + +static void bpf_program__exit(struct bpf_program *prog) +{ + if (!prog) + return; + + if (prog->clear_priv) + prog->clear_priv(prog, prog->priv); + + prog->priv = NULL; + prog->clear_priv = NULL; + + bpf_program__unload(prog); + zfree(&prog->name); + zfree(&prog->section_name); + zfree(&prog->pin_name); + zfree(&prog->insns); + zfree(&prog->reloc_desc); + + prog->nr_reloc = 0; + prog->insns_cnt = 0; + prog->idx = -1; +} + +static char *__bpf_program__pin_name(struct bpf_program *prog) +{ + char *name, *p; + + name = p = strdup(prog->section_name); + while ((p = strchr(p, '/'))) + *p = '_'; + + return name; +} + +static int +bpf_program__init(void *data, size_t size, char *section_name, int idx, + struct bpf_program *prog) +{ + const size_t bpf_insn_sz = sizeof(struct bpf_insn); + + if (size == 0 || size % bpf_insn_sz) { + pr_warn("corrupted section '%s', size: %zu\n", + section_name, size); + return -EINVAL; + } + + memset(prog, 0, sizeof(*prog)); + + prog->section_name = strdup(section_name); + if (!prog->section_name) { + pr_warn("failed to alloc name for prog under section(%d) %s\n", + idx, section_name); + goto errout; + } + + prog->pin_name = __bpf_program__pin_name(prog); + if (!prog->pin_name) { + pr_warn("failed to alloc pin name for prog under section(%d) %s\n", + idx, section_name); + goto errout; + } + + prog->insns = malloc(size); + if (!prog->insns) { + pr_warn("failed to alloc insns for prog under section %s\n", + section_name); + goto errout; + } + prog->insns_cnt = size / bpf_insn_sz; + memcpy(prog->insns, data, size); + prog->idx = idx; + prog->instances.fds = NULL; + prog->instances.nr = -1; + prog->type = BPF_PROG_TYPE_UNSPEC; + + return 0; +errout: + bpf_program__exit(prog); + return -ENOMEM; +} + +static int +bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, + char *section_name, int idx) +{ + struct bpf_program prog, *progs; + int nr_progs, err; + + err = bpf_program__init(data, size, section_name, idx, &prog); + if (err) + return err; + + prog.caps = &obj->caps; + progs = obj->programs; + nr_progs = obj->nr_programs; + + progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0])); + if (!progs) { + /* + * In this case the original obj->programs + * is still valid, so don't need special treat for + * bpf_close_object(). + */ + pr_warn("failed to alloc a new program under section '%s'\n", + section_name); + bpf_program__exit(&prog); + return -ENOMEM; + } + + pr_debug("found program %s\n", prog.section_name); + obj->programs = progs; + obj->nr_programs = nr_progs + 1; + prog.obj = obj; + progs[nr_progs] = prog; + return 0; +} + +static int +bpf_object__init_prog_names(struct bpf_object *obj) +{ + Elf_Data *symbols = obj->efile.symbols; + struct bpf_program *prog; + size_t pi, si; + + for (pi = 0; pi < obj->nr_programs; pi++) { + const char *name = NULL; + + prog = &obj->programs[pi]; + + for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name; + si++) { + GElf_Sym sym; + + if (!gelf_getsym(symbols, si, &sym)) + continue; + if (sym.st_shndx != prog->idx) + continue; + if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL) + continue; + + name = elf_strptr(obj->efile.elf, + obj->efile.strtabidx, + sym.st_name); + if (!name) { + pr_warn("failed to get sym name string for prog %s\n", + prog->section_name); + return -LIBBPF_ERRNO__LIBELF; + } + } + + if (!name && prog->idx == obj->efile.text_shndx) + name = ".text"; + + if (!name) { + pr_warn("failed to find sym for prog %s\n", + prog->section_name); + return -EINVAL; + } + + prog->name = strdup(name); + if (!prog->name) { + pr_warn("failed to allocate memory for prog sym %s\n", + name); + return -ENOMEM; + } + } + + return 0; +} + +static __u32 get_kernel_version(void) +{ + __u32 major, minor, patch; + struct utsname info; + + uname(&info); + if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) + return 0; + return KERNEL_VERSION(major, minor, patch); +} + +static struct bpf_object *bpf_object__new(const char *path, + const void *obj_buf, + size_t obj_buf_sz, + const char *obj_name) +{ + struct bpf_object *obj; + char *end; + + obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1); + if (!obj) { + pr_warn("alloc memory failed for %s\n", path); + return ERR_PTR(-ENOMEM); + } + + strcpy(obj->path, path); + if (obj_name) { + strncpy(obj->name, obj_name, sizeof(obj->name) - 1); + obj->name[sizeof(obj->name) - 1] = 0; + } else { + /* Using basename() GNU version which doesn't modify arg. */ + 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 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. + */ + 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; + + obj->kern_version = get_kernel_version(); + obj->loaded = false; + + INIT_LIST_HEAD(&obj->list); + list_add(&obj->list, &bpf_objects_list); + return obj; +} + +static void bpf_object__elf_finish(struct bpf_object *obj) +{ + if (!obj_elf_valid(obj)) + return; + + if (obj->efile.elf) { + elf_end(obj->efile.elf); + obj->efile.elf = NULL; + } + obj->efile.symbols = NULL; + obj->efile.data = NULL; + obj->efile.rodata = NULL; + obj->efile.bss = NULL; + + zfree(&obj->efile.reloc_sects); + obj->efile.nr_reloc_sects = 0; + zclose(obj->efile.fd); + obj->efile.obj_buf = NULL; + obj->efile.obj_buf_sz = 0; +} + +static int bpf_object__elf_init(struct bpf_object *obj) +{ + int err = 0; + GElf_Ehdr *ep; + + if (obj_elf_valid(obj)) { + pr_warn("elf init: internal error\n"); + return -LIBBPF_ERRNO__LIBELF; + } + + if (obj->efile.obj_buf_sz > 0) { + /* + * obj_buf should have been validated by + * bpf_object__open_buffer(). + */ + obj->efile.elf = elf_memory((char *)obj->efile.obj_buf, + obj->efile.obj_buf_sz); + } else { + obj->efile.fd = open(obj->path, O_RDONLY); + if (obj->efile.fd < 0) { + char errmsg[STRERR_BUFSIZE], *cp; + + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("failed to open %s: %s\n", obj->path, cp); + return err; + } + + obj->efile.elf = elf_begin(obj->efile.fd, + LIBBPF_ELF_C_READ_MMAP, NULL); + } + + if (!obj->efile.elf) { + pr_warn("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_warn("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_warn("%s is not an eBPF object file\n", obj->path); + err = -LIBBPF_ERRNO__FORMAT; + goto errout; + } + + return 0; +errout: + bpf_object__elf_finish(obj); + return err; +} + +static int bpf_object__check_endianness(struct bpf_object *obj) +{ +#if __BYTE_ORDER == __LITTLE_ENDIAN + if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB) + return 0; +#elif __BYTE_ORDER == __BIG_ENDIAN + if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB) + return 0; +#else +# error "Unrecognized __BYTE_ORDER__" +#endif + pr_warn("endianness mismatch.\n"); + return -LIBBPF_ERRNO__ENDIAN; +} + +static int +bpf_object__init_license(struct bpf_object *obj, void *data, size_t size) +{ + 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) +{ + __u32 kver; + + if (size != sizeof(kver)) { + pr_warn("invalid kver section in %s\n", obj->path); + return -LIBBPF_ERRNO__FORMAT; + } + memcpy(&kver, data, sizeof(kver)); + obj->kern_version = kver; + pr_debug("kernel version of %s is %x\n", obj->path, obj->kern_version); + return 0; +} + +static int compare_bpf_map(const void *_a, const void *_b) +{ + const struct bpf_map *a = _a; + const struct bpf_map *b = _b; + + 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) +{ + if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS || + type == BPF_MAP_TYPE_HASH_OF_MAPS) + return true; + return false; +} + +static int bpf_object_search_section_size(const struct bpf_object *obj, + const char *name, size_t *d_size) +{ + const GElf_Ehdr *ep = &obj->efile.ehdr; + Elf *elf = obj->efile.elf; + Elf_Scn *scn = NULL; + int idx = 0; + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + const char *sec_name; + Elf_Data *data; + GElf_Shdr sh; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + pr_warn("failed to get section(%d) header from %s\n", + idx, obj->path); + return -EIO; + } + + sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); + if (!sec_name) { + pr_warn("failed to get section(%d) name from %s\n", + idx, obj->path); + return -EIO; + } + + if (strcmp(name, sec_name)) + continue; + + data = elf_getdata(scn, 0); + if (!data) { + pr_warn("failed to get section(%d) data from %s(%s)\n", + idx, name, obj->path); + return -EIO; + } + + *d_size = data->d_size; + return 0; + } + + return -ENOENT; +} + +int bpf_object__section_size(const struct bpf_object *obj, const char *name, + __u32 *size) +{ + int ret = -ENOENT; + size_t d_size; + + *size = 0; + if (!name) { + return -EINVAL; + } else if (!strcmp(name, ".data")) { + if (obj->efile.data) + *size = obj->efile.data->d_size; + } else if (!strcmp(name, ".bss")) { + if (obj->efile.bss) + *size = obj->efile.bss->d_size; + } else if (!strcmp(name, ".rodata")) { + if (obj->efile.rodata) + *size = obj->efile.rodata->d_size; + } else { + ret = bpf_object_search_section_size(obj, name, &d_size); + if (!ret) + *size = d_size; + } + + return *size ? 0 : ret; +} + +int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, + __u32 *off) +{ + Elf_Data *symbols = obj->efile.symbols; + const char *sname; + size_t si; + + if (!name || !off) + return -EINVAL; + + for (si = 0; si < symbols->d_size / sizeof(GElf_Sym); si++) { + GElf_Sym sym; + + if (!gelf_getsym(symbols, si, &sym)) + continue; + if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL || + GELF_ST_TYPE(sym.st_info) != STT_OBJECT) + continue; + + sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name); + if (!sname) { + pr_warn("failed to get sym name string for var %s\n", + name); + return -EIO; + } + if (strcmp(name, sname) == 0) { + *off = sym.st_value; + return 0; + } + } + + return -ENOENT; +} + +static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) +{ + 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_warn("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, enum libbpf_map_type type, + int sec_idx, Elf_Data *data, void **data_buff) +{ + 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->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); + if (!map->name) { + pr_warn("failed to alloc map name\n"); + return -ENOMEM; + } + + 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; + if (obj->caps.array_mmap) + def->map_flags |= BPF_F_MMAPABLE; + + pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n", + map_name, map->sec_idx, map->sec_offset, def->map_flags); + + if (data_buff) { + *data_buff = malloc(data->d_size); + if (!*data_buff) { + zfree(&map->name); + pr_warn("failed to alloc map content buffer\n"); + return -ENOMEM; + } + memcpy(*data_buff, data->d_buf, data->d_size); + } + + pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name); + return 0; +} + +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) +{ + Elf_Data *symbols = obj->efile.symbols; + int i, map_def_sz = 0, nr_maps = 0, nr_syms; + Elf_Data *data = NULL; + Elf_Scn *scn; + + if (obj->efile.maps_shndx < 0) + return 0; + + if (!symbols) + return -EINVAL; + + scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx); + if (scn) + data = elf_getdata(scn, NULL); + if (!scn || !data) { + pr_warn("failed to get Elf_Data from map section %d\n", + obj->efile.maps_shndx); + return -EINVAL; + } + + /* + * Count number of maps. Each map has a name. + * Array of maps is not supported: only the first element is + * considered. + * + * TODO: Detect array of map and report error. + */ + nr_syms = symbols->d_size / sizeof(GElf_Sym); + for (i = 0; i < nr_syms; i++) { + GElf_Sym sym; + + if (!gelf_getsym(symbols, i, &sym)) + continue; + if (sym.st_shndx != obj->efile.maps_shndx) + continue; + nr_maps++; + } + /* Assume equally sized map definitions */ + pr_debug("maps in %s: %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + + if (!data->d_size || nr_maps == 0 || (data->d_size % nr_maps) != 0) { + pr_warn("unable to determine map definition size section %s, %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + return -EINVAL; + } + map_def_sz = data->d_size / nr_maps; + + /* 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 = 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_warn("failed to get map #%d name sym string for obj %s\n", + i, obj->path); + return -LIBBPF_ERRNO__FORMAT; + } + + 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_warn("corrupted maps section in %s: last map \"%s\" too small\n", + obj->path, map_name); + return -EINVAL; + } + + map->name = strdup(map_name); + if (!map->name) { + pr_warn("failed to alloc map name\n"); + return -ENOMEM; + } + 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 + * bpf_map_def, copy it. Any extra fields in our version + * of bpf_map_def will default to zero as a result of the + * calloc above. + */ + if (map_def_sz <= sizeof(struct bpf_map_def)) { + memcpy(&map->def, def, map_def_sz); + } else { + /* + * Here the map structure being read is bigger than what + * we expect, truncate if the excess bits are all zero. + * If they are not zero, reject this map as + * incompatible. + */ + char *b; + + for (b = ((char *)def) + sizeof(struct bpf_map_def); + b < ((char *)def) + map_def_sz; b++) { + if (*b != 0) { + pr_warn("maps section in %s: \"%s\" has unrecognized, non-zero options\n", + obj->path, map_name); + if (strict) + return -EINVAL; + } + } + memcpy(&map->def, def, sizeof(struct bpf_map_def)); + } + } + return 0; +} + +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id) +{ + const struct btf_type *t = btf__type_by_id(btf, id); + + if (res_id) + *res_id = id; + + while (btf_is_mod(t) || btf_is_typedef(t)) { + if (res_id) + *res_id = t->type; + t = btf__type_by_id(btf, t->type); + } + + 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, NULL); + 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_is_ptr(t)) { + pr_warn("map '%s': attr '%s': expected PTR, got %u.\n", + map_name, name, btf_kind(t)); + return false; + } + + arr_t = btf__type_by_id(btf, t->type); + if (!arr_t) { + pr_warn("map '%s': attr '%s': type [%u] not found.\n", + map_name, name, t->type); + return false; + } + if (!btf_is_array(arr_t)) { + pr_warn("map '%s': attr '%s': expected ARRAY, got %u.\n", + map_name, name, btf_kind(arr_t)); + return false; + } + arr_info = btf_array(arr_t); + *res = arr_info->nelems; + return true; +} + +static int build_map_pin_path(struct bpf_map *map, const char *path) +{ + char buf[PATH_MAX]; + int err, len; + + 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 = bpf_map__set_pin_path(map, buf); + if (err) + return err; + + return 0; +} + +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 char *pin_root_path) +{ + 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 = btf_var_secinfos(sec) + var_idx; + var = btf__type_by_id(obj->btf, vi->type); + var_extra = btf_var(var); + map_name = btf__name_by_offset(obj->btf, var->name_off); + vlen = btf_vlen(var); + + if (map_name == NULL || map_name[0] == '\0') { + pr_warn("map #%d: empty name.\n", var_idx); + return -EINVAL; + } + if ((__u64)vi->offset + vi->size > data->d_size) { + pr_warn("map '%s' BTF data is corrupted.\n", map_name); + return -EINVAL; + } + if (!btf_is_var(var)) { + pr_warn("map '%s': unexpected var kind %u.\n", + map_name, btf_kind(var)); + return -EINVAL; + } + if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && + var_extra->linkage != BTF_VAR_STATIC) { + pr_warn("map '%s': unsupported var linkage %u.\n", + map_name, var_extra->linkage); + return -EOPNOTSUPP; + } + + def = skip_mods_and_typedefs(obj->btf, var->type, NULL); + if (!btf_is_struct(def)) { + pr_warn("map '%s': unexpected def kind %u.\n", + map_name, btf_kind(var)); + return -EINVAL; + } + if (def->size > vi->size) { + pr_warn("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_warn("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_vlen(def); + m = btf_members(def); + for (i = 0; i < vlen; i++, m++) { + const char *name = btf__name_by_offset(obj->btf, m->name_off); + + if (!name) { + pr_warn("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_warn("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_warn("map '%s': key type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (!btf_is_ptr(t)) { + pr_warn("map '%s': key spec is not PTR: %u.\n", + map_name, btf_kind(t)); + return -EINVAL; + } + sz = btf__resolve_size(obj->btf, t->type); + if (sz < 0) { + pr_warn("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_warn("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_warn("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_warn("map '%s': value type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (!btf_is_ptr(t)) { + pr_warn("map '%s': value spec is not PTR: %u.\n", + map_name, btf_kind(t)); + return -EINVAL; + } + sz = btf__resolve_size(obj->btf, t->type); + if (sz < 0) { + pr_warn("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_warn("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 (strcmp(name, "pinning") == 0) { + __u32 val; + int err; + + if (!get_map_field_int(map_name, obj->btf, def, m, + &val)) + return -EINVAL; + pr_debug("map '%s': found pinning = %u.\n", + map_name, val); + + if (val != LIBBPF_PIN_NONE && + val != LIBBPF_PIN_BY_NAME) { + pr_warn("map '%s': invalid pinning value %u.\n", + map_name, val); + return -EINVAL; + } + if (val == LIBBPF_PIN_BY_NAME) { + err = build_map_pin_path(map, pin_root_path); + if (err) { + pr_warn("map '%s': couldn't build pin path.\n", + map_name); + return err; + } + } + } else { + if (strict) { + pr_warn("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_warn("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 char *pin_root_path) +{ + 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_warn("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_is_datasec(t)) + continue; + name = btf__name_by_offset(obj->btf, t->name_off); + if (strcmp(name, MAPS_ELF_SEC) == 0) { + sec = t; + break; + } + } + + if (!sec) { + pr_warn("DATASEC '%s' not found.\n", MAPS_ELF_SEC); + return -ENOENT; + } + + vlen = btf_vlen(sec); + for (i = 0; i < vlen; i++) { + err = bpf_object__init_user_btf_map(obj, sec, i, + obj->efile.btf_maps_shndx, + data, strict, + pin_root_path); + if (err) + return err; + } + + return 0; +} + +static int bpf_object__init_maps(struct bpf_object *obj, bool relaxed_maps, + const char *pin_root_path) +{ + bool strict = !relaxed_maps; + int err; + + err = bpf_object__init_user_maps(obj, strict); + if (err) + return err; + + err = bpf_object__init_user_btf_maps(obj, strict, pin_root_path); + 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 0; +} + +static bool section_have_execinstr(struct bpf_object *obj, int idx) +{ + Elf_Scn *scn; + GElf_Shdr sh; + + scn = elf_getscn(obj->efile.elf, idx); + if (!scn) + return false; + + if (gelf_getshdr(scn, &sh) != &sh) + return false; + + if (sh.sh_flags & SHF_EXECINSTR) + return true; + + return false; +} + +static void bpf_object__sanitize_btf(struct bpf_object *obj) +{ + bool has_datasec = obj->caps.btf_datasec; + bool has_func = obj->caps.btf_func; + struct btf *btf = obj->btf; + struct btf_type *t; + int i, j, vlen; + + if (!obj->btf || (has_func && has_datasec)) + return; + + for (i = 1; i <= btf__get_nr_types(btf); i++) { + t = (struct btf_type *)btf__type_by_id(btf, i); + + if (!has_datasec && btf_is_var(t)) { + /* replace VAR with INT */ + t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); + /* + * using size = 1 is the safest choice, 4 will be too + * big and cause kernel BTF validation failure if + * original variable took less than 4 bytes + */ + t->size = 1; + *(int *)(t + 1) = BTF_INT_ENC(0, 0, 8); + } else if (!has_datasec && btf_is_datasec(t)) { + /* replace DATASEC with STRUCT */ + const struct btf_var_secinfo *v = btf_var_secinfos(t); + struct btf_member *m = btf_members(t); + struct btf_type *vt; + char *name; + + name = (char *)btf__name_by_offset(btf, t->name_off); + while (*name) { + if (*name == '.') + *name = '_'; + name++; + } + + vlen = btf_vlen(t); + t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, vlen); + for (j = 0; j < vlen; j++, v++, m++) { + /* order of field assignments is important */ + m->offset = v->offset * 8; + m->type = v->type; + /* preserve variable name as member name */ + vt = (void *)btf__type_by_id(btf, v->type); + m->name_off = vt->name_off; + } + } else if (!has_func && btf_is_func_proto(t)) { + /* replace FUNC_PROTO with ENUM */ + vlen = btf_vlen(t); + t->info = BTF_INFO_ENC(BTF_KIND_ENUM, 0, vlen); + t->size = sizeof(__u32); /* kernel enforced */ + } else if (!has_func && btf_is_func(t)) { + /* replace FUNC with TYPEDEF */ + t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0); + } + } +} + +static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) +{ + if (!obj->btf_ext) + return; + + if (!obj->caps.btf_func) { + btf_ext__free(obj->btf_ext); + obj->btf_ext = NULL; + } +} + +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_warn("Error loading ELF section %s: %d.\n", + BTF_ELF_SEC, err); + goto out; + } + err = btf__finalize_data(obj, obj->btf); + if (err) { + pr_warn("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_warn("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_warn("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_warn("Error loading %s into kernel: %d.\n", + BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + /* btf_ext can't exist without btf, so free it as well */ + if (obj->btf_ext) { + btf_ext__free(obj->btf_ext); + obj->btf_ext = NULL; + } + + if (bpf_object__is_btf_mandatory(obj)) + return err; + } + return 0; +} + +static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, + const char *pin_root_path) +{ + Elf *elf = obj->efile.elf; + GElf_Ehdr *ep = &obj->efile.ehdr; + Elf_Data *btf_ext_data = NULL; + Elf_Data *btf_data = NULL; + Elf_Scn *scn = NULL; + int idx = 0, err = 0; + + /* Elf is corrupted/truncated, avoid calling elf_strptr. */ + if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) { + pr_warn("failed to get e_shstrndx from %s\n", obj->path); + return -LIBBPF_ERRNO__FORMAT; + } + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + char *name; + GElf_Shdr sh; + Elf_Data *data; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + pr_warn("failed to get section(%d) header from %s\n", + idx, obj->path); + return -LIBBPF_ERRNO__FORMAT; + } + + name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); + if (!name) { + pr_warn("failed to get section(%d) name from %s\n", + idx, obj->path); + return -LIBBPF_ERRNO__FORMAT; + } + + data = elf_getdata(scn, 0); + if (!data) { + pr_warn("failed to get section(%d) data from %s(%s)\n", + idx, name, obj->path); + 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, + (int)sh.sh_link, (unsigned long)sh.sh_flags, + (int)sh.sh_type); + + if (strcmp(name, "license") == 0) { + 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) { + btf_ext_data = data; + } else if (sh.sh_type == SHT_SYMTAB) { + if (obj->efile.symbols) { + pr_warn("bpf: multiple SYMTAB in %s\n", + obj->path); + 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) + obj->efile.text_shndx = idx; + err = bpf_object__add_program(obj, data->d_buf, + data->d_size, + name, idx); + if (err) { + char errmsg[STRERR_BUFSIZE]; + char *cp; + + cp = libbpf_strerror_r(-err, errmsg, + sizeof(errmsg)); + pr_warn("failed to alloc program %s (%s): %s", + name, obj->path, cp); + return err; + } + } else if (strcmp(name, ".data") == 0) { + obj->efile.data = data; + obj->efile.data_shndx = idx; + } else if (strcmp(name, ".rodata") == 0) { + obj->efile.rodata = data; + obj->efile.rodata_shndx = idx; + } else { + pr_debug("skip section(%d) %s\n", idx, name); + } + } else if (sh.sh_type == SHT_REL) { + int nr_sects = obj->efile.nr_reloc_sects; + void *sects = obj->efile.reloc_sects; + int sec = sh.sh_info; /* points to other section */ + + /* Only do relo for section with exec instructions */ + if (!section_have_execinstr(obj, sec)) { + pr_debug("skip relo %s(%d) for section(%d)\n", + name, idx, sec); + continue; + } + + sects = reallocarray(sects, nr_sects + 1, + sizeof(*obj->efile.reloc_sects)); + if (!sects) { + pr_warn("reloc_sects realloc failed\n"); + return -ENOMEM; + } + + obj->efile.reloc_sects = sects; + obj->efile.nr_reloc_sects++; + + obj->efile.reloc_sects[nr_sects].shdr = sh; + obj->efile.reloc_sects[nr_sects].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 (!obj->efile.strtabidx || obj->efile.strtabidx > idx) { + pr_warn("Corrupted ELF file: index of strtab invalid\n"); + return -LIBBPF_ERRNO__FORMAT; + } + err = bpf_object__init_btf(obj, btf_data, btf_ext_data); + if (!err) + err = bpf_object__init_maps(obj, relaxed_maps, pin_root_path); + if (!err) + err = bpf_object__sanitize_and_load_btf(obj); + if (!err) + err = bpf_object__init_prog_names(obj); + return err; +} + +static struct bpf_program * +bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx) +{ + struct bpf_program *prog; + size_t i; + + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + if (prog->idx == idx) + return prog; + } + return NULL; +} + +struct bpf_program * +bpf_object__find_program_by_title(const struct bpf_object *obj, + const char *title) +{ + struct bpf_program *pos; + + bpf_object__for_each_program(pos, obj) { + if (pos->section_name && !strcmp(pos->section_name, title)) + return pos; + } + return NULL; +} + +static bool bpf_object__shndx_is_data(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.data_shndx || + shndx == obj->efile.bss_shndx || + shndx == obj->efile.rodata_shndx; +} + +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; +} + +static enum libbpf_map_type +bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) +{ + if (shndx == obj->efile.data_shndx) + return LIBBPF_MAP_DATA; + else if (shndx == obj->efile.bss_shndx) + return LIBBPF_MAP_BSS; + else if (shndx == obj->efile.rodata_shndx) + return LIBBPF_MAP_RODATA; + else + return LIBBPF_MAP_UNSPEC; +} + +static int bpf_program__record_reloc(struct bpf_program *prog, + struct reloc_desc *reloc_desc, + __u32 insn_idx, const char *name, + const GElf_Sym *sym, const GElf_Rel *rel) +{ + struct bpf_insn *insn = &prog->insns[insn_idx]; + size_t map_idx, nr_maps = prog->obj->nr_maps; + struct bpf_object *obj = prog->obj; + __u32 shdr_idx = sym->st_shndx; + enum libbpf_map_type type; + struct bpf_map *map; + + /* sub-program call relocation */ + if (insn->code == (BPF_JMP | BPF_CALL)) { + if (insn->src_reg != BPF_PSEUDO_CALL) { + pr_warn("incorrect bpf_call opcode\n"); + return -LIBBPF_ERRNO__RELOC; + } + /* text_shndx can be 0, if no default "main" program exists */ + if (!shdr_idx || shdr_idx != obj->efile.text_shndx) { + pr_warn("bad call relo against section %u\n", shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + if (sym->st_value % 8) { + pr_warn("bad call relo offset: %llu\n", (__u64)sym->st_value); + return -LIBBPF_ERRNO__RELOC; + } + reloc_desc->type = RELO_CALL; + reloc_desc->insn_idx = insn_idx; + reloc_desc->sym_off = sym->st_value; + obj->has_pseudo_calls = true; + return 0; + } + + if (insn->code != (BPF_LD | BPF_IMM | BPF_DW)) { + pr_warn("invalid relo for insns[%d].code 0x%x\n", + insn_idx, insn->code); + return -LIBBPF_ERRNO__RELOC; + } + if (!shdr_idx || shdr_idx >= SHN_LORESERVE) { + pr_warn("invalid relo for \'%s\' in special section 0x%x; forgot to initialize global var?..\n", + name, shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + + type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx); + + /* generic map reference relocation */ + if (type == LIBBPF_MAP_UNSPEC) { + if (!bpf_object__shndx_is_maps(obj, shdr_idx)) { + pr_warn("bad map relo against section %u\n", + shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + for (map_idx = 0; map_idx < nr_maps; map_idx++) { + map = &obj->maps[map_idx]; + if (map->libbpf_type != type || + map->sec_idx != sym->st_shndx || + map->sec_offset != sym->st_value) + continue; + pr_debug("found map %zd (%s, sec %d, off %zu) for insn %u\n", + map_idx, map->name, map->sec_idx, + map->sec_offset, insn_idx); + break; + } + if (map_idx >= nr_maps) { + pr_warn("map relo failed to find map for sec %u, off %llu\n", + shdr_idx, (__u64)sym->st_value); + return -LIBBPF_ERRNO__RELOC; + } + reloc_desc->type = RELO_LD64; + reloc_desc->insn_idx = insn_idx; + reloc_desc->map_idx = map_idx; + reloc_desc->sym_off = 0; /* sym->st_value determines map_idx */ + return 0; + } + + /* global data map relocation */ + if (!bpf_object__shndx_is_data(obj, shdr_idx)) { + pr_warn("bad data relo against section %u\n", shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + if (!obj->caps.global_data) { + pr_warn("relocation: kernel does not support global \'%s\' variable access in insns[%d]\n", + name, insn_idx); + return -LIBBPF_ERRNO__RELOC; + } + for (map_idx = 0; map_idx < nr_maps; map_idx++) { + map = &obj->maps[map_idx]; + if (map->libbpf_type != type) + continue; + pr_debug("found data map %zd (%s, sec %d, off %zu) for insn %u\n", + map_idx, map->name, map->sec_idx, map->sec_offset, + insn_idx); + break; + } + if (map_idx >= nr_maps) { + pr_warn("data relo failed to find map for sec %u\n", + shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + + reloc_desc->type = RELO_DATA; + reloc_desc->insn_idx = insn_idx; + reloc_desc->map_idx = map_idx; + reloc_desc->sym_off = sym->st_value; + return 0; +} + +static int +bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, + Elf_Data *data, struct bpf_object *obj) +{ + Elf_Data *symbols = obj->efile.symbols; + int err, i, nrels; + + 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); + if (!prog->reloc_desc) { + pr_warn("failed to alloc memory in relocation\n"); + return -ENOMEM; + } + prog->nr_reloc = nrels; + + for (i = 0; i < nrels; i++) { + const char *name; + __u32 insn_idx; + GElf_Sym sym; + GElf_Rel rel; + + if (!gelf_getrel(data, i, &rel)) { + pr_warn("relocation: failed to get %d reloc\n", i); + return -LIBBPF_ERRNO__FORMAT; + } + if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { + pr_warn("relocation: symbol %"PRIx64" not found\n", + GELF_R_SYM(rel.r_info)); + return -LIBBPF_ERRNO__FORMAT; + } + if (rel.r_offset % sizeof(struct bpf_insn)) + return -LIBBPF_ERRNO__FORMAT; + + insn_idx = rel.r_offset / sizeof(struct bpf_insn); + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name) ? : "<?>"; + + pr_debug("relo for shdr %u, symb %llu, value %llu, type %d, bind %d, name %d (\'%s\'), insn %u\n", + (__u32)sym.st_shndx, (__u64)GELF_R_SYM(rel.r_info), + (__u64)sym.st_value, GELF_ST_TYPE(sym.st_info), + GELF_ST_BIND(sym.st_info), sym.st_name, name, + insn_idx); + + err = bpf_program__record_reloc(prog, &prog->reloc_desc[i], + insn_idx, name, &sym, &rel); + if (err) + return err; + } + return 0; +} + +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(obj->btf, map->name, def->key_size, + def->value_size, &key_type_id, + &value_type_id); + } else { + /* + * LLVM annotates global data differently in BTF, that is, + * only as '.data', '.bss' or '.rodata'. + */ + ret = btf__find_by_name(obj->btf, + libbpf_type_to_btf_name[map->libbpf_type]); + } + if (ret < 0) + return ret; + + map->btf_key_type_id = key_type_id; + map->btf_value_type_id = bpf_map__is_internal(map) ? + ret : value_type_id; + return 0; +} + +int bpf_map__reuse_fd(struct bpf_map *map, int fd) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int new_fd, err; + char *new_name; + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) + return err; + + new_name = strdup(info.name); + if (!new_name) + return -errno; + + new_fd = open("/", O_RDONLY | O_CLOEXEC); + if (new_fd < 0) { + err = -errno; + goto err_free_new_name; + } + + new_fd = dup3(fd, new_fd, O_CLOEXEC); + if (new_fd < 0) { + err = -errno; + goto err_close_new_fd; + } + + err = zclose(map->fd); + if (err) { + err = -errno; + goto err_close_new_fd; + } + free(map->name); + + map->fd = new_fd; + map->name = new_name; + map->def.type = info.type; + map->def.key_size = info.key_size; + map->def.value_size = info.value_size; + map->def.max_entries = info.max_entries; + map->def.map_flags = info.map_flags; + map->btf_key_type_id = info.btf_key_type_id; + map->btf_value_type_id = info.btf_value_type_id; + map->reused = true; + + return 0; + +err_close_new_fd: + close(new_fd); +err_free_new_name: + free(new_name); + return err; +} + +int bpf_map__resize(struct bpf_map *map, __u32 max_entries) +{ + if (!map || !max_entries) + return -EINVAL; + + /* If map already created, its attributes can't be changed. */ + if (map->fd >= 0) + return -EBUSY; + + map->def.max_entries = max_entries; + + return 0; +} + +static int +bpf_object__probe_name(struct bpf_object *obj) +{ + struct bpf_load_program_attr attr; + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret; + + /* make sure basic loading works */ + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insns = insns; + attr.insns_cnt = ARRAY_SIZE(insns); + attr.license = "GPL"; + + ret = bpf_load_program_xattr(&attr, NULL, 0); + if (ret < 0) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n", + __func__, cp, errno); + return -errno; + } + close(ret); + + /* now try the same program, but with the name */ + + attr.name = "test"; + ret = bpf_load_program_xattr(&attr, NULL, 0); + if (ret >= 0) { + obj->caps.name = 1; + close(ret); + } + + return 0; +} + +static int +bpf_object__probe_global_data(struct bpf_object *obj) +{ + struct bpf_load_program_attr prg_attr; + struct bpf_create_map_attr map_attr; + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret, map; + + memset(&map_attr, 0, sizeof(map_attr)); + map_attr.map_type = BPF_MAP_TYPE_ARRAY; + map_attr.key_size = sizeof(int); + map_attr.value_size = 32; + map_attr.max_entries = 1; + + map = bpf_create_map_xattr(&map_attr); + if (map < 0) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, errno); + return -errno; + } + + insns[0].imm = map; + + memset(&prg_attr, 0, sizeof(prg_attr)); + prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + prg_attr.insns = insns; + prg_attr.insns_cnt = ARRAY_SIZE(insns); + prg_attr.license = "GPL"; + + ret = bpf_load_program_xattr(&prg_attr, NULL, 0); + if (ret >= 0) { + obj->caps.global_data = 1; + close(ret); + } + + close(map); + return 0; +} + +static int bpf_object__probe_btf_func(struct bpf_object *obj) +{ + static const char strs[] = "\0int\0x\0a"; + /* void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), + }; + int btf_fd; + + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); + if (btf_fd >= 0) { + obj->caps.btf_func = 1; + close(btf_fd); + return 1; + } + + return 0; +} + +static int bpf_object__probe_btf_datasec(struct bpf_object *obj) +{ + static const char strs[] = "\0x\0.data"; + /* static int a; */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* DATASEC val */ /* [3] */ + BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + }; + int btf_fd; + + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); + if (btf_fd >= 0) { + obj->caps.btf_datasec = 1; + close(btf_fd); + return 1; + } + + return 0; +} + +static int bpf_object__probe_array_mmap(struct bpf_object *obj) +{ + struct bpf_create_map_attr attr = { + .map_type = BPF_MAP_TYPE_ARRAY, + .map_flags = BPF_F_MMAPABLE, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1, + }; + int fd; + + fd = bpf_create_map_xattr(&attr); + if (fd >= 0) { + obj->caps.array_mmap = 1; + close(fd); + return 1; + } + + return 0; +} + +static int +bpf_object__probe_caps(struct bpf_object *obj) +{ + int (*probe_fn[])(struct bpf_object *obj) = { + bpf_object__probe_name, + bpf_object__probe_global_data, + bpf_object__probe_btf_func, + bpf_object__probe_btf_datasec, + bpf_object__probe_array_mmap, + }; + int i, ret; + + for (i = 0; i < ARRAY_SIZE(probe_fn); i++) { + ret = probe_fn[i](obj); + if (ret < 0) + pr_debug("Probe #%d failed with %d.\n", i, ret); + } + + return 0; +} + +static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) +{ + struct bpf_map_info map_info = {}; + char msg[STRERR_BUFSIZE]; + __u32 map_info_len; + + map_info_len = sizeof(map_info); + + if (bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len)) { + pr_warn("failed to get map info for map FD %d: %s\n", + map_fd, libbpf_strerror_r(errno, msg, sizeof(msg))); + return false; + } + + return (map_info.type == map->def.type && + map_info.key_size == map->def.key_size && + map_info.value_size == map->def.value_size && + map_info.max_entries == map->def.max_entries && + map_info.map_flags == map->def.map_flags); +} + +static int +bpf_object__reuse_map(struct bpf_map *map) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err, pin_fd; + + pin_fd = bpf_obj_get(map->pin_path); + if (pin_fd < 0) { + err = -errno; + if (err == -ENOENT) { + pr_debug("found no pinned map to reuse at '%s'\n", + map->pin_path); + return 0; + } + + cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); + pr_warn("couldn't retrieve pinned map '%s': %s\n", + map->pin_path, cp); + return err; + } + + if (!map_is_reuse_compat(map, pin_fd)) { + pr_warn("couldn't reuse pinned map at '%s': parameter mismatch\n", + map->pin_path); + close(pin_fd); + return -EINVAL; + } + + err = bpf_map__reuse_fd(map, pin_fd); + if (err) { + close(pin_fd); + return err; + } + map->pinned = true; + pr_debug("reused pinned map at '%s'\n", map->pin_path); + + return 0; +} + +static int +bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err, zero = 0; + __u8 *data; + + /* Nothing to do here since kernel already zero-initializes .bss map. */ + if (map->libbpf_type == LIBBPF_MAP_BSS) + return 0; + + data = map->libbpf_type == LIBBPF_MAP_DATA ? + obj->sections.data : obj->sections.rodata; + + err = bpf_map_update_elem(map->fd, &zero, data, 0); + /* Freeze .rodata map as read-only from syscall side. */ + if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) { + err = bpf_map_freeze(map->fd); + if (err) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("Error freezing map(%s) as read-only: %s\n", + map->name, cp); + err = 0; + } + } + return err; +} + +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; + + for (i = 0; i < obj->nr_maps; i++) { + struct bpf_map *map = &obj->maps[i]; + struct bpf_map_def *def = &map->def; + char *cp, errmsg[STRERR_BUFSIZE]; + int *pfd = &map->fd; + + if (map->pin_path) { + err = bpf_object__reuse_map(map); + if (err) { + pr_warn("error reusing pinned map %s\n", + map->name); + return err; + } + } + + if (map->fd >= 0) { + pr_debug("skip map create (preset) %s: fd=%d\n", + map->name, map->fd); + continue; + } + + if (obj->caps.name) + create_attr.name = map->name; + create_attr.map_ifindex = map->map_ifindex; + create_attr.map_type = def->type; + create_attr.map_flags = def->map_flags; + create_attr.key_size = def->key_size; + create_attr.value_size = def->value_size; + 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_warn("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; + if (bpf_map_type__is_map_in_map(def->type) && + map->inner_map_fd >= 0) + create_attr.inner_map_fd = map->inner_map_fd; + + 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 || + create_attr.btf_value_type_id)) { + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", + map->name, cp, err); + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + map->btf_key_type_id = 0; + map->btf_value_type_id = 0; + *pfd = bpf_create_map_xattr(&create_attr); + } + + if (*pfd < 0) { + size_t j; + + err = -errno; +err_out: + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("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; + } + + if (bpf_map__is_internal(map)) { + err = bpf_object__populate_internal_map(obj, map); + if (err < 0) { + zclose(*pfd); + goto err_out; + } + } + + if (map->pin_path && !map->pinned) { + err = bpf_map__pin(map, NULL); + if (err) { + pr_warn("failed to auto-pin map name '%s' at '%s'\n", + map->name, map->pin_path); + return err; + } + } + + pr_debug("created map %s: fd=%d\n", map->name, *pfd); + } + + return 0; +} + +static int +check_btf_ext_reloc_err(struct bpf_program *prog, int err, + void *btf_prog_info, const char *info_name) +{ + if (err != -ENOENT) { + pr_warn("Error in loading %s for sec %s.\n", + info_name, prog->section_name); + return err; + } + + /* err == -ENOENT (i.e. prog->section_name not found in btf_ext) */ + + if (btf_prog_info) { + /* + * Some info has already been found but has problem + * in the last btf_ext reloc. Must have to error out. + */ + pr_warn("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. */ + pr_warn("Cannot find %s for main program sec %s. Ignore all %s.\n", + info_name, prog->section_name, info_name); + return 0; +} + +static int +bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj, + const char *section_name, __u32 insn_offset) +{ + int err; + + if (!insn_offset || prog->func_info) { + /* + * !insn_offset => main program + * + * For sub prog, the main program's func_info has to + * be loaded first (i.e. prog->func_info != NULL) + */ + err = btf_ext__reloc_func_info(obj->btf, obj->btf_ext, + section_name, insn_offset, + &prog->func_info, + &prog->func_info_cnt); + if (err) + return check_btf_ext_reloc_err(prog, err, + prog->func_info, + "bpf_func_info"); + + prog->func_info_rec_size = btf_ext__func_info_rec_size(obj->btf_ext); + } + + if (!insn_offset || prog->line_info) { + err = btf_ext__reloc_line_info(obj->btf, obj->btf_ext, + section_name, insn_offset, + &prog->line_info, + &prog->line_info_cnt); + if (err) + return check_btf_ext_reloc_err(prog, err, + prog->line_info, + "bpf_line_info"); + + prog->line_info_rec_size = btf_ext__line_info_rec_size(obj->btf_ext); + } + + return 0; +} + +#define BPF_CORE_SPEC_MAX_LEN 64 + +/* represents BPF CO-RE field or array element accessor */ +struct bpf_core_accessor { + __u32 type_id; /* struct/union type or array element type */ + __u32 idx; /* field index or array index */ + const char *name; /* field name or NULL for array accessor */ +}; + +struct bpf_core_spec { + const struct btf *btf; + /* high-level spec: named fields and array indices only */ + struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; + /* high-level spec length */ + int len; + /* raw, low-level spec: 1-to-1 with accessor spec string */ + int raw_spec[BPF_CORE_SPEC_MAX_LEN]; + /* raw spec length */ + int raw_len; + /* field bit offset represented by spec */ + __u32 bit_offset; +}; + +static bool str_is_empty(const char *s) +{ + return !s || !s[0]; +} + +/* + * Turn bpf_field_reloc into a low- and high-level spec representation, + * validating correctness along the way, as well as calculating resulting + * field bit offset, specified by accessor string. Low-level spec captures + * every single level of nestedness, including traversing anonymous + * struct/union members. High-level one only captures semantically meaningful + * "turning points": named fields and array indicies. + * E.g., for this case: + * + * struct sample { + * int __unimportant; + * struct { + * int __1; + * int __2; + * int a[7]; + * }; + * }; + * + * struct sample *s = ...; + * + * int x = &s->a[3]; // access string = '0:1:2:3' + * + * Low-level spec has 1:1 mapping with each element of access string (it's + * just a parsed access string representation): [0, 1, 2, 3]. + * + * High-level spec will capture only 3 points: + * - intial zero-index access by pointer (&s->... is the same as &s[0]...); + * - field 'a' access (corresponds to '2' in low-level spec); + * - array element #3 access (corresponds to '3' in low-level spec). + * + */ +static int bpf_core_spec_parse(const struct btf *btf, + __u32 type_id, + const char *spec_str, + struct bpf_core_spec *spec) +{ + int access_idx, parsed_len, i; + const struct btf_type *t; + const char *name; + __u32 id; + __s64 sz; + + if (str_is_empty(spec_str) || *spec_str == ':') + return -EINVAL; + + memset(spec, 0, sizeof(*spec)); + spec->btf = btf; + + /* parse spec_str="0:1:2:3:4" into array raw_spec=[0, 1, 2, 3, 4] */ + while (*spec_str) { + if (*spec_str == ':') + ++spec_str; + if (sscanf(spec_str, "%d%n", &access_idx, &parsed_len) != 1) + return -EINVAL; + if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + spec_str += parsed_len; + spec->raw_spec[spec->raw_len++] = access_idx; + } + + if (spec->raw_len == 0) + return -EINVAL; + + /* first spec value is always reloc type array index */ + t = skip_mods_and_typedefs(btf, type_id, &id); + if (!t) + return -EINVAL; + + access_idx = spec->raw_spec[0]; + spec->spec[0].type_id = id; + spec->spec[0].idx = access_idx; + spec->len++; + + sz = btf__resolve_size(btf, id); + if (sz < 0) + return sz; + spec->bit_offset = access_idx * sz * 8; + + for (i = 1; i < spec->raw_len; i++) { + t = skip_mods_and_typedefs(btf, id, &id); + if (!t) + return -EINVAL; + + access_idx = spec->raw_spec[i]; + + if (btf_is_composite(t)) { + const struct btf_member *m; + __u32 bit_offset; + + if (access_idx >= btf_vlen(t)) + return -EINVAL; + + bit_offset = btf_member_bit_offset(t, access_idx); + spec->bit_offset += bit_offset; + + m = btf_members(t) + access_idx; + if (m->name_off) { + name = btf__name_by_offset(btf, m->name_off); + if (str_is_empty(name)) + return -EINVAL; + + spec->spec[spec->len].type_id = id; + spec->spec[spec->len].idx = access_idx; + spec->spec[spec->len].name = name; + spec->len++; + } + + id = m->type; + } else if (btf_is_array(t)) { + const struct btf_array *a = btf_array(t); + + t = skip_mods_and_typedefs(btf, a->type, &id); + if (!t || access_idx >= a->nelems) + return -EINVAL; + + spec->spec[spec->len].type_id = id; + spec->spec[spec->len].idx = access_idx; + spec->len++; + + sz = btf__resolve_size(btf, id); + if (sz < 0) + return sz; + spec->bit_offset += access_idx * sz * 8; + } else { + pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %d\n", + type_id, spec_str, i, id, btf_kind(t)); + return -EINVAL; + } + } + + return 0; +} + +static bool bpf_core_is_flavor_sep(const char *s) +{ + /* check X___Y name pattern, where X and Y are not underscores */ + return s[0] != '_' && /* X */ + s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */ + s[4] != '_'; /* Y */ +} + +/* Given 'some_struct_name___with_flavor' return the length of a name prefix + * before last triple underscore. Struct name part after last triple + * underscore is ignored by BPF CO-RE relocation during relocation matching. + */ +static size_t bpf_core_essential_name_len(const char *name) +{ + size_t n = strlen(name); + int i; + + for (i = n - 5; i >= 0; i--) { + if (bpf_core_is_flavor_sep(name + i)) + return i + 1; + } + return n; +} + +/* dynamically sized list of type IDs */ +struct ids_vec { + __u32 *data; + int len; +}; + +static void bpf_core_free_cands(struct ids_vec *cand_ids) +{ + free(cand_ids->data); + free(cand_ids); +} + +static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, + __u32 local_type_id, + const struct btf *targ_btf) +{ + size_t local_essent_len, targ_essent_len; + const char *local_name, *targ_name; + const struct btf_type *t; + struct ids_vec *cand_ids; + __u32 *new_ids; + int i, err, n; + + t = btf__type_by_id(local_btf, local_type_id); + if (!t) + return ERR_PTR(-EINVAL); + + local_name = btf__name_by_offset(local_btf, t->name_off); + if (str_is_empty(local_name)) + return ERR_PTR(-EINVAL); + local_essent_len = bpf_core_essential_name_len(local_name); + + cand_ids = calloc(1, sizeof(*cand_ids)); + if (!cand_ids) + return ERR_PTR(-ENOMEM); + + n = btf__get_nr_types(targ_btf); + for (i = 1; i <= n; i++) { + t = btf__type_by_id(targ_btf, i); + targ_name = btf__name_by_offset(targ_btf, t->name_off); + if (str_is_empty(targ_name)) + continue; + + targ_essent_len = bpf_core_essential_name_len(targ_name); + if (targ_essent_len != local_essent_len) + continue; + + if (strncmp(local_name, targ_name, local_essent_len) == 0) { + pr_debug("[%d] %s: found candidate [%d] %s\n", + local_type_id, local_name, i, targ_name); + new_ids = realloc(cand_ids->data, cand_ids->len + 1); + if (!new_ids) { + err = -ENOMEM; + goto err_out; + } + cand_ids->data = new_ids; + cand_ids->data[cand_ids->len++] = i; + } + } + return cand_ids; +err_out: + bpf_core_free_cands(cand_ids); + return ERR_PTR(err); +} + +/* Check two types for compatibility, skipping const/volatile/restrict and + * typedefs, to ensure we are relocating compatible entities: + * - any two STRUCTs/UNIONs are compatible and can be mixed; + * - any two FWDs are compatible, if their names match (modulo flavor suffix); + * - any two PTRs are always compatible; + * - for ENUMs, names should be the same (ignoring flavor suffix) or at + * least one of enums should be anonymous; + * - for ENUMs, check sizes, names are ignored; + * - for INT, size and signedness are ignored; + * - for ARRAY, dimensionality is ignored, element types are checked for + * compatibility recursively; + * - everything else shouldn't be ever a target of relocation. + * These rules are not set in stone and probably will be adjusted as we get + * more experience with using BPF CO-RE relocations. + */ +static int bpf_core_fields_are_compat(const struct btf *local_btf, + __u32 local_id, + const struct btf *targ_btf, + __u32 targ_id) +{ + const struct btf_type *local_type, *targ_type; + +recur: + local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id); + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!local_type || !targ_type) + return -EINVAL; + + if (btf_is_composite(local_type) && btf_is_composite(targ_type)) + return 1; + if (btf_kind(local_type) != btf_kind(targ_type)) + return 0; + + switch (btf_kind(local_type)) { + case BTF_KIND_PTR: + return 1; + case BTF_KIND_FWD: + case BTF_KIND_ENUM: { + const char *local_name, *targ_name; + size_t local_len, targ_len; + + local_name = btf__name_by_offset(local_btf, + local_type->name_off); + targ_name = btf__name_by_offset(targ_btf, targ_type->name_off); + local_len = bpf_core_essential_name_len(local_name); + targ_len = bpf_core_essential_name_len(targ_name); + /* one of them is anonymous or both w/ same flavor-less names */ + return local_len == 0 || targ_len == 0 || + (local_len == targ_len && + strncmp(local_name, targ_name, local_len) == 0); + } + case BTF_KIND_INT: + /* just reject deprecated bitfield-like integers; all other + * integers are by default compatible between each other + */ + return btf_int_offset(local_type) == 0 && + btf_int_offset(targ_type) == 0; + case BTF_KIND_ARRAY: + local_id = btf_array(local_type)->type; + targ_id = btf_array(targ_type)->type; + goto recur; + default: + pr_warn("unexpected kind %d relocated, local [%d], target [%d]\n", + btf_kind(local_type), local_id, targ_id); + return 0; + } +} + +/* + * Given single high-level named field accessor in local type, find + * corresponding high-level accessor for a target type. Along the way, + * maintain low-level spec for target as well. Also keep updating target + * bit offset. + * + * Searching is performed through recursive exhaustive enumeration of all + * fields of a struct/union. If there are any anonymous (embedded) + * structs/unions, they are recursively searched as well. If field with + * desired name is found, check compatibility between local and target types, + * before returning result. + * + * 1 is returned, if field is found. + * 0 is returned if no compatible field is found. + * <0 is returned on error. + */ +static int bpf_core_match_member(const struct btf *local_btf, + const struct bpf_core_accessor *local_acc, + const struct btf *targ_btf, + __u32 targ_id, + struct bpf_core_spec *spec, + __u32 *next_targ_id) +{ + const struct btf_type *local_type, *targ_type; + const struct btf_member *local_member, *m; + const char *local_name, *targ_name; + __u32 local_id; + int i, n, found; + + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!targ_type) + return -EINVAL; + if (!btf_is_composite(targ_type)) + return 0; + + local_id = local_acc->type_id; + local_type = btf__type_by_id(local_btf, local_id); + local_member = btf_members(local_type) + local_acc->idx; + local_name = btf__name_by_offset(local_btf, local_member->name_off); + + n = btf_vlen(targ_type); + m = btf_members(targ_type); + for (i = 0; i < n; i++, m++) { + __u32 bit_offset; + + bit_offset = btf_member_bit_offset(targ_type, i); + + /* too deep struct/union/array nesting */ + if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + + /* speculate this member will be the good one */ + spec->bit_offset += bit_offset; + spec->raw_spec[spec->raw_len++] = i; + + targ_name = btf__name_by_offset(targ_btf, m->name_off); + if (str_is_empty(targ_name)) { + /* embedded struct/union, we need to go deeper */ + found = bpf_core_match_member(local_btf, local_acc, + targ_btf, m->type, + spec, next_targ_id); + if (found) /* either found or error */ + return found; + } else if (strcmp(local_name, targ_name) == 0) { + /* matching named field */ + struct bpf_core_accessor *targ_acc; + + targ_acc = &spec->spec[spec->len++]; + targ_acc->type_id = targ_id; + targ_acc->idx = i; + targ_acc->name = targ_name; + + *next_targ_id = m->type; + found = bpf_core_fields_are_compat(local_btf, + local_member->type, + targ_btf, m->type); + if (!found) + spec->len--; /* pop accessor */ + return found; + } + /* member turned out not to be what we looked for */ + spec->bit_offset -= bit_offset; + spec->raw_len--; + } + + return 0; +} + +/* + * Try to match local spec to a target type and, if successful, produce full + * target spec (high-level, low-level + bit offset). + */ +static int bpf_core_spec_match(struct bpf_core_spec *local_spec, + const struct btf *targ_btf, __u32 targ_id, + struct bpf_core_spec *targ_spec) +{ + const struct btf_type *targ_type; + const struct bpf_core_accessor *local_acc; + struct bpf_core_accessor *targ_acc; + int i, sz, matched; + + memset(targ_spec, 0, sizeof(*targ_spec)); + targ_spec->btf = targ_btf; + + local_acc = &local_spec->spec[0]; + targ_acc = &targ_spec->spec[0]; + + for (i = 0; i < local_spec->len; i++, local_acc++, targ_acc++) { + targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id, + &targ_id); + if (!targ_type) + return -EINVAL; + + if (local_acc->name) { + matched = bpf_core_match_member(local_spec->btf, + local_acc, + targ_btf, targ_id, + targ_spec, &targ_id); + if (matched <= 0) + return matched; + } else { + /* for i=0, targ_id is already treated as array element + * type (because it's the original struct), for others + * we should find array element type first + */ + if (i > 0) { + const struct btf_array *a; + + if (!btf_is_array(targ_type)) + return 0; + + a = btf_array(targ_type); + if (local_acc->idx >= a->nelems) + return 0; + if (!skip_mods_and_typedefs(targ_btf, a->type, + &targ_id)) + return -EINVAL; + } + + /* too deep struct/union/array nesting */ + if (targ_spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + + targ_acc->type_id = targ_id; + targ_acc->idx = local_acc->idx; + targ_acc->name = NULL; + targ_spec->len++; + targ_spec->raw_spec[targ_spec->raw_len] = targ_acc->idx; + targ_spec->raw_len++; + + sz = btf__resolve_size(targ_btf, targ_id); + if (sz < 0) + return sz; + targ_spec->bit_offset += local_acc->idx * sz * 8; + } + } + + return 1; +} + +static int bpf_core_calc_field_relo(const struct bpf_program *prog, + const struct bpf_field_reloc *relo, + const struct bpf_core_spec *spec, + __u32 *val, bool *validate) +{ + const struct bpf_core_accessor *acc = &spec->spec[spec->len - 1]; + const struct btf_type *t = btf__type_by_id(spec->btf, acc->type_id); + __u32 byte_off, byte_sz, bit_off, bit_sz; + const struct btf_member *m; + const struct btf_type *mt; + bool bitfield; + __s64 sz; + + /* a[n] accessor needs special handling */ + if (!acc->name) { + if (relo->kind == BPF_FIELD_BYTE_OFFSET) { + *val = spec->bit_offset / 8; + } else if (relo->kind == BPF_FIELD_BYTE_SIZE) { + sz = btf__resolve_size(spec->btf, acc->type_id); + if (sz < 0) + return -EINVAL; + *val = sz; + } else { + pr_warn("prog '%s': relo %d at insn #%d can't be applied to array access\n", + bpf_program__title(prog, false), + relo->kind, relo->insn_off / 8); + return -EINVAL; + } + if (validate) + *validate = true; + return 0; + } + + m = btf_members(t) + acc->idx; + mt = skip_mods_and_typedefs(spec->btf, m->type, NULL); + bit_off = spec->bit_offset; + bit_sz = btf_member_bitfield_size(t, acc->idx); + + bitfield = bit_sz > 0; + if (bitfield) { + byte_sz = mt->size; + byte_off = bit_off / 8 / byte_sz * byte_sz; + /* figure out smallest int size necessary for bitfield load */ + while (bit_off + bit_sz - byte_off * 8 > byte_sz * 8) { + if (byte_sz >= 8) { + /* bitfield can't be read with 64-bit read */ + pr_warn("prog '%s': relo %d at insn #%d can't be satisfied for bitfield\n", + bpf_program__title(prog, false), + relo->kind, relo->insn_off / 8); + return -E2BIG; + } + byte_sz *= 2; + byte_off = bit_off / 8 / byte_sz * byte_sz; + } + } else { + sz = btf__resolve_size(spec->btf, m->type); + if (sz < 0) + return -EINVAL; + byte_sz = sz; + byte_off = spec->bit_offset / 8; + bit_sz = byte_sz * 8; + } + + /* for bitfields, all the relocatable aspects are ambiguous and we + * might disagree with compiler, so turn off validation of expected + * value, except for signedness + */ + if (validate) + *validate = !bitfield; + + switch (relo->kind) { + case BPF_FIELD_BYTE_OFFSET: + *val = byte_off; + break; + case BPF_FIELD_BYTE_SIZE: + *val = byte_sz; + break; + case BPF_FIELD_SIGNED: + /* enums will be assumed unsigned */ + *val = btf_is_enum(mt) || + (btf_int_encoding(mt) & BTF_INT_SIGNED); + if (validate) + *validate = true; /* signedness is never ambiguous */ + break; + case BPF_FIELD_LSHIFT_U64: +#if __BYTE_ORDER == __LITTLE_ENDIAN + *val = 64 - (bit_off + bit_sz - byte_off * 8); +#else + *val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8); +#endif + break; + case BPF_FIELD_RSHIFT_U64: + *val = 64 - bit_sz; + if (validate) + *validate = true; /* right shift is never ambiguous */ + break; + case BPF_FIELD_EXISTS: + default: + pr_warn("prog '%s': unknown relo %d at insn #%d\n", + bpf_program__title(prog, false), + relo->kind, relo->insn_off / 8); + return -EINVAL; + } + + return 0; +} + +/* + * Patch relocatable BPF instruction. + * + * Patched value is determined by relocation kind and target specification. + * For field existence relocation target spec will be NULL if field is not + * found. + * Expected insn->imm value is determined using relocation kind and local + * spec, and is checked before patching instruction. If actual insn->imm value + * is wrong, bail out with error. + * + * Currently three kinds of BPF instructions are supported: + * 1. rX = <imm> (assignment with immediate operand); + * 2. rX += <imm> (arithmetic operations with immediate operand); + */ +static int bpf_core_reloc_insn(struct bpf_program *prog, + const struct bpf_field_reloc *relo, + const struct bpf_core_spec *local_spec, + const struct bpf_core_spec *targ_spec) +{ + bool failed = false, validate = true; + __u32 orig_val, new_val; + struct bpf_insn *insn; + int insn_idx, err; + __u8 class; + + if (relo->insn_off % sizeof(struct bpf_insn)) + return -EINVAL; + insn_idx = relo->insn_off / sizeof(struct bpf_insn); + + if (relo->kind == BPF_FIELD_EXISTS) { + orig_val = 1; /* can't generate EXISTS relo w/o local field */ + new_val = targ_spec ? 1 : 0; + } else if (!targ_spec) { + failed = true; + new_val = (__u32)-1; + } else { + err = bpf_core_calc_field_relo(prog, relo, local_spec, + &orig_val, &validate); + if (err) + return err; + err = bpf_core_calc_field_relo(prog, relo, targ_spec, + &new_val, NULL); + if (err) + return err; + } + + insn = &prog->insns[insn_idx]; + class = BPF_CLASS(insn->code); + + if (class == BPF_ALU || class == BPF_ALU64) { + if (BPF_SRC(insn->code) != BPF_K) + return -EINVAL; + if (!failed && validate && insn->imm != orig_val) { + pr_warn("prog '%s': unexpected insn #%d value: got %u, exp %u -> %u\n", + bpf_program__title(prog, false), insn_idx, + insn->imm, orig_val, new_val); + return -EINVAL; + } + orig_val = insn->imm; + insn->imm = new_val; + pr_debug("prog '%s': patched insn #%d (ALU/ALU64)%s imm %u -> %u\n", + bpf_program__title(prog, false), insn_idx, + failed ? " w/ failed reloc" : "", orig_val, new_val); + } else { + pr_warn("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n", + bpf_program__title(prog, false), + insn_idx, insn->code, insn->src_reg, insn->dst_reg, + insn->off, insn->imm); + return -EINVAL; + } + + return 0; +} + +static struct btf *btf_load_raw(const char *path) +{ + struct btf *btf; + size_t read_cnt; + struct stat st; + void *data; + FILE *f; + + if (stat(path, &st)) + return ERR_PTR(-errno); + + data = malloc(st.st_size); + if (!data) + return ERR_PTR(-ENOMEM); + + f = fopen(path, "rb"); + if (!f) { + btf = ERR_PTR(-errno); + goto cleanup; + } + + read_cnt = fread(data, 1, st.st_size, f); + fclose(f); + if (read_cnt < st.st_size) { + btf = ERR_PTR(-EBADF); + goto cleanup; + } + + btf = btf__new(data, read_cnt); + +cleanup: + free(data); + return btf; +} + +/* + * Probe few well-known locations for vmlinux kernel image and try to load BTF + * data out of it to use for target BTF. + */ +static struct btf *bpf_core_find_kernel_btf(void) +{ + struct { + const char *path_fmt; + bool raw_btf; + } 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" }, + }; + char path[PATH_MAX + 1]; + struct utsname buf; + struct btf *btf; + int i; + + uname(&buf); + + for (i = 0; i < ARRAY_SIZE(locations); i++) { + snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release); + + if (access(path, R_OK)) + continue; + + if (locations[i].raw_btf) + btf = btf_load_raw(path); + else + btf = btf__parse_elf(path, NULL); + + pr_debug("loading kernel BTF '%s': %ld\n", + path, IS_ERR(btf) ? PTR_ERR(btf) : 0); + if (IS_ERR(btf)) + continue; + + return btf; + } + + pr_warn("failed to find valid kernel BTF\n"); + return ERR_PTR(-ESRCH); +} + +/* Output spec definition in the format: + * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>, + * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b + */ +static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) +{ + const struct btf_type *t; + const char *s; + __u32 type_id; + int i; + + type_id = spec->spec[0].type_id; + t = btf__type_by_id(spec->btf, type_id); + s = btf__name_by_offset(spec->btf, t->name_off); + libbpf_print(level, "[%u] %s + ", type_id, s); + + for (i = 0; i < spec->raw_len; i++) + libbpf_print(level, "%d%s", spec->raw_spec[i], + i == spec->raw_len - 1 ? " => " : ":"); + + libbpf_print(level, "%u.%u @ &x", + spec->bit_offset / 8, spec->bit_offset % 8); + + for (i = 0; i < spec->len; i++) { + if (spec->spec[i].name) + libbpf_print(level, ".%s", spec->spec[i].name); + else + libbpf_print(level, "[%u]", spec->spec[i].idx); + } + +} + +static size_t bpf_core_hash_fn(const void *key, void *ctx) +{ + return (size_t)key; +} + +static bool bpf_core_equal_fn(const void *k1, const void *k2, void *ctx) +{ + return k1 == k2; +} + +static void *u32_as_hash_key(__u32 x) +{ + return (void *)(uintptr_t)x; +} + +/* + * CO-RE relocate single instruction. + * + * The outline and important points of the algorithm: + * 1. For given local type, find corresponding candidate target types. + * Candidate type is a type with the same "essential" name, ignoring + * everything after last triple underscore (___). E.g., `sample`, + * `sample___flavor_one`, `sample___flavor_another_one`, are all candidates + * for each other. Names with triple underscore are referred to as + * "flavors" and are useful, among other things, to allow to + * specify/support incompatible variations of the same kernel struct, which + * might differ between different kernel versions and/or build + * configurations. + * + * N.B. Struct "flavors" could be generated by bpftool's BTF-to-C + * converter, when deduplicated BTF of a kernel still contains more than + * one different types with the same name. In that case, ___2, ___3, etc + * are appended starting from second name conflict. But start flavors are + * also useful to be defined "locally", in BPF program, to extract same + * data from incompatible changes between different kernel + * versions/configurations. For instance, to handle field renames between + * kernel versions, one can use two flavors of the struct name with the + * same common name and use conditional relocations to extract that field, + * depending on target kernel version. + * 2. For each candidate type, try to match local specification to this + * candidate target type. Matching involves finding corresponding + * high-level spec accessors, meaning that all named fields should match, + * as well as all array accesses should be within the actual bounds. Also, + * types should be compatible (see bpf_core_fields_are_compat for details). + * 3. It is supported and expected that there might be multiple flavors + * matching the spec. As long as all the specs resolve to the same set of + * offsets across all candidates, there is no error. If there is any + * ambiguity, CO-RE relocation will fail. This is necessary to accomodate + * imprefection of BTF deduplication, which can cause slight duplication of + * the same BTF type, if some directly or indirectly referenced (by + * pointer) type gets resolved to different actual types in different + * object files. If such situation occurs, deduplicated BTF will end up + * with two (or more) structurally identical types, which differ only in + * types they refer to through pointer. This should be OK in most cases and + * is not an error. + * 4. Candidate types search is performed by linearly scanning through all + * types in target BTF. It is anticipated that this is overall more + * efficient memory-wise and not significantly worse (if not better) + * CPU-wise compared to prebuilding a map from all local type names to + * a list of candidate type names. It's also sped up by caching resolved + * list of matching candidates per each local "root" type ID, that has at + * least one bpf_field_reloc associated with it. This list is shared + * between multiple relocations for the same type ID and is updated as some + * of the candidates are pruned due to structural incompatibility. + */ +static int bpf_core_reloc_field(struct bpf_program *prog, + const struct bpf_field_reloc *relo, + int relo_idx, + const struct btf *local_btf, + const struct btf *targ_btf, + struct hashmap *cand_cache) +{ + const char *prog_name = bpf_program__title(prog, false); + struct bpf_core_spec local_spec, cand_spec, targ_spec; + const void *type_key = u32_as_hash_key(relo->type_id); + const struct btf_type *local_type, *cand_type; + const char *local_name, *cand_name; + struct ids_vec *cand_ids; + __u32 local_id, cand_id; + const char *spec_str; + int i, j, err; + + local_id = relo->type_id; + local_type = btf__type_by_id(local_btf, local_id); + if (!local_type) + return -EINVAL; + + local_name = btf__name_by_offset(local_btf, local_type->name_off); + if (str_is_empty(local_name)) + return -EINVAL; + + spec_str = btf__name_by_offset(local_btf, relo->access_str_off); + if (str_is_empty(spec_str)) + return -EINVAL; + + err = bpf_core_spec_parse(local_btf, local_id, spec_str, &local_spec); + if (err) { + pr_warn("prog '%s': relo #%d: parsing [%d] %s + %s failed: %d\n", + prog_name, relo_idx, local_id, local_name, spec_str, + err); + return -EINVAL; + } + + pr_debug("prog '%s': relo #%d: kind %d, spec is ", prog_name, relo_idx, + relo->kind); + bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec); + libbpf_print(LIBBPF_DEBUG, "\n"); + + if (!hashmap__find(cand_cache, type_key, (void **)&cand_ids)) { + cand_ids = bpf_core_find_cands(local_btf, local_id, targ_btf); + if (IS_ERR(cand_ids)) { + pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s: %ld", + prog_name, relo_idx, local_id, local_name, + PTR_ERR(cand_ids)); + return PTR_ERR(cand_ids); + } + err = hashmap__set(cand_cache, type_key, cand_ids, NULL, NULL); + if (err) { + bpf_core_free_cands(cand_ids); + return err; + } + } + + for (i = 0, j = 0; i < cand_ids->len; i++) { + cand_id = cand_ids->data[i]; + cand_type = btf__type_by_id(targ_btf, cand_id); + cand_name = btf__name_by_offset(targ_btf, cand_type->name_off); + + err = bpf_core_spec_match(&local_spec, targ_btf, + cand_id, &cand_spec); + pr_debug("prog '%s': relo #%d: matching candidate #%d %s against spec ", + prog_name, relo_idx, i, cand_name); + bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec); + libbpf_print(LIBBPF_DEBUG, ": %d\n", err); + if (err < 0) { + pr_warn("prog '%s': relo #%d: matching error: %d\n", + prog_name, relo_idx, err); + return err; + } + if (err == 0) + continue; + + if (j == 0) { + targ_spec = cand_spec; + } else if (cand_spec.bit_offset != targ_spec.bit_offset) { + /* if there are many candidates, they should all + * resolve to the same bit offset + */ + pr_warn("prog '%s': relo #%d: offset ambiguity: %u != %u\n", + prog_name, relo_idx, cand_spec.bit_offset, + targ_spec.bit_offset); + return -EINVAL; + } + + cand_ids->data[j++] = cand_spec.spec[0].type_id; + } + + /* + * For BPF_FIELD_EXISTS relo or when relaxed CO-RE reloc mode is + * requested, it's expected that we might not find any candidates. + * In this case, if field wasn't found in any candidate, the list of + * candidates shouldn't change at all, we'll just handle relocating + * appropriately, depending on relo's kind. + */ + if (j > 0) + cand_ids->len = j; + + if (j == 0 && !prog->obj->relaxed_core_relocs && + relo->kind != BPF_FIELD_EXISTS) { + pr_warn("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n", + prog_name, relo_idx, local_id, local_name, spec_str); + return -ESRCH; + } + + /* bpf_core_reloc_insn should know how to handle missing targ_spec */ + err = bpf_core_reloc_insn(prog, relo, &local_spec, + j ? &targ_spec : NULL); + if (err) { + pr_warn("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n", + prog_name, relo_idx, relo->insn_off, err); + return -EINVAL; + } + + return 0; +} + +static int +bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path) +{ + const struct btf_ext_info_sec *sec; + const struct bpf_field_reloc *rec; + const struct btf_ext_info *seg; + struct hashmap_entry *entry; + struct hashmap *cand_cache = NULL; + struct bpf_program *prog; + struct btf *targ_btf; + const char *sec_name; + int i, err = 0; + + if (targ_btf_path) + targ_btf = btf__parse_elf(targ_btf_path, NULL); + else + targ_btf = bpf_core_find_kernel_btf(); + if (IS_ERR(targ_btf)) { + pr_warn("failed to get target BTF: %ld\n", PTR_ERR(targ_btf)); + return PTR_ERR(targ_btf); + } + + cand_cache = hashmap__new(bpf_core_hash_fn, bpf_core_equal_fn, NULL); + if (IS_ERR(cand_cache)) { + err = PTR_ERR(cand_cache); + goto out; + } + + seg = &obj->btf_ext->field_reloc_info; + for_each_btf_ext_sec(seg, sec) { + sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off); + if (str_is_empty(sec_name)) { + err = -EINVAL; + goto out; + } + prog = bpf_object__find_program_by_title(obj, sec_name); + if (!prog) { + pr_warn("failed to find program '%s' for CO-RE offset relocation\n", + sec_name); + err = -EINVAL; + goto out; + } + + pr_debug("prog '%s': performing %d CO-RE offset relocs\n", + sec_name, sec->num_info); + + for_each_btf_ext_rec(seg, sec, i, rec) { + err = bpf_core_reloc_field(prog, rec, i, obj->btf, + targ_btf, cand_cache); + if (err) { + pr_warn("prog '%s': relo #%d: failed to relocate: %d\n", + sec_name, i, err); + goto out; + } + } + } + +out: + btf__free(targ_btf); + if (!IS_ERR_OR_NULL(cand_cache)) { + hashmap__for_each_entry(cand_cache, entry, i) { + bpf_core_free_cands(entry->value); + } + hashmap__free(cand_cache); + } + return err; +} + +static int +bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) +{ + int err = 0; + + if (obj->btf_ext->field_reloc_info.len) + err = bpf_core_reloc_fields(obj, targ_btf_path); + + return err; +} + +static int +bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, + struct reloc_desc *relo) +{ + struct bpf_insn *insn, *new_insn; + struct bpf_program *text; + size_t new_cnt; + int err; + + if (relo->type != RELO_CALL) + return -LIBBPF_ERRNO__RELOC; + + if (prog->idx == obj->efile.text_shndx) { + pr_warn("relo in .text insn %d into off %d (insn #%d)\n", + relo->insn_idx, relo->sym_off, relo->sym_off / 8); + return -LIBBPF_ERRNO__RELOC; + } + + if (prog->main_prog_cnt == 0) { + text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx); + if (!text) { + pr_warn("no .text section found yet relo into text exist\n"); + return -LIBBPF_ERRNO__RELOC; + } + new_cnt = prog->insns_cnt + text->insns_cnt; + new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn)); + if (!new_insn) { + pr_warn("oom in prog realloc\n"); + return -ENOMEM; + } + prog->insns = new_insn; + + if (obj->btf_ext) { + err = bpf_program_reloc_btf_ext(prog, obj, + text->section_name, + prog->insns_cnt); + if (err) + return err; + } + + memcpy(new_insn + prog->insns_cnt, text->insns, + text->insns_cnt * sizeof(*insn)); + prog->main_prog_cnt = prog->insns_cnt; + prog->insns_cnt = new_cnt; + pr_debug("added %zd insn from %s to prog %s\n", + text->insns_cnt, text->section_name, + prog->section_name); + } + insn = &prog->insns[relo->insn_idx]; + insn->imm += relo->sym_off / 8 + prog->main_prog_cnt - relo->insn_idx; + return 0; +} + +static int +bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) +{ + int i, err; + + if (!prog) + return 0; + + if (obj->btf_ext) { + err = bpf_program_reloc_btf_ext(prog, obj, + prog->section_name, 0); + if (err) + return err; + } + + if (!prog->reloc_desc) + return 0; + + for (i = 0; i < prog->nr_reloc; i++) { + struct reloc_desc *relo = &prog->reloc_desc[i]; + + if (relo->type == RELO_LD64 || relo->type == RELO_DATA) { + struct bpf_insn *insn = &prog->insns[relo->insn_idx]; + + if (relo->insn_idx + 1 >= (int)prog->insns_cnt) { + pr_warn("relocation out of range: '%s'\n", + prog->section_name); + return -LIBBPF_ERRNO__RELOC; + } + + if (relo->type != RELO_DATA) { + insn[0].src_reg = BPF_PSEUDO_MAP_FD; + } else { + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[1].imm = insn[0].imm + relo->sym_off; + } + insn[0].imm = obj->maps[relo->map_idx].fd; + } else if (relo->type == RELO_CALL) { + err = bpf_program__reloc_text(prog, obj, relo); + if (err) + return err; + } + } + + zfree(&prog->reloc_desc); + prog->nr_reloc = 0; + return 0; +} + +static int +bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) +{ + struct bpf_program *prog; + size_t i; + int err; + + if (obj->btf_ext) { + err = bpf_object__relocate_core(obj, targ_btf_path); + if (err) { + pr_warn("failed to perform CO-RE relocations: %d\n", + err); + return err; + } + } + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + + err = bpf_program__relocate(prog, obj); + if (err) { + pr_warn("failed to relocate '%s'\n", prog->section_name); + return err; + } + } + return 0; +} + +static int bpf_object__collect_reloc(struct bpf_object *obj) +{ + int i, err; + + if (!obj_elf_valid(obj)) { + pr_warn("Internal error: elf object is closed\n"); + return -LIBBPF_ERRNO__INTERNAL; + } + + for (i = 0; i < obj->efile.nr_reloc_sects; i++) { + GElf_Shdr *shdr = &obj->efile.reloc_sects[i].shdr; + Elf_Data *data = obj->efile.reloc_sects[i].data; + int idx = shdr->sh_info; + struct bpf_program *prog; + + if (shdr->sh_type != SHT_REL) { + pr_warn("internal error at %d\n", __LINE__); + return -LIBBPF_ERRNO__INTERNAL; + } + + prog = bpf_object__find_prog_by_idx(obj, idx); + if (!prog) { + pr_warn("relocation failed: no section(%d)\n", idx); + return -LIBBPF_ERRNO__RELOC; + } + + err = bpf_program__collect_reloc(prog, shdr, data, obj); + if (err) + return err; + } + return 0; +} + +static int +load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, + char *license, __u32 kern_version, int *pfd) +{ + struct bpf_load_program_attr load_attr; + char *cp, errmsg[STRERR_BUFSIZE]; + int log_buf_size = BPF_LOG_BUF_SIZE; + char *log_buf; + int btf_fd, 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; + if (prog->caps->name) + load_attr.name = prog->name; + load_attr.insns = insns; + load_attr.insns_cnt = insns_cnt; + load_attr.license = license; + if (prog->type == BPF_PROG_TYPE_TRACING) { + load_attr.attach_prog_fd = prog->attach_prog_fd; + load_attr.attach_btf_id = prog->attach_btf_id; + } else { + load_attr.kern_version = kern_version; + load_attr.prog_ifindex = prog->prog_ifindex; + } + /* if .BTF.ext was loaded, kernel supports associated BTF for prog */ + if (prog->obj->btf_ext) + btf_fd = bpf_object__btf_fd(prog->obj); + else + btf_fd = -1; + load_attr.prog_btf_fd = btf_fd >= 0 ? btf_fd : 0; + load_attr.func_info = prog->func_info; + load_attr.func_info_rec_size = prog->func_info_rec_size; + load_attr.func_info_cnt = prog->func_info_cnt; + load_attr.line_info = prog->line_info; + 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; + load_attr.prog_flags = prog->prog_flags; + +retry_load: + log_buf = malloc(log_buf_size); + if (!log_buf) + pr_warn("Alloc log buffer for bpf loader error, continue without log\n"); + + ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size); + + if (ret >= 0) { + if (load_attr.log_level) + pr_debug("verifier log:\n%s", log_buf); + *pfd = ret; + ret = 0; + goto out; + } + + if (errno == ENOSPC) { + log_buf_size <<= 1; + free(log_buf); + goto retry_load; + } + ret = -errno; + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("load bpf program failed: %s\n", cp); + + if (log_buf && log_buf[0] != '\0') { + ret = -LIBBPF_ERRNO__VERIFY; + pr_warn("-- BEGIN DUMP LOG ---\n"); + pr_warn("\n%s\n", log_buf); + pr_warn("-- END LOG --\n"); + } else if (load_attr.insns_cnt >= BPF_MAXINSNS) { + pr_warn("Program too large (%zu insns), at most %d insns\n", + load_attr.insns_cnt, BPF_MAXINSNS); + ret = -LIBBPF_ERRNO__PROG2BIG; + } else if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) { + /* Wrong program type? */ + int fd; + + load_attr.prog_type = BPF_PROG_TYPE_KPROBE; + load_attr.expected_attach_type = 0; + fd = bpf_load_program_xattr(&load_attr, NULL, 0); + if (fd >= 0) { + close(fd); + ret = -LIBBPF_ERRNO__PROGTYPE; + goto out; + } + } + +out: + free(log_buf); + return ret; +} + +int +bpf_program__load(struct bpf_program *prog, + char *license, __u32 kern_version) +{ + int err = 0, fd, i; + + if (prog->instances.nr < 0 || !prog->instances.fds) { + if (prog->preprocessor) { + pr_warn("Internal error: can't load program '%s'\n", + prog->section_name); + return -LIBBPF_ERRNO__INTERNAL; + } + + prog->instances.fds = malloc(sizeof(int)); + if (!prog->instances.fds) { + pr_warn("Not enough memory for BPF fds\n"); + return -ENOMEM; + } + prog->instances.nr = 1; + prog->instances.fds[0] = -1; + } + + if (!prog->preprocessor) { + if (prog->instances.nr != 1) { + pr_warn("Program '%s' is inconsistent: nr(%d) != 1\n", + prog->section_name, prog->instances.nr); + } + err = load_program(prog, prog->insns, prog->insns_cnt, + license, kern_version, &fd); + if (!err) + prog->instances.fds[0] = fd; + goto out; + } + + for (i = 0; i < prog->instances.nr; i++) { + struct bpf_prog_prep_result result; + bpf_program_prep_t preprocessor = prog->preprocessor; + + memset(&result, 0, sizeof(result)); + err = preprocessor(prog, i, prog->insns, + prog->insns_cnt, &result); + if (err) { + pr_warn("Preprocessing the %dth instance of program '%s' failed\n", + i, prog->section_name); + goto out; + } + + if (!result.new_insn_ptr || !result.new_insn_cnt) { + pr_debug("Skip loading the %dth instance of program '%s'\n", + i, prog->section_name); + prog->instances.fds[i] = -1; + if (result.pfd) + *result.pfd = -1; + continue; + } + + err = load_program(prog, result.new_insn_ptr, + result.new_insn_cnt, + license, kern_version, &fd); + + if (err) { + pr_warn("Loading the %dth instance of program '%s' failed\n", + i, prog->section_name); + goto out; + } + + if (result.pfd) + *result.pfd = fd; + prog->instances.fds[i] = fd; + } +out: + if (err) + pr_warn("failed to load program '%s'\n", prog->section_name); + zfree(&prog->insns); + prog->insns_cnt = 0; + return err; +} + +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, int log_level) +{ + size_t i; + int err; + + 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); + if (err) + return err; + } + return 0; +} + +static int libbpf_find_attach_btf_id(const char *name, + enum bpf_attach_type attach_type, + __u32 attach_prog_fd); +static struct bpf_object * +__bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, + struct bpf_object_open_opts *opts) +{ + const char *pin_root_path; + struct bpf_program *prog; + struct bpf_object *obj; + const char *obj_name; + char tmp_name[64]; + bool relaxed_maps; + __u32 attach_prog_fd; + int err; + + if (elf_version(EV_CURRENT) == EV_NONE) { + pr_warn("failed to init libelf for %s\n", + path ? : "(mem buf)"); + return ERR_PTR(-LIBBPF_ERRNO__LIBELF); + } + + if (!OPTS_VALID(opts, bpf_object_open_opts)) + return ERR_PTR(-EINVAL); + + obj_name = OPTS_GET(opts, object_name, NULL); + if (obj_buf) { + if (!obj_name) { + snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx", + (unsigned long)obj_buf, + (unsigned long)obj_buf_sz); + obj_name = tmp_name; + } + path = obj_name; + pr_debug("loading object '%s' from buffer\n", obj_name); + } + + obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name); + if (IS_ERR(obj)) + return obj; + + obj->relaxed_core_relocs = OPTS_GET(opts, relaxed_core_relocs, false); + relaxed_maps = OPTS_GET(opts, relaxed_maps, false); + pin_root_path = OPTS_GET(opts, pin_root_path, NULL); + attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); + + CHECK_ERR(bpf_object__elf_init(obj), err, out); + CHECK_ERR(bpf_object__check_endianness(obj), err, out); + CHECK_ERR(bpf_object__probe_caps(obj), err, out); + CHECK_ERR(bpf_object__elf_collect(obj, relaxed_maps, pin_root_path), + err, out); + CHECK_ERR(bpf_object__collect_reloc(obj), err, out); + bpf_object__elf_finish(obj); + + bpf_object__for_each_program(prog, obj) { + enum bpf_prog_type prog_type; + enum bpf_attach_type attach_type; + + err = libbpf_prog_type_by_name(prog->section_name, &prog_type, + &attach_type); + if (err == -ESRCH) + /* couldn't guess, but user might manually specify */ + continue; + if (err) + goto out; + + bpf_program__set_type(prog, prog_type); + bpf_program__set_expected_attach_type(prog, attach_type); + if (prog_type == BPF_PROG_TYPE_TRACING) { + err = libbpf_find_attach_btf_id(prog->section_name, + attach_type, + attach_prog_fd); + if (err <= 0) + goto out; + prog->attach_btf_id = err; + prog->attach_prog_fd = attach_prog_fd; + } + } + + return obj; +out: + bpf_object__close(obj); + return ERR_PTR(err); +} + +static struct bpf_object * +__bpf_object__open_xattr(struct bpf_object_open_attr *attr, int flags) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, + .relaxed_maps = flags & MAPS_RELAX_COMPAT, + ); + + /* param validation */ + if (!attr->file) + return NULL; + + pr_debug("loading %s\n", attr->file); + return __bpf_object__open(attr->file, NULL, 0, &opts); +} + +struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr) +{ + return __bpf_object__open_xattr(attr, 0); +} + +struct bpf_object *bpf_object__open(const char *path) +{ + struct bpf_object_open_attr attr = { + .file = path, + .prog_type = BPF_PROG_TYPE_UNSPEC, + }; + + return bpf_object__open_xattr(&attr); +} + +struct bpf_object * +bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts) +{ + if (!path) + return ERR_PTR(-EINVAL); + + pr_debug("loading %s\n", path); + + return __bpf_object__open(path, NULL, 0, opts); +} + +struct bpf_object * +bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, + struct bpf_object_open_opts *opts) +{ + if (!obj_buf || obj_buf_sz == 0) + return ERR_PTR(-EINVAL); + + return __bpf_object__open(NULL, obj_buf, obj_buf_sz, opts); +} + +struct bpf_object * +bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, + const char *name) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, + .object_name = name, + /* wrong default, but backwards-compatible */ + .relaxed_maps = true, + ); + + /* returning NULL is wrong, but backwards-compatible */ + if (!obj_buf || obj_buf_sz == 0) + return NULL; + + return bpf_object__open_mem(obj_buf, obj_buf_sz, &opts); +} + +int bpf_object__unload(struct bpf_object *obj) +{ + size_t i; + + if (!obj) + return -EINVAL; + + for (i = 0; i < obj->nr_maps; i++) + zclose(obj->maps[i].fd); + + for (i = 0; i < obj->nr_programs; i++) + bpf_program__unload(&obj->programs[i]); + + return 0; +} + +int bpf_object__load_xattr(struct bpf_object_load_attr *attr) +{ + struct bpf_object *obj; + int err, i; + + if (!attr) + return -EINVAL; + obj = attr->obj; + if (!obj) + return -EINVAL; + + if (obj->loaded) { + pr_warn("object should not be loaded twice\n"); + return -EINVAL; + } + + obj->loaded = true; + + CHECK_ERR(bpf_object__create_maps(obj), err, out); + CHECK_ERR(bpf_object__relocate(obj, attr->target_btf_path), err, out); + CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out); + + return 0; +out: + /* unpin any maps that were auto-pinned during load */ + for (i = 0; i < obj->nr_maps; i++) + if (obj->maps[i].pinned && !obj->maps[i].reused) + bpf_map__unpin(&obj->maps[i], NULL); + + bpf_object__unload(obj); + pr_warn("failed to load object '%s'\n", obj->path); + 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 make_parent_dir(const char *path) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + char *dname, *dir; + int err = 0; + + dname = strdup(path); + if (dname == NULL) + return -ENOMEM; + + dir = dirname(dname); + if (mkdir(dir, 0700) && errno != EEXIST) + err = -errno; + + free(dname); + if (err) { + cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); + pr_warn("failed to mkdir %s: %s\n", path, cp); + } + return err; +} + +static int check_path(const char *path) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + struct statfs st_fs; + char *dname, *dir; + int err = 0; + + if (path == NULL) + return -EINVAL; + + dname = strdup(path); + if (dname == NULL) + return -ENOMEM; + + dir = dirname(dname); + if (statfs(dir, &st_fs)) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("failed to statfs %s: %s\n", dir, cp); + err = -errno; + } + free(dname); + + if (!err && st_fs.f_type != BPF_FS_MAGIC) { + pr_warn("specified path %s is not on BPF FS\n", path); + err = -EINVAL; + } + + return err; +} + +int bpf_program__pin_instance(struct bpf_program *prog, const char *path, + int instance) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err; + + err = make_parent_dir(path); + if (err) + return err; + + err = check_path(path); + if (err) + return err; + + if (prog == NULL) { + pr_warn("invalid program pointer\n"); + return -EINVAL; + } + + if (instance < 0 || instance >= prog->instances.nr) { + pr_warn("invalid prog instance %d of prog %s (max %d)\n", + instance, prog->section_name, prog->instances.nr); + return -EINVAL; + } + + if (bpf_obj_pin(prog->instances.fds[instance], path)) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("failed to pin program: %s\n", cp); + return -errno; + } + pr_debug("pinned program '%s'\n", path); + + return 0; +} + +int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, + int instance) +{ + int err; + + err = check_path(path); + if (err) + return err; + + if (prog == NULL) { + pr_warn("invalid program pointer\n"); + return -EINVAL; + } + + if (instance < 0 || instance >= prog->instances.nr) { + pr_warn("invalid prog instance %d of prog %s (max %d)\n", + instance, prog->section_name, prog->instances.nr); + return -EINVAL; + } + + err = unlink(path); + if (err != 0) + return -errno; + pr_debug("unpinned program '%s'\n", path); + + return 0; +} + +int bpf_program__pin(struct bpf_program *prog, const char *path) +{ + int i, err; + + err = make_parent_dir(path); + if (err) + return err; + + err = check_path(path); + if (err) + return err; + + if (prog == NULL) { + pr_warn("invalid program pointer\n"); + return -EINVAL; + } + + if (prog->instances.nr <= 0) { + pr_warn("no instances of prog %s to pin\n", + prog->section_name); + return -EINVAL; + } + + if (prog->instances.nr == 1) { + /* don't create subdirs when pinning single instance */ + return bpf_program__pin_instance(prog, path, 0); + } + + for (i = 0; i < prog->instances.nr; i++) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%d", path, i); + if (len < 0) { + err = -EINVAL; + goto err_unpin; + } else if (len >= PATH_MAX) { + err = -ENAMETOOLONG; + goto err_unpin; + } + + err = bpf_program__pin_instance(prog, buf, i); + if (err) + goto err_unpin; + } + + return 0; + +err_unpin: + for (i = i - 1; i >= 0; i--) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%d", path, i); + if (len < 0) + continue; + else if (len >= PATH_MAX) + continue; + + bpf_program__unpin_instance(prog, buf, i); + } + + rmdir(path); + + return err; +} + +int bpf_program__unpin(struct bpf_program *prog, const char *path) +{ + int i, err; + + err = check_path(path); + if (err) + return err; + + if (prog == NULL) { + pr_warn("invalid program pointer\n"); + return -EINVAL; + } + + if (prog->instances.nr <= 0) { + pr_warn("no instances of prog %s to pin\n", + prog->section_name); + return -EINVAL; + } + + if (prog->instances.nr == 1) { + /* don't create subdirs when pinning single instance */ + return bpf_program__unpin_instance(prog, path, 0); + } + + for (i = 0; i < prog->instances.nr; i++) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%d", path, i); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + err = bpf_program__unpin_instance(prog, buf, i); + if (err) + return err; + } + + err = rmdir(path); + if (err) + return -errno; + + return 0; +} + +int bpf_map__pin(struct bpf_map *map, const char *path) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err; + + if (map == NULL) { + pr_warn("invalid map pointer\n"); + return -EINVAL; + } + + if (map->pin_path) { + if (path && strcmp(path, map->pin_path)) { + pr_warn("map '%s' already has pin path '%s' different from '%s'\n", + bpf_map__name(map), map->pin_path, path); + return -EINVAL; + } else if (map->pinned) { + pr_debug("map '%s' already pinned at '%s'; not re-pinning\n", + bpf_map__name(map), map->pin_path); + return 0; + } + } else { + if (!path) { + pr_warn("missing a path to pin map '%s' at\n", + bpf_map__name(map)); + return -EINVAL; + } else if (map->pinned) { + pr_warn("map '%s' already pinned\n", bpf_map__name(map)); + return -EEXIST; + } + + map->pin_path = strdup(path); + if (!map->pin_path) { + err = -errno; + goto out_err; + } + } + + err = make_parent_dir(map->pin_path); + if (err) + return err; + + err = check_path(map->pin_path); + if (err) + return err; + + if (bpf_obj_pin(map->fd, map->pin_path)) { + err = -errno; + goto out_err; + } + + map->pinned = true; + pr_debug("pinned map '%s'\n", map->pin_path); + + return 0; + +out_err: + cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); + pr_warn("failed to pin map: %s\n", cp); + return err; +} + +int bpf_map__unpin(struct bpf_map *map, const char *path) +{ + int err; + + if (map == NULL) { + pr_warn("invalid map pointer\n"); + return -EINVAL; + } + + if (map->pin_path) { + if (path && strcmp(path, map->pin_path)) { + pr_warn("map '%s' already has pin path '%s' different from '%s'\n", + bpf_map__name(map), map->pin_path, path); + return -EINVAL; + } + path = map->pin_path; + } else if (!path) { + pr_warn("no path to unpin map '%s' from\n", + bpf_map__name(map)); + return -EINVAL; + } + + err = check_path(path); + if (err) + return err; + + err = unlink(path); + if (err != 0) + return -errno; + + map->pinned = false; + pr_debug("unpinned map '%s' from '%s'\n", bpf_map__name(map), path); + + return 0; +} + +int bpf_map__set_pin_path(struct bpf_map *map, const char *path) +{ + char *new = NULL; + + if (path) { + new = strdup(path); + if (!new) + return -errno; + } + + free(map->pin_path); + map->pin_path = new; + return 0; +} + +const char *bpf_map__get_pin_path(const struct bpf_map *map) +{ + return map->pin_path; +} + +bool bpf_map__is_pinned(const struct bpf_map *map) +{ + return map->pinned; +} + +int bpf_object__pin_maps(struct bpf_object *obj, const char *path) +{ + struct bpf_map *map; + int err; + + if (!obj) + return -ENOENT; + + if (!obj->loaded) { + pr_warn("object not yet loaded; load it first\n"); + return -ENOENT; + } + + bpf_object__for_each_map(map, obj) { + char *pin_path = NULL; + char buf[PATH_MAX]; + + 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; + goto err_unpin_maps; + } + pin_path = buf; + } else if (!map->pin_path) { + continue; + } + + err = bpf_map__pin(map, pin_path); + if (err) + goto err_unpin_maps; + } + + return 0; + +err_unpin_maps: + while ((map = bpf_map__prev(map, obj))) { + if (!map->pin_path) + continue; + + bpf_map__unpin(map, NULL); + } + + return err; +} + +int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) +{ + struct bpf_map *map; + int err; + + if (!obj) + return -ENOENT; + + bpf_object__for_each_map(map, obj) { + char *pin_path = NULL; + char buf[PATH_MAX]; + + if (path) { + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + bpf_map__name(map)); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + pin_path = buf; + } else if (!map->pin_path) { + continue; + } + + err = bpf_map__unpin(map, pin_path); + if (err) + return err; + } + + return 0; +} + +int bpf_object__pin_programs(struct bpf_object *obj, const char *path) +{ + struct bpf_program *prog; + int err; + + if (!obj) + return -ENOENT; + + if (!obj->loaded) { + pr_warn("object not yet loaded; load it first\n"); + return -ENOENT; + } + + bpf_object__for_each_program(prog, obj) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + prog->pin_name); + if (len < 0) { + err = -EINVAL; + goto err_unpin_programs; + } else if (len >= PATH_MAX) { + err = -ENAMETOOLONG; + goto err_unpin_programs; + } + + err = bpf_program__pin(prog, buf); + if (err) + goto err_unpin_programs; + } + + return 0; + +err_unpin_programs: + while ((prog = bpf_program__prev(prog, obj))) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + prog->pin_name); + if (len < 0) + continue; + else if (len >= PATH_MAX) + continue; + + bpf_program__unpin(prog, buf); + } + + return err; +} + +int bpf_object__unpin_programs(struct bpf_object *obj, const char *path) +{ + struct bpf_program *prog; + int err; + + if (!obj) + return -ENOENT; + + bpf_object__for_each_program(prog, obj) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + prog->pin_name); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + err = bpf_program__unpin(prog, buf); + if (err) + return err; + } + + return 0; +} + +int bpf_object__pin(struct bpf_object *obj, const char *path) +{ + int err; + + err = bpf_object__pin_maps(obj, path); + if (err) + return err; + + err = bpf_object__pin_programs(obj, path); + if (err) { + bpf_object__unpin_maps(obj, path); + return err; + } + + return 0; +} + +void bpf_object__close(struct bpf_object *obj) +{ + size_t i; + + if (!obj) + return; + + if (obj->clear_priv) + obj->clear_priv(obj, obj->priv); + + bpf_object__elf_finish(obj); + bpf_object__unload(obj); + btf__free(obj->btf); + btf_ext__free(obj->btf_ext); + + for (i = 0; i < obj->nr_maps; i++) { + zfree(&obj->maps[i].name); + zfree(&obj->maps[i].pin_path); + if (obj->maps[i].clear_priv) + obj->maps[i].clear_priv(&obj->maps[i], + obj->maps[i].priv); + obj->maps[i].priv = NULL; + obj->maps[i].clear_priv = NULL; + } + + zfree(&obj->sections.rodata); + zfree(&obj->sections.data); + zfree(&obj->maps); + obj->nr_maps = 0; + + if (obj->programs && obj->nr_programs) { + for (i = 0; i < obj->nr_programs; i++) + bpf_program__exit(&obj->programs[i]); + } + zfree(&obj->programs); + + list_del(&obj->list); + free(obj); +} + +struct bpf_object * +bpf_object__next(struct bpf_object *prev) +{ + struct bpf_object *next; + + if (!prev) + next = list_first_entry(&bpf_objects_list, + struct bpf_object, + list); + else + next = list_next_entry(prev, list); + + /* Empty list is noticed here so don't need checking on entry. */ + if (&next->list == &bpf_objects_list) + return NULL; + + return next; +} + +const char *bpf_object__name(const struct bpf_object *obj) +{ + return obj ? obj->name : ERR_PTR(-EINVAL); +} + +unsigned int bpf_object__kversion(const struct bpf_object *obj) +{ + return obj ? obj->kern_version : 0; +} + +struct btf *bpf_object__btf(const struct bpf_object *obj) +{ + return obj ? obj->btf : NULL; +} + +int bpf_object__btf_fd(const struct bpf_object *obj) +{ + return obj->btf ? btf__fd(obj->btf) : -1; +} + +int bpf_object__set_priv(struct bpf_object *obj, void *priv, + bpf_object_clear_priv_t clear_priv) +{ + if (obj->priv && obj->clear_priv) + obj->clear_priv(obj, obj->priv); + + obj->priv = priv; + obj->clear_priv = clear_priv; + return 0; +} + +void *bpf_object__priv(const struct bpf_object *obj) +{ + return obj ? obj->priv : ERR_PTR(-EINVAL); +} + +static struct bpf_program * +__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; + + if (!nr_programs) + return NULL; + + if (!p) + /* Iter from the beginning */ + return forward ? &obj->programs[0] : + &obj->programs[nr_programs - 1]; + + if (p->obj != obj) { + pr_warn("error: program handler doesn't match object\n"); + return NULL; + } + + idx = (p - obj->programs) + (forward ? 1 : -1); + if (idx >= obj->nr_programs || idx < 0) + return NULL; + return &obj->programs[idx]; +} + +struct bpf_program * +bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj) +{ + struct bpf_program *prog = prev; + + do { + prog = __bpf_program__iter(prog, obj, true); + } while (prog && bpf_program__is_function_storage(prog, obj)); + + return prog; +} + +struct bpf_program * +bpf_program__prev(struct bpf_program *next, const struct bpf_object *obj) +{ + struct bpf_program *prog = next; + + do { + prog = __bpf_program__iter(prog, obj, false); + } while (prog && bpf_program__is_function_storage(prog, obj)); + + return prog; +} + +int bpf_program__set_priv(struct bpf_program *prog, void *priv, + bpf_program_clear_priv_t clear_priv) +{ + if (prog->priv && prog->clear_priv) + prog->clear_priv(prog, prog->priv); + + prog->priv = priv; + prog->clear_priv = clear_priv; + return 0; +} + +void *bpf_program__priv(const struct bpf_program *prog) +{ + return prog ? prog->priv : ERR_PTR(-EINVAL); +} + +void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex) +{ + prog->prog_ifindex = ifindex; +} + +const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy) +{ + const char *title; + + title = prog->section_name; + if (needs_copy) { + title = strdup(title); + if (!title) { + pr_warn("failed to strdup program title\n"); + return ERR_PTR(-ENOMEM); + } + } + + return title; +} + +int bpf_program__fd(const struct bpf_program *prog) +{ + return bpf_program__nth_fd(prog, 0); +} + +size_t bpf_program__size(const struct bpf_program *prog) +{ + return prog->insns_cnt * sizeof(struct bpf_insn); +} + +int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, + bpf_program_prep_t prep) +{ + int *instances_fds; + + if (nr_instances <= 0 || !prep) + return -EINVAL; + + if (prog->instances.nr > 0 || prog->instances.fds) { + pr_warn("Can't set pre-processor after loading\n"); + return -EINVAL; + } + + instances_fds = malloc(sizeof(int) * nr_instances); + if (!instances_fds) { + pr_warn("alloc memory failed for fds\n"); + return -ENOMEM; + } + + /* fill all fd with -1 */ + memset(instances_fds, -1, sizeof(int) * nr_instances); + + prog->instances.nr = nr_instances; + prog->instances.fds = instances_fds; + prog->preprocessor = prep; + return 0; +} + +int bpf_program__nth_fd(const struct bpf_program *prog, int n) +{ + int fd; + + if (!prog) + return -EINVAL; + + if (n >= prog->instances.nr || n < 0) { + pr_warn("Can't get the %dth fd from program %s: only %d instances\n", + n, prog->section_name, prog->instances.nr); + return -EINVAL; + } + + fd = prog->instances.fds[n]; + if (fd < 0) { + pr_warn("%dth instance of program '%s' is invalid\n", + n, prog->section_name); + return -ENOENT; + } + + return fd; +} + +enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog) +{ + return prog->type; +} + +void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) +{ + prog->type = type; +} + +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(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); +BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS); +BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT); +BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT); +BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT); +BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); +BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); +BPF_PROG_TYPE_FNS(tracing, BPF_PROG_TYPE_TRACING); + +enum bpf_attach_type +bpf_program__get_expected_attach_type(struct bpf_program *prog) +{ + return prog->expected_attach_type; +} + +void bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type) +{ + prog->expected_attach_type = type; +} + +#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, btf, atype) \ + { string, sizeof(string) - 1, ptype, eatype, is_attachable, btf, atype } + +/* Programs that can NOT be attached. */ +#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0) + +/* Programs that can be attached. */ +#define BPF_APROG_SEC(string, ptype, atype) \ + BPF_PROG_SEC_IMPL(string, ptype, 0, 1, 0, atype) + +/* Programs that must specify expected attach type at load time. */ +#define BPF_EAPROG_SEC(string, ptype, eatype) \ + BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, 0, eatype) + +/* Programs that use BTF to identify attach point */ +#define BPF_PROG_BTF(string, ptype, eatype) \ + BPF_PROG_SEC_IMPL(string, ptype, eatype, 0, 1, 0) + +/* Programs that can be attached but attach type can't be identified by section + * name. Kept for backward compatibility. + */ +#define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype) + +static const struct { + const char *sec; + size_t len; + enum bpf_prog_type prog_type; + enum bpf_attach_type expected_attach_type; + bool is_attachable; + bool is_attach_btf; + enum bpf_attach_type attach_type; +} section_names[] = { + BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), + BPF_PROG_SEC("kprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("uprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("kretprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("uretprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), + BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), + BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT), + BPF_PROG_SEC("tp/", BPF_PROG_TYPE_TRACEPOINT), + BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT), + BPF_PROG_SEC("raw_tp/", BPF_PROG_TYPE_RAW_TRACEPOINT), + BPF_PROG_BTF("tp_btf/", BPF_PROG_TYPE_TRACING, + BPF_TRACE_RAW_TP), + BPF_PROG_BTF("fentry/", BPF_PROG_TYPE_TRACING, + BPF_TRACE_FENTRY), + BPF_PROG_BTF("fexit/", BPF_PROG_TYPE_TRACING, + BPF_TRACE_FEXIT), + BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), + BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), + BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), + BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT), + BPF_PROG_SEC("lwt_xmit", BPF_PROG_TYPE_LWT_XMIT), + BPF_PROG_SEC("lwt_seg6local", BPF_PROG_TYPE_LWT_SEG6LOCAL), + BPF_APROG_SEC("cgroup_skb/ingress", BPF_PROG_TYPE_CGROUP_SKB, + BPF_CGROUP_INET_INGRESS), + BPF_APROG_SEC("cgroup_skb/egress", BPF_PROG_TYPE_CGROUP_SKB, + BPF_CGROUP_INET_EGRESS), + BPF_APROG_COMPAT("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB), + BPF_APROG_SEC("cgroup/sock", BPF_PROG_TYPE_CGROUP_SOCK, + BPF_CGROUP_INET_SOCK_CREATE), + BPF_EAPROG_SEC("cgroup/post_bind4", BPF_PROG_TYPE_CGROUP_SOCK, + BPF_CGROUP_INET4_POST_BIND), + BPF_EAPROG_SEC("cgroup/post_bind6", BPF_PROG_TYPE_CGROUP_SOCK, + BPF_CGROUP_INET6_POST_BIND), + BPF_APROG_SEC("cgroup/dev", BPF_PROG_TYPE_CGROUP_DEVICE, + BPF_CGROUP_DEVICE), + BPF_APROG_SEC("sockops", BPF_PROG_TYPE_SOCK_OPS, + BPF_CGROUP_SOCK_OPS), + BPF_APROG_SEC("sk_skb/stream_parser", BPF_PROG_TYPE_SK_SKB, + BPF_SK_SKB_STREAM_PARSER), + BPF_APROG_SEC("sk_skb/stream_verdict", BPF_PROG_TYPE_SK_SKB, + BPF_SK_SKB_STREAM_VERDICT), + BPF_APROG_COMPAT("sk_skb", BPF_PROG_TYPE_SK_SKB), + BPF_APROG_SEC("sk_msg", BPF_PROG_TYPE_SK_MSG, + BPF_SK_MSG_VERDICT), + BPF_APROG_SEC("lirc_mode2", BPF_PROG_TYPE_LIRC_MODE2, + BPF_LIRC_MODE2), + BPF_APROG_SEC("flow_dissector", BPF_PROG_TYPE_FLOW_DISSECTOR, + BPF_FLOW_DISSECTOR), + BPF_EAPROG_SEC("cgroup/bind4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_INET4_BIND), + BPF_EAPROG_SEC("cgroup/bind6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_INET6_BIND), + BPF_EAPROG_SEC("cgroup/connect4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_INET4_CONNECT), + BPF_EAPROG_SEC("cgroup/connect6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_INET6_CONNECT), + BPF_EAPROG_SEC("cgroup/sendmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_UDP4_SENDMSG), + BPF_EAPROG_SEC("cgroup/sendmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_UDP6_SENDMSG), + BPF_EAPROG_SEC("cgroup/recvmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_UDP4_RECVMSG), + BPF_EAPROG_SEC("cgroup/recvmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + 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 +#undef BPF_PROG_SEC +#undef BPF_APROG_SEC +#undef BPF_EAPROG_SEC +#undef BPF_APROG_COMPAT + +#define MAX_TYPE_NAME_SIZE 32 + +static char *libbpf_get_type_names(bool attach_type) +{ + int i, len = ARRAY_SIZE(section_names) * MAX_TYPE_NAME_SIZE; + char *buf; + + buf = malloc(len); + if (!buf) + return NULL; + + buf[0] = '\0'; + /* Forge string buf with all available names */ + for (i = 0; i < ARRAY_SIZE(section_names); i++) { + if (attach_type && !section_names[i].is_attachable) + continue; + + if (strlen(buf) + strlen(section_names[i].sec) + 2 > len) { + free(buf); + return NULL; + } + strcat(buf, " "); + strcat(buf, section_names[i].sec); + } + + return buf; +} + +int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, + enum bpf_attach_type *expected_attach_type) +{ + char *type_names; + int i; + + if (!name) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(section_names); i++) { + if (strncmp(name, section_names[i].sec, section_names[i].len)) + continue; + *prog_type = section_names[i].prog_type; + *expected_attach_type = section_names[i].expected_attach_type; + return 0; + } + pr_warn("failed to guess program type from ELF section '%s'\n", name); + type_names = libbpf_get_type_names(false); + if (type_names != NULL) { + pr_info("supported section(type) names are:%s\n", type_names); + free(type_names); + } + + return -ESRCH; +} + +#define BTF_PREFIX "btf_trace_" +int libbpf_find_vmlinux_btf_id(const char *name, + enum bpf_attach_type attach_type) +{ + struct btf *btf = bpf_core_find_kernel_btf(); + char raw_tp_btf[128] = BTF_PREFIX; + char *dst = raw_tp_btf + sizeof(BTF_PREFIX) - 1; + const char *btf_name; + int err = -EINVAL; + __u32 kind; + + if (IS_ERR(btf)) { + pr_warn("vmlinux BTF is not found\n"); + return -EINVAL; + } + + if (attach_type == BPF_TRACE_RAW_TP) { + /* prepend "btf_trace_" prefix per kernel convention */ + strncat(dst, name, sizeof(raw_tp_btf) - sizeof(BTF_PREFIX)); + btf_name = raw_tp_btf; + kind = BTF_KIND_TYPEDEF; + } else { + btf_name = name; + kind = BTF_KIND_FUNC; + } + err = btf__find_by_name_kind(btf, btf_name, kind); + btf__free(btf); + return err; +} + +static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) +{ + struct bpf_prog_info_linear *info_linear; + struct bpf_prog_info *info; + struct btf *btf = NULL; + int err = -EINVAL; + + info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0); + if (IS_ERR_OR_NULL(info_linear)) { + pr_warn("failed get_prog_info_linear for FD %d\n", + attach_prog_fd); + return -EINVAL; + } + info = &info_linear->info; + if (!info->btf_id) { + pr_warn("The target program doesn't have BTF\n"); + goto out; + } + if (btf__get_from_id(info->btf_id, &btf)) { + pr_warn("Failed to get BTF of the program\n"); + goto out; + } + err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); + btf__free(btf); + if (err <= 0) { + pr_warn("%s is not found in prog's BTF\n", name); + goto out; + } +out: + free(info_linear); + return err; +} + +static int libbpf_find_attach_btf_id(const char *name, + enum bpf_attach_type attach_type, + __u32 attach_prog_fd) +{ + int i, err; + + if (!name) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(section_names); i++) { + if (!section_names[i].is_attach_btf) + continue; + if (strncmp(name, section_names[i].sec, section_names[i].len)) + continue; + if (attach_prog_fd) + err = libbpf_find_prog_btf_id(name + section_names[i].len, + attach_prog_fd); + else + err = libbpf_find_vmlinux_btf_id(name + section_names[i].len, + attach_type); + if (err <= 0) + pr_warn("%s is not found in vmlinux BTF\n", name); + return err; + } + pr_warn("failed to identify btf_id based on ELF section name '%s'\n", name); + return -ESRCH; +} + +int libbpf_attach_type_by_name(const char *name, + enum bpf_attach_type *attach_type) +{ + char *type_names; + int i; + + if (!name) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(section_names); i++) { + if (strncmp(name, section_names[i].sec, section_names[i].len)) + continue; + if (!section_names[i].is_attachable) + return -EINVAL; + *attach_type = section_names[i].attach_type; + return 0; + } + pr_warn("failed to guess attach type based on ELF section name '%s'\n", name); + type_names = libbpf_get_type_names(true); + if (type_names != NULL) { + pr_info("attachable section(type) names are:%s\n", type_names); + free(type_names); + } + + return -EINVAL; +} + +int bpf_map__fd(const struct bpf_map *map) +{ + return map ? map->fd : -EINVAL; +} + +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(const struct bpf_map *map) +{ + return map ? map->name : NULL; +} + +__u32 bpf_map__btf_key_type_id(const struct bpf_map *map) +{ + return map ? map->btf_key_type_id : 0; +} + +__u32 bpf_map__btf_value_type_id(const struct bpf_map *map) +{ + return map ? map->btf_value_type_id : 0; +} + +int bpf_map__set_priv(struct bpf_map *map, void *priv, + bpf_map_clear_priv_t clear_priv) +{ + if (!map) + return -EINVAL; + + if (map->priv) { + if (map->clear_priv) + map->clear_priv(map, map->priv); + } + + map->priv = priv; + map->clear_priv = clear_priv; + return 0; +} + +void *bpf_map__priv(const struct bpf_map *map) +{ + return map ? map->priv : ERR_PTR(-EINVAL); +} + +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(const struct bpf_map *map) +{ + return map->libbpf_type != LIBBPF_MAP_UNSPEC; +} + +void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) +{ + map->map_ifindex = ifindex; +} + +int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) +{ + if (!bpf_map_type__is_map_in_map(map->def.type)) { + pr_warn("error: unsupported map type\n"); + return -EINVAL; + } + if (map->inner_map_fd != -1) { + pr_warn("error: inner_map_fd already specified\n"); + return -EINVAL; + } + map->inner_map_fd = fd; + return 0; +} + +static struct bpf_map * +__bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) +{ + ssize_t idx; + struct bpf_map *s, *e; + + if (!obj || !obj->maps) + return NULL; + + s = obj->maps; + e = obj->maps + obj->nr_maps; + + if ((m < s) || (m >= e)) { + pr_warn("error in %s: map handler doesn't belong to object\n", + __func__); + return NULL; + } + + idx = (m - obj->maps) + i; + if (idx >= obj->nr_maps || idx < 0) + return NULL; + return &obj->maps[idx]; +} + +struct bpf_map * +bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj) +{ + if (prev == NULL) + return obj->maps; + + return __bpf_map__iter(prev, obj, 1); +} + +struct bpf_map * +bpf_map__prev(const struct bpf_map *next, const struct bpf_object *obj) +{ + if (next == NULL) { + if (!obj->nr_maps) + return NULL; + return obj->maps + obj->nr_maps - 1; + } + + return __bpf_map__iter(next, obj, -1); +} + +struct bpf_map * +bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name) +{ + struct bpf_map *pos; + + bpf_object__for_each_map(pos, obj) { + if (pos->name && !strcmp(pos->name, name)) + return pos; + } + return NULL; +} + +int +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)); +} + +struct bpf_map * +bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset) +{ + return ERR_PTR(-ENOTSUP); +} + +long libbpf_get_error(const void *ptr) +{ + return PTR_ERR_OR_ZERO(ptr); +} + +int bpf_prog_load(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd) +{ + struct bpf_prog_load_attr attr; + + memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); + attr.file = file; + attr.prog_type = type; + attr.expected_attach_type = 0; + + return bpf_prog_load_xattr(&attr, pobj, prog_fd); +} + +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 = {}; + struct bpf_program *prog, *first_prog = NULL; + struct bpf_object *obj; + struct bpf_map *map; + int err; + + if (!attr) + return -EINVAL; + 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; + + bpf_object__for_each_program(prog, obj) { + enum bpf_attach_type attach_type = attr->expected_attach_type; + /* + * to preserve backwards compatibility, bpf_prog_load treats + * attr->prog_type, if specified, as an override to whatever + * bpf_object__open guessed + */ + if (attr->prog_type != BPF_PROG_TYPE_UNSPEC) { + bpf_program__set_type(prog, attr->prog_type); + bpf_program__set_expected_attach_type(prog, + attach_type); + } + if (bpf_program__get_type(prog) == BPF_PROG_TYPE_UNSPEC) { + /* + * we haven't guessed from section name and user + * didn't provide a fallback type, too bad... + */ + bpf_object__close(obj); + return -EINVAL; + } + + prog->prog_ifindex = attr->ifindex; + prog->log_level = attr->log_level; + prog->prog_flags = attr->prog_flags; + if (!first_prog) + first_prog = prog; + } + + bpf_object__for_each_map(map, obj) { + if (!bpf_map__is_offload_neutral(map)) + map->map_ifindex = attr->ifindex; + } + + if (!first_prog) { + pr_warn("object file doesn't contain bpf program\n"); + bpf_object__close(obj); + return -ENOENT; + } + + err = bpf_object__load(obj); + if (err) { + bpf_object__close(obj); + return -EINVAL; + } + + *pobj = obj; + *prog_fd = bpf_program__fd(first_prog); + 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_warn("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_warn("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_warn("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_warn("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_warn("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_warn("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 = ptr_to_u64(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_warn("%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_warn("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_warn("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_warn("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_warn("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_warn("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_warn("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_warn("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_warn("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_warn("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_warn("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; +} + +struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link_fd *link; + int prog_fd, pfd; + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("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(NULL, prog_fd); + if (pfd < 0) { + pfd = -errno; + free(link); + pr_warn("program '%s': failed to attach to trace: %s\n", + bpf_program__title(prog, false), + 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, + bpf_perf_event_print_t fn, void *private_data) +{ + struct perf_event_mmap_page *header = mmap_mem; + __u64 data_head = ring_buffer_read_head(header); + __u64 data_tail = header->data_tail; + void *base = ((__u8 *)header) + page_size; + int ret = LIBBPF_PERF_EVENT_CONT; + struct perf_event_header *ehdr; + size_t ehdr_size; + + while (data_head != data_tail) { + ehdr = base + (data_tail & (mmap_size - 1)); + ehdr_size = ehdr->size; + + if (((void *)ehdr) + ehdr_size > base + mmap_size) { + void *copy_start = ehdr; + size_t len_first = base + mmap_size - copy_start; + size_t len_secnd = ehdr_size - len_first; + + if (*copy_size < ehdr_size) { + free(*copy_mem); + *copy_mem = malloc(ehdr_size); + if (!*copy_mem) { + *copy_size = 0; + ret = LIBBPF_PERF_EVENT_ERROR; + break; + } + *copy_size = ehdr_size; + } + + memcpy(*copy_mem, copy_start, len_first); + memcpy(*copy_mem + len_first, base, len_secnd); + ehdr = *copy_mem; + } + + ret = fn(ehdr, private_data); + data_tail += ehdr_size; + if (ret != LIBBPF_PERF_EVENT_CONT) + break; + } + + ring_buffer_write_tail(header, data_tail); + 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_warn("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_warn("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_warn("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_warn("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 = { 0, }; + + attr.config = PERF_COUNT_SW_BPF_OUTPUT, + attr.type = PERF_TYPE_SOFTWARE; + attr.sample_type = PERF_SAMPLE_RAW; + attr.sample_period = 1; + attr.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_warn("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_warn("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_warn("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_warn("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_warn("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_warn("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_warn("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_warn("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_warn("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_warn("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 */ + int size_offset; /* > 0: offset of rec size, + * < 0: fix size of -size_offset + */ +}; + +static struct bpf_prog_info_array_desc bpf_prog_info_array_desc[] = { + [BPF_PROG_INFO_JITED_INSNS] = { + offsetof(struct bpf_prog_info, jited_prog_insns), + offsetof(struct bpf_prog_info, jited_prog_len), + -1, + }, + [BPF_PROG_INFO_XLATED_INSNS] = { + offsetof(struct bpf_prog_info, xlated_prog_insns), + offsetof(struct bpf_prog_info, xlated_prog_len), + -1, + }, + [BPF_PROG_INFO_MAP_IDS] = { + offsetof(struct bpf_prog_info, map_ids), + offsetof(struct bpf_prog_info, nr_map_ids), + -(int)sizeof(__u32), + }, + [BPF_PROG_INFO_JITED_KSYMS] = { + offsetof(struct bpf_prog_info, jited_ksyms), + offsetof(struct bpf_prog_info, nr_jited_ksyms), + -(int)sizeof(__u64), + }, + [BPF_PROG_INFO_JITED_FUNC_LENS] = { + offsetof(struct bpf_prog_info, jited_func_lens), + offsetof(struct bpf_prog_info, nr_jited_func_lens), + -(int)sizeof(__u32), + }, + [BPF_PROG_INFO_FUNC_INFO] = { + offsetof(struct bpf_prog_info, func_info), + offsetof(struct bpf_prog_info, nr_func_info), + offsetof(struct bpf_prog_info, func_info_rec_size), + }, + [BPF_PROG_INFO_LINE_INFO] = { + offsetof(struct bpf_prog_info, line_info), + offsetof(struct bpf_prog_info, nr_line_info), + offsetof(struct bpf_prog_info, line_info_rec_size), + }, + [BPF_PROG_INFO_JITED_LINE_INFO] = { + offsetof(struct bpf_prog_info, jited_line_info), + offsetof(struct bpf_prog_info, nr_jited_line_info), + offsetof(struct bpf_prog_info, jited_line_info_rec_size), + }, + [BPF_PROG_INFO_PROG_TAGS] = { + offsetof(struct bpf_prog_info, prog_tags), + offsetof(struct bpf_prog_info, nr_prog_tags), + -(int)sizeof(__u8) * BPF_TAG_SIZE, + }, + +}; + +static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, + int offset) +{ + __u32 *array = (__u32 *)info; + + if (offset >= 0) + return array[offset / sizeof(__u32)]; + return -(int)offset; +} + +static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info, + int offset) +{ + __u64 *array = (__u64 *)info; + + if (offset >= 0) + return array[offset / sizeof(__u64)]; + return -(int)offset; +} + +static void bpf_prog_info_set_offset_u32(struct bpf_prog_info *info, int offset, + __u32 val) +{ + __u32 *array = (__u32 *)info; + + if (offset >= 0) + array[offset / sizeof(__u32)] = val; +} + +static void bpf_prog_info_set_offset_u64(struct bpf_prog_info *info, int offset, + __u64 val) +{ + __u64 *array = (__u64 *)info; + + if (offset >= 0) + array[offset / sizeof(__u64)] = val; +} + +struct bpf_prog_info_linear * +bpf_program__get_prog_info_linear(int fd, __u64 arrays) +{ + struct bpf_prog_info_linear *info_linear; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + __u32 data_len = 0; + int i, err; + void *ptr; + + if (arrays >> BPF_PROG_INFO_LAST_ARRAY) + return ERR_PTR(-EINVAL); + + /* step 1: get array dimensions */ + err = bpf_obj_get_info_by_fd(fd, &info, &info_len); + if (err) { + pr_debug("can't get prog info: %s", strerror(errno)); + return ERR_PTR(-EFAULT); + } + + /* step 2: calculate total size of all arrays */ + for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) { + bool include_array = (arrays & (1UL << i)) > 0; + struct bpf_prog_info_array_desc *desc; + __u32 count, size; + + desc = bpf_prog_info_array_desc + i; + + /* kernel is too old to support this field */ + if (info_len < desc->array_offset + sizeof(__u32) || + info_len < desc->count_offset + sizeof(__u32) || + (desc->size_offset > 0 && info_len < desc->size_offset)) + include_array = false; + + if (!include_array) { + arrays &= ~(1UL << i); /* clear the bit */ + continue; + } + + count = bpf_prog_info_read_offset_u32(&info, desc->count_offset); + size = bpf_prog_info_read_offset_u32(&info, desc->size_offset); + + data_len += count * size; + } + + /* step 3: allocate continuous memory */ + data_len = roundup(data_len, sizeof(__u64)); + info_linear = malloc(sizeof(struct bpf_prog_info_linear) + data_len); + if (!info_linear) + return ERR_PTR(-ENOMEM); + + /* step 4: fill data to info_linear->info */ + info_linear->arrays = arrays; + memset(&info_linear->info, 0, sizeof(info)); + ptr = info_linear->data; + + for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) { + struct bpf_prog_info_array_desc *desc; + __u32 count, size; + + if ((arrays & (1UL << i)) == 0) + continue; + + desc = bpf_prog_info_array_desc + i; + count = bpf_prog_info_read_offset_u32(&info, desc->count_offset); + size = bpf_prog_info_read_offset_u32(&info, desc->size_offset); + bpf_prog_info_set_offset_u32(&info_linear->info, + desc->count_offset, count); + bpf_prog_info_set_offset_u32(&info_linear->info, + desc->size_offset, size); + bpf_prog_info_set_offset_u64(&info_linear->info, + desc->array_offset, + ptr_to_u64(ptr)); + ptr += count * size; + } + + /* step 5: call syscall again to get required arrays */ + err = bpf_obj_get_info_by_fd(fd, &info_linear->info, &info_len); + if (err) { + pr_debug("can't get prog info: %s", strerror(errno)); + free(info_linear); + return ERR_PTR(-EFAULT); + } + + /* step 6: verify the data */ + for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) { + struct bpf_prog_info_array_desc *desc; + __u32 v1, v2; + + if ((arrays & (1UL << i)) == 0) + continue; + + desc = bpf_prog_info_array_desc + i; + v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset); + v2 = bpf_prog_info_read_offset_u32(&info_linear->info, + desc->count_offset); + if (v1 != v2) + pr_warn("%s: mismatch in element count\n", __func__); + + v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset); + v2 = bpf_prog_info_read_offset_u32(&info_linear->info, + desc->size_offset); + if (v1 != v2) + pr_warn("%s: mismatch in rec size\n", __func__); + } + + /* step 7: update info_len and data_len */ + info_linear->info_len = sizeof(struct bpf_prog_info); + info_linear->data_len = data_len; + + return info_linear; +} + +void bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear) +{ + int i; + + for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) { + struct bpf_prog_info_array_desc *desc; + __u64 addr, offs; + + if ((info_linear->arrays & (1UL << i)) == 0) + continue; + + desc = bpf_prog_info_array_desc + i; + addr = bpf_prog_info_read_offset_u64(&info_linear->info, + desc->array_offset); + offs = addr - ptr_to_u64(info_linear->data); + bpf_prog_info_set_offset_u64(&info_linear->info, + desc->array_offset, offs); + } +} + +void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear) +{ + int i; + + for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) { + struct bpf_prog_info_array_desc *desc; + __u64 addr, offs; + + if ((info_linear->arrays & (1UL << i)) == 0) + continue; + + desc = bpf_prog_info_array_desc + i; + offs = bpf_prog_info_read_offset_u64(&info_linear->info, + desc->array_offset); + addr = offs + ptr_to_u64(info_linear->data); + bpf_prog_info_set_offset_u64(&info_linear->info, + 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; + int tmp_cpus = 0; + static int cpus; + char buf[128]; + int error = 0; + int fd = -1; + + tmp_cpus = READ_ONCE(cpus); + if (tmp_cpus > 0) + return tmp_cpus; + + fd = open(fcpu, O_RDONLY); + if (fd < 0) { + error = errno; + pr_warn("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_warn("Failed to read # of possible cpus from %s: %s\n", + fcpu, strerror(error)); + return -error; + } + if (len == sizeof(buf)) { + pr_warn("File %s size overflow\n", fcpu); + return -EOVERFLOW; + } + buf[len] = '\0'; + + for (ir = 0, tmp_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_warn("Failed to get # CPUs from %s\n", + &buf[il]); + return -EINVAL; + } else if (n == 1) { + end = start; + } + tmp_cpus += end - start + 1; + il = ir + 1; + } + } + if (tmp_cpus <= 0) { + pr_warn("Invalid #CPUs %d from %s\n", tmp_cpus, fcpu); + return -EINVAL; + } + + WRITE_ONCE(cpus, tmp_cpus); + return tmp_cpus; +} diff --git a/src/contrib/libbpf/bpf/libbpf.h b/src/contrib/libbpf/bpf/libbpf.h new file mode 100644 index 0000000..0dbf4bf --- /dev/null +++ b/src/contrib/libbpf/bpf/libbpf.h @@ -0,0 +1,637 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Common eBPF ELF object loading operations. + * + * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> + * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015 Huawei Inc. + */ +#ifndef __LIBBPF_LIBBPF_H +#define __LIBBPF_LIBBPF_H + +#include <stdarg.h> +#include <stdio.h> +#include <stdint.h> +#include <stdbool.h> +#include <sys/types.h> // for size_t +#include <linux/bpf.h> + +#ifdef __cplusplus +extern "C" { +#endif + +#ifndef LIBBPF_API +#define LIBBPF_API __attribute__((visibility("default"))) +#endif + +enum libbpf_errno { + __LIBBPF_ERRNO__START = 4000, + + /* Something wrong in libelf */ + LIBBPF_ERRNO__LIBELF = __LIBBPF_ERRNO__START, + LIBBPF_ERRNO__FORMAT, /* BPF object format invalid */ + LIBBPF_ERRNO__KVERSION, /* Incorrect or no 'version' section */ + LIBBPF_ERRNO__ENDIAN, /* Endian mismatch */ + LIBBPF_ERRNO__INTERNAL, /* Internal error in libbpf */ + LIBBPF_ERRNO__RELOC, /* Relocation failed */ + LIBBPF_ERRNO__LOAD, /* Load program failure for unknown reason */ + LIBBPF_ERRNO__VERIFY, /* Kernel verifier blocks program loading */ + LIBBPF_ERRNO__PROG2BIG, /* Program too big */ + LIBBPF_ERRNO__KVER, /* Incorrect kernel version */ + LIBBPF_ERRNO__PROGTYPE, /* Kernel doesn't support this program type */ + LIBBPF_ERRNO__WRNGPID, /* Wrong pid in netlink message */ + LIBBPF_ERRNO__INVSEQ, /* Invalid netlink sequence */ + LIBBPF_ERRNO__NLPARSE, /* netlink parsing error */ + __LIBBPF_ERRNO__END, +}; + +LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size); + +enum libbpf_print_level { + LIBBPF_WARN, + LIBBPF_INFO, + LIBBPF_DEBUG, +}; + +typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level, + const char *, va_list ap); + +LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn); + +/* Hide internal to user */ +struct bpf_object; + +struct bpf_object_open_attr { + const char *file; + enum bpf_prog_type prog_type; +}; + +/* Helper macro to declare and initialize libbpf options struct + * + * This dance with uninitialized declaration, followed by memset to zero, + * followed by assignment using compound literal syntax is done to preserve + * ability to use a nice struct field initialization syntax and **hopefully** + * have all the padding bytes initialized to zero. It's not guaranteed though, + * when copying literal, that compiler won't copy garbage in literal's padding + * bytes, but that's the best way I've found and it seems to work in practice. + * + * Macro declares opts struct of given type and name, zero-initializes, + * including any extra padding, it with memset() and then assigns initial + * values provided by users in struct initializer-syntax as varargs. + */ +#define DECLARE_LIBBPF_OPTS(TYPE, NAME, ...) \ + struct TYPE NAME = ({ \ + memset(&NAME, 0, sizeof(struct TYPE)); \ + (struct TYPE) { \ + .sz = sizeof(struct TYPE), \ + __VA_ARGS__ \ + }; \ + }) + +struct bpf_object_open_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* object name override, if provided: + * - for object open from file, this will override setting object + * name from file path's base name; + * - for object open from memory buffer, this will specify an object + * name and will override default "<addr>-<buf-size>" name; + */ + const char *object_name; + /* parse map definitions non-strictly, allowing extra attributes/data */ + bool relaxed_maps; + /* process CO-RE relocations non-strictly, allowing them to fail */ + bool relaxed_core_relocs; + /* maps that set the 'pinning' attribute in their definition will have + * their pin_path attribute set to a file in this directory, and be + * auto-pinned to that path on load; defaults to "/sys/fs/bpf". + */ + const char *pin_root_path; + __u32 attach_prog_fd; +}; +#define bpf_object_open_opts__last_field attach_prog_fd + +LIBBPF_API struct bpf_object *bpf_object__open(const char *path); +LIBBPF_API struct bpf_object * +bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts); +LIBBPF_API struct bpf_object * +bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, + struct bpf_object_open_opts *opts); + +/* deprecated bpf_object__open variants */ +LIBBPF_API struct bpf_object * +bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, + const char *name); +LIBBPF_API struct bpf_object * +bpf_object__open_xattr(struct bpf_object_open_attr *attr); + +int bpf_object__section_size(const struct bpf_object *obj, const char *name, + __u32 *size); +int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, + __u32 *off); + +enum libbpf_pin_type { + LIBBPF_PIN_NONE, + /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ + LIBBPF_PIN_BY_NAME, +}; + +/* pin_maps and unpin_maps can both be called with a NULL path, in which case + * they will use the pin_path attribute of each map (and ignore all maps that + * don't have a pin_path set). + */ +LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path); +LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj, + const char *path); +LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj, + const char *path); +LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj, + const char *path); +LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path); +LIBBPF_API void bpf_object__close(struct bpf_object *object); + +struct bpf_object_load_attr { + struct bpf_object *obj; + int log_level; + const char *target_btf_path; +}; + +/* Load/unload object into/from kernel */ +LIBBPF_API int bpf_object__load(struct bpf_object *obj); +LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr); +LIBBPF_API int bpf_object__unload(struct bpf_object *obj); +LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); +LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); + +struct btf; +LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj); +LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); + +LIBBPF_API struct bpf_program * +bpf_object__find_program_by_title(const struct bpf_object *obj, + const char *title); + +LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev); +#define bpf_object__for_each_safe(pos, tmp) \ + for ((pos) = bpf_object__next(NULL), \ + (tmp) = bpf_object__next(pos); \ + (pos) != NULL; \ + (pos) = (tmp), (tmp) = bpf_object__next(tmp)) + +typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *); +LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv, + bpf_object_clear_priv_t clear_priv); +LIBBPF_API void *bpf_object__priv(const struct bpf_object *prog); + +LIBBPF_API int +libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, + enum bpf_attach_type *expected_attach_type); +LIBBPF_API int libbpf_attach_type_by_name(const char *name, + enum bpf_attach_type *attach_type); +LIBBPF_API int libbpf_find_vmlinux_btf_id(const char *name, + enum bpf_attach_type attach_type); + +/* Accessors of bpf_program */ +struct bpf_program; +LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog, + const struct bpf_object *obj); + +#define bpf_object__for_each_program(pos, obj) \ + for ((pos) = bpf_program__next(NULL, (obj)); \ + (pos) != NULL; \ + (pos) = bpf_program__next((pos), (obj))) + +LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog, + const struct bpf_object *obj); + +typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *); + +LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv, + bpf_program_clear_priv_t clear_priv); + +LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog); +LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, + __u32 ifindex); + +LIBBPF_API const char *bpf_program__title(const struct bpf_program *prog, + bool needs_copy); + +/* returns program size in bytes */ +LIBBPF_API size_t bpf_program__size(const struct bpf_program *prog); + +LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license, + __u32 kern_version); +LIBBPF_API int bpf_program__fd(const struct bpf_program *prog); +LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog, + const char *path, + int instance); +LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog, + const char *path, + int instance); +LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path); +LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path); +LIBBPF_API void bpf_program__unload(struct bpf_program *prog); + +struct bpf_link; + +LIBBPF_API int bpf_link__destroy(struct bpf_link *link); + +LIBBPF_API struct bpf_link * +bpf_program__attach_perf_event(struct bpf_program *prog, int pfd); +LIBBPF_API struct bpf_link * +bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe, + const char *func_name); +LIBBPF_API struct bpf_link * +bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe, + pid_t pid, const char *binary_path, + size_t func_offset); +LIBBPF_API struct bpf_link * +bpf_program__attach_tracepoint(struct bpf_program *prog, + const char *tp_category, + const char *tp_name); +LIBBPF_API struct bpf_link * +bpf_program__attach_raw_tracepoint(struct bpf_program *prog, + const char *tp_name); + +LIBBPF_API struct bpf_link * +bpf_program__attach_trace(struct bpf_program *prog); +struct bpf_insn; + +/* + * Libbpf allows callers to adjust BPF programs before being loaded + * into kernel. One program in an object file can be transformed into + * multiple variants to be attached to different hooks. + * + * bpf_program_prep_t, bpf_program__set_prep and bpf_program__nth_fd + * form an API for this purpose. + * + * - bpf_program_prep_t: + * Defines a 'preprocessor', which is a caller defined function + * passed to libbpf through bpf_program__set_prep(), and will be + * called before program is loaded. The processor should adjust + * the program one time for each instance according to the instance id + * passed to it. + * + * - bpf_program__set_prep: + * Attaches a preprocessor to a BPF program. The number of instances + * that should be created is also passed through this function. + * + * - bpf_program__nth_fd: + * After the program is loaded, get resulting FD of a given instance + * of the BPF program. + * + * If bpf_program__set_prep() is not used, the program would be loaded + * without adjustment during bpf_object__load(). The program has only + * one instance. In this case bpf_program__fd(prog) is equal to + * bpf_program__nth_fd(prog, 0). + */ + +struct bpf_prog_prep_result { + /* + * If not NULL, load new instruction array. + * If set to NULL, don't load this instance. + */ + struct bpf_insn *new_insn_ptr; + int new_insn_cnt; + + /* If not NULL, result FD is written to it. */ + int *pfd; +}; + +/* + * Parameters of bpf_program_prep_t: + * - prog: The bpf_program being loaded. + * - n: Index of instance being generated. + * - insns: BPF instructions array. + * - insns_cnt:Number of instructions in insns. + * - res: Output parameter, result of transformation. + * + * Return value: + * - Zero: pre-processing success. + * - Non-zero: pre-processing error, stop loading. + */ +typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n, + struct bpf_insn *insns, int insns_cnt, + struct bpf_prog_prep_result *res); + +LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, + bpf_program_prep_t prep); + +LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n); + +/* + * Adjust type of BPF program. Default is kprobe. + */ +LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog); + +LIBBPF_API enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog); +LIBBPF_API void bpf_program__set_type(struct bpf_program *prog, + enum bpf_prog_type type); + +LIBBPF_API enum bpf_attach_type +bpf_program__get_expected_attach_type(struct bpf_program *prog); +LIBBPF_API void +bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type); + +LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog); + +/* + * No need for __attribute__((packed)), all members of 'bpf_map_def' + * are all aligned. In addition, using __attribute__((packed)) + * would trigger a -Wpacked warning message, and lead to an error + * if -Werror is set. + */ +struct bpf_map_def { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; + unsigned int map_flags; +}; + +/* + * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel, + * so no need to worry about a name clash. + */ +struct bpf_map; +LIBBPF_API struct bpf_map * +bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); + +LIBBPF_API int +bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name); + +/* + * Get bpf_map through the offset of corresponding struct bpf_map_def + * in the BPF object file. + */ +LIBBPF_API struct bpf_map * +bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset); + +LIBBPF_API struct bpf_map * +bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj); +#define bpf_object__for_each_map(pos, obj) \ + for ((pos) = bpf_map__next(NULL, (obj)); \ + (pos) != NULL; \ + (pos) = bpf_map__next((pos), (obj))) +#define bpf_map__for_each bpf_object__for_each_map + +LIBBPF_API struct bpf_map * +bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj); + +LIBBPF_API int bpf_map__fd(const struct bpf_map *map); +LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); +LIBBPF_API const char *bpf_map__name(const struct bpf_map *map); +LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map); +LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map); + +typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); +LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, + bpf_map_clear_priv_t clear_priv); +LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); +LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); +LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); +LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); +LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); +LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); +LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); +LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); +LIBBPF_API bool bpf_map__is_pinned(const struct bpf_map *map); +LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); +LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path); + +LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd); + +LIBBPF_API long libbpf_get_error(const void *ptr); + +struct bpf_prog_load_attr { + const char *file; + enum bpf_prog_type prog_type; + enum bpf_attach_type expected_attach_type; + int ifindex; + int log_level; + int prog_flags; +}; + +LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, + struct bpf_object **pobj, int *prog_fd); +LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd); + +struct xdp_link_info { + __u32 prog_id; + __u32 drv_prog_id; + __u32 hw_prog_id; + __u32 skb_prog_id; + __u8 attach_mode; +}; + +LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); +LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); +LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, + size_t info_size, __u32 flags); + +struct perf_buffer; + +typedef void (*perf_buffer_sample_fn)(void *ctx, int cpu, + void *data, __u32 size); +typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt); + +/* common use perf buffer options */ +struct perf_buffer_opts { + /* if specified, sample_cb is called for each sample */ + perf_buffer_sample_fn sample_cb; + /* if specified, lost_cb is called for each batch of lost samples */ + perf_buffer_lost_fn lost_cb; + /* ctx is provided to sample_cb and lost_cb */ + void *ctx; +}; + +LIBBPF_API struct perf_buffer * +perf_buffer__new(int map_fd, size_t page_cnt, + const struct perf_buffer_opts *opts); + +enum bpf_perf_event_ret { + LIBBPF_PERF_EVENT_DONE = 0, + LIBBPF_PERF_EVENT_ERROR = -1, + LIBBPF_PERF_EVENT_CONT = -2, +}; + +struct perf_event_header; + +typedef enum bpf_perf_event_ret +(*perf_buffer_event_fn)(void *ctx, int cpu, struct perf_event_header *event); + +/* raw perf buffer options, giving most power and control */ +struct perf_buffer_raw_opts { + /* perf event attrs passed directly into perf_event_open() */ + struct perf_event_attr *attr; + /* raw event callback */ + perf_buffer_event_fn event_cb; + /* ctx is provided to event_cb */ + void *ctx; + /* if cpu_cnt == 0, open all on all possible CPUs (up to the number of + * max_entries of given PERF_EVENT_ARRAY map) + */ + int cpu_cnt; + /* if cpu_cnt > 0, cpus is an array of CPUs to open ring buffers on */ + int *cpus; + /* if cpu_cnt > 0, map_keys specify map keys to set per-CPU FDs for */ + int *map_keys; +}; + +LIBBPF_API struct perf_buffer * +perf_buffer__new_raw(int map_fd, size_t page_cnt, + const struct perf_buffer_raw_opts *opts); + +LIBBPF_API void perf_buffer__free(struct perf_buffer *pb); +LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms); + +typedef enum bpf_perf_event_ret + (*bpf_perf_event_print_t)(struct perf_event_header *hdr, + void *private_data); +LIBBPF_API 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, + bpf_perf_event_print_t fn, void *private_data); + +struct nlattr; +typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); +int libbpf_netlink_open(unsigned int *nl_pid); +int libbpf_nl_get_link(int sock, unsigned int nl_pid, + libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); +int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie); +int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie); +int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie); + +struct bpf_prog_linfo; +struct bpf_prog_info; + +LIBBPF_API void bpf_prog_linfo__free(struct bpf_prog_linfo *prog_linfo); +LIBBPF_API struct bpf_prog_linfo * +bpf_prog_linfo__new(const struct bpf_prog_info *info); +LIBBPF_API const struct bpf_line_info * +bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo, + __u64 addr, __u32 func_idx, __u32 nr_skip); +LIBBPF_API const struct bpf_line_info * +bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo, + __u32 insn_off, __u32 nr_skip); + +/* + * Probe for supported system features + * + * Note that running many of these probes in a short amount of time can cause + * the kernel to reach the maximal size of lockable memory allowed for the + * user, causing subsequent probes to fail. In this case, the caller may want + * to adjust that limit with setrlimit(). + */ +LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type, + __u32 ifindex); +LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex); +LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id, + enum bpf_prog_type prog_type, __u32 ifindex); + +/* + * Get bpf_prog_info in continuous memory + * + * struct bpf_prog_info has multiple arrays. The user has option to choose + * arrays to fetch from kernel. The following APIs provide an uniform way to + * fetch these data. All arrays in bpf_prog_info are stored in a single + * continuous memory region. This makes it easy to store the info in a + * file. + * + * Before writing bpf_prog_info_linear to files, it is necessary to + * translate pointers in bpf_prog_info to offsets. Helper functions + * bpf_program__bpil_addr_to_offs() and bpf_program__bpil_offs_to_addr() + * are introduced to switch between pointers and offsets. + * + * Examples: + * # To fetch map_ids and prog_tags: + * __u64 arrays = (1UL << BPF_PROG_INFO_MAP_IDS) | + * (1UL << BPF_PROG_INFO_PROG_TAGS); + * struct bpf_prog_info_linear *info_linear = + * bpf_program__get_prog_info_linear(fd, arrays); + * + * # To save data in file + * bpf_program__bpil_addr_to_offs(info_linear); + * write(f, info_linear, sizeof(*info_linear) + info_linear->data_len); + * + * # To read data from file + * read(f, info_linear, <proper_size>); + * bpf_program__bpil_offs_to_addr(info_linear); + */ +enum bpf_prog_info_array { + BPF_PROG_INFO_FIRST_ARRAY = 0, + BPF_PROG_INFO_JITED_INSNS = 0, + BPF_PROG_INFO_XLATED_INSNS, + BPF_PROG_INFO_MAP_IDS, + BPF_PROG_INFO_JITED_KSYMS, + BPF_PROG_INFO_JITED_FUNC_LENS, + BPF_PROG_INFO_FUNC_INFO, + BPF_PROG_INFO_LINE_INFO, + BPF_PROG_INFO_JITED_LINE_INFO, + BPF_PROG_INFO_PROG_TAGS, + BPF_PROG_INFO_LAST_ARRAY, +}; + +struct bpf_prog_info_linear { + /* size of struct bpf_prog_info, when the tool is compiled */ + __u32 info_len; + /* total bytes allocated for data, round up to 8 bytes */ + __u32 data_len; + /* which arrays are included in data */ + __u64 arrays; + struct bpf_prog_info info; + __u8 data[]; +}; + +LIBBPF_API struct bpf_prog_info_linear * +bpf_program__get_prog_info_linear(int fd, __u64 arrays); + +LIBBPF_API void +bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear); + +LIBBPF_API void +bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); + +/* + * A helper function to get the number of possible CPUs before looking up + * per-CPU maps. Negative errno is returned on failure. + * + * Example usage: + * + * int ncpus = libbpf_num_possible_cpus(); + * if (ncpus < 0) { + * // error handling + * } + * long values[ncpus]; + * bpf_map_lookup_elem(per_cpu_map_fd, key, values); + * + */ +LIBBPF_API int libbpf_num_possible_cpus(void); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* __LIBBPF_LIBBPF_H */ diff --git a/src/contrib/libbpf/bpf/libbpf_errno.c b/src/contrib/libbpf/bpf/libbpf_errno.c new file mode 100644 index 0000000..4343e40 --- /dev/null +++ b/src/contrib/libbpf/bpf/libbpf_errno.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> + * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015 Huawei Inc. + * Copyright (C) 2017 Nicira, Inc. + */ + +#undef _GNU_SOURCE +#include <stdio.h> +#include <string.h> + +#include "libbpf.h" + +#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START) +#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c) +#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START) + +static const char *libbpf_strerror_table[NR_ERRNO] = { + [ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf", + [ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid", + [ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost", + [ERRCODE_OFFSET(ENDIAN)] = "Endian mismatch", + [ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf", + [ERRCODE_OFFSET(RELOC)] = "Relocation failed", + [ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading", + [ERRCODE_OFFSET(PROG2BIG)] = "Program too big", + [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version", + [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type", + [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message", + [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence", + [ERRCODE_OFFSET(NLPARSE)] = "Incorrect netlink message parsing", +}; + +int libbpf_strerror(int err, char *buf, size_t size) +{ + if (!buf || !size) + return -1; + + err = err > 0 ? err : -err; + + if (err < __LIBBPF_ERRNO__START) { + int ret; + + ret = strerror_r(err, buf, size); + buf[size - 1] = '\0'; + return ret; + } + + if (err < __LIBBPF_ERRNO__END) { + const char *msg; + + msg = libbpf_strerror_table[ERRNO_OFFSET(err)]; + snprintf(buf, size, "%s", msg); + buf[size - 1] = '\0'; + return 0; + } + + snprintf(buf, size, "Unknown libbpf error %d", err); + buf[size - 1] = '\0'; + return -1; +} diff --git a/src/contrib/libbpf/bpf/libbpf_internal.h b/src/contrib/libbpf/bpf/libbpf_internal.h new file mode 100644 index 0000000..97ac17a --- /dev/null +++ b/src/contrib/libbpf/bpf/libbpf_internal.h @@ -0,0 +1,217 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Internal libbpf helpers. + * + * Copyright (c) 2019 Facebook + */ + +#ifndef __LIBBPF_LIBBPF_INTERNAL_H +#define __LIBBPF_LIBBPF_INTERNAL_H + +#include "libbpf.h" + +#define BTF_INFO_ENC(kind, kind_flag, vlen) \ + ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) +#define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type) +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) +#define BTF_MEMBER_ENC(name, type, bits_offset) (name), (type), (bits_offset) +#define BTF_PARAM_ENC(name, type) (name), (type) +#define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size) + +#ifndef min +# define min(x, y) ((x) < (y) ? (x) : (y)) +#endif +#ifndef max +# define max(x, y) ((x) < (y) ? (y) : (x)) +#endif +#ifndef offsetofend +# define offsetofend(TYPE, FIELD) \ + (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) +#endif + +/* Symbol versioning is different between static and shared library. + * Properly versioned symbols are needed for shared library, but + * only the symbol of the new version is needed for static library. + */ +#ifdef SHARED +# define COMPAT_VERSION(internal_name, api_name, version) \ + asm(".symver " #internal_name "," #api_name "@" #version); +# define DEFAULT_VERSION(internal_name, api_name, version) \ + asm(".symver " #internal_name "," #api_name "@@" #version); +#else +# define COMPAT_VERSION(internal_name, api_name, version) +# define DEFAULT_VERSION(internal_name, api_name, version) \ + extern typeof(internal_name) api_name \ + __attribute__((alias(#internal_name))); +#endif + +extern void libbpf_print(enum libbpf_print_level level, + const char *format, ...) + __attribute__((format(printf, 2, 3))); + +#define __pr(level, fmt, ...) \ +do { \ + libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__); \ +} while (0) + +#define pr_warn(fmt, ...) __pr(LIBBPF_WARN, fmt, ##__VA_ARGS__) +#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__) +#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__) + +static inline bool libbpf_validate_opts(const char *opts, + size_t opts_sz, size_t user_sz, + const char *type_name) +{ + if (user_sz < sizeof(size_t)) { + pr_warn("%s size (%zu) is too small\n", type_name, user_sz); + return false; + } + if (user_sz > opts_sz) { + size_t i; + + for (i = opts_sz; i < user_sz; i++) { + if (opts[i]) { + pr_warn("%s has non-zero extra bytes", + type_name); + return false; + } + } + } + return true; +} + +#define OPTS_VALID(opts, type) \ + (!(opts) || libbpf_validate_opts((const char *)opts, \ + offsetofend(struct type, \ + type##__last_field), \ + (opts)->sz, #type)) +#define OPTS_HAS(opts, field) \ + ((opts) && opts->sz >= offsetofend(typeof(*(opts)), field)) +#define OPTS_GET(opts, field, fallback_value) \ + (OPTS_HAS(opts, field) ? (opts)->field : fallback_value) + +int libbpf__load_raw_btf(const char *raw_types, size_t types_len, + const char *str_sec, size_t str_len); + +struct btf_ext_info { + /* + * info points to the individual info section (e.g. func_info and + * line_info) from the .BTF.ext. It does not include the __u32 rec_size. + */ + void *info; + __u32 rec_size; + __u32 len; +}; + +#define for_each_btf_ext_sec(seg, sec) \ + for (sec = (seg)->info; \ + (void *)sec < (seg)->info + (seg)->len; \ + sec = (void *)sec + sizeof(struct btf_ext_info_sec) + \ + (seg)->rec_size * sec->num_info) + +#define for_each_btf_ext_rec(seg, sec, i, rec) \ + for (i = 0, rec = (void *)&(sec)->data; \ + i < (sec)->num_info; \ + i++, rec = (void *)rec + (seg)->rec_size) + +struct btf_ext { + union { + struct btf_ext_header *hdr; + void *data; + }; + struct btf_ext_info func_info; + struct btf_ext_info line_info; + struct btf_ext_info field_reloc_info; + __u32 data_size; +}; + +struct btf_ext_info_sec { + __u32 sec_name_off; + __u32 num_info; + /* Followed by num_info * record_size number of bytes */ + __u8 data[0]; +}; + +/* The minimum bpf_func_info checked by the loader */ +struct bpf_func_info_min { + __u32 insn_off; + __u32 type_id; +}; + +/* The minimum bpf_line_info checked by the loader */ +struct bpf_line_info_min { + __u32 insn_off; + __u32 file_name_off; + __u32 line_off; + __u32 line_col; +}; + +/* bpf_field_info_kind encodes which aspect of captured field has to be + * adjusted by relocations. Currently supported values are: + * - BPF_FIELD_BYTE_OFFSET: field offset (in bytes); + * - BPF_FIELD_EXISTS: field existence (1, if field exists; 0, otherwise); + */ +enum bpf_field_info_kind { + BPF_FIELD_BYTE_OFFSET = 0, /* field byte offset */ + BPF_FIELD_BYTE_SIZE = 1, + BPF_FIELD_EXISTS = 2, /* field existence in target kernel */ + BPF_FIELD_SIGNED = 3, + BPF_FIELD_LSHIFT_U64 = 4, + BPF_FIELD_RSHIFT_U64 = 5, +}; + +/* The minimum bpf_field_reloc checked by the loader + * + * Field relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual field info; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * field; + * - access_str_off - offset into corresponding .BTF string section. String + * itself encodes an accessed field using a sequence of field and array + * indicies, separated by colon (:). It's conceptually very close to LLVM's + * getelementptr ([0]) instruction's arguments for identifying offset to + * a field. + * + * Example to provide a better feel. + * + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int x = &s->a; // encoded as "0:0" (a is field #0) + * int y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit field relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_field_reloc { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; + enum bpf_field_info_kind kind; +}; + +#endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/src/contrib/libbpf/bpf/libbpf_probes.c b/src/contrib/libbpf/bpf/libbpf_probes.c new file mode 100644 index 0000000..a9eb8b3 --- /dev/null +++ b/src/contrib/libbpf/bpf/libbpf_probes.c @@ -0,0 +1,323 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2019 Netronome Systems, Inc. */ + +#include <errno.h> +#include <fcntl.h> +#include <string.h> +#include <stdlib.h> +#include <unistd.h> +#include <net/if.h> +#include <sys/utsname.h> + +#include <linux/btf.h> +#include <linux/filter.h> +#include <linux/kernel.h> + +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" + +static bool grep(const char *buffer, const char *pattern) +{ + return !!strstr(buffer, pattern); +} + +static int get_vendor_id(int ifindex) +{ + char ifname[IF_NAMESIZE], path[64], buf[8]; + ssize_t len; + int fd; + + if (!if_indextoname(ifindex, ifname)) + return -1; + + snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname); + + fd = open(path, O_RDONLY); + if (fd < 0) + return -1; + + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len < 0) + return -1; + if (len >= (ssize_t)sizeof(buf)) + return -1; + buf[len] = '\0'; + + return strtol(buf, NULL, 0); +} + +static int get_kernel_version(void) +{ + int version, subversion, patchlevel; + struct utsname utsn; + + /* Return 0 on failure, and attempt to probe with empty kversion */ + if (uname(&utsn)) + return 0; + + if (sscanf(utsn.release, "%d.%d.%d", + &version, &subversion, &patchlevel) != 3) + return 0; + + return (version << 16) + (subversion << 8) + patchlevel; +} + +static void +probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, + size_t insns_cnt, char *buf, size_t buf_len, __u32 ifindex) +{ + struct bpf_load_program_attr xattr = {}; + int fd; + + switch (prog_type) { + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + xattr.expected_attach_type = BPF_CGROUP_INET4_CONNECT; + break; + case BPF_PROG_TYPE_KPROBE: + xattr.kern_version = get_kernel_version(); + break; + case BPF_PROG_TYPE_UNSPEC: + case BPF_PROG_TYPE_SOCKET_FILTER: + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_SCHED_ACT: + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_XDP: + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_LWT_IN: + case BPF_PROG_TYPE_LWT_OUT: + case BPF_PROG_TYPE_LWT_XMIT: + case BPF_PROG_TYPE_SOCK_OPS: + case BPF_PROG_TYPE_SK_SKB: + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_SK_MSG: + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: + case BPF_PROG_TYPE_LWT_SEG6LOCAL: + case BPF_PROG_TYPE_LIRC_MODE2: + case BPF_PROG_TYPE_SK_REUSEPORT: + case BPF_PROG_TYPE_FLOW_DISSECTOR: + case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + case BPF_PROG_TYPE_TRACING: + default: + break; + } + + xattr.prog_type = prog_type; + xattr.insns = insns; + xattr.insns_cnt = insns_cnt; + xattr.license = "GPL"; + xattr.prog_ifindex = ifindex; + + fd = bpf_load_program_xattr(&xattr, buf, buf_len); + if (fd >= 0) + close(fd); +} + +bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex) +{ + struct bpf_insn insns[2] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN() + }; + + if (ifindex && prog_type == BPF_PROG_TYPE_SCHED_CLS) + /* nfp returns -EINVAL on exit(0) with TC offload */ + insns[0].imm = 2; + + errno = 0; + probe_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex); + + return errno != EINVAL && errno != EOPNOTSUPP; +} + +int libbpf__load_raw_btf(const char *raw_types, size_t types_len, + const char *str_sec, size_t str_len) +{ + struct btf_header hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = types_len, + .str_off = types_len, + .str_len = str_len, + }; + int btf_fd, btf_len; + __u8 *raw_btf; + + btf_len = hdr.hdr_len + hdr.type_len + hdr.str_len; + raw_btf = malloc(btf_len); + if (!raw_btf) + return -ENOMEM; + + memcpy(raw_btf, &hdr, sizeof(hdr)); + memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len); + memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len); + + btf_fd = bpf_load_btf(raw_btf, btf_len, NULL, 0, false); + + free(raw_btf); + return btf_fd; +} + +static int load_sk_storage_btf(void) +{ + const char strs[] = "\0bpf_spin_lock\0val\0cnt\0l"; + /* struct bpf_spin_lock { + * int val; + * }; + * struct val { + * int cnt; + * struct bpf_spin_lock l; + * }; + */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* struct bpf_spin_lock */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4), + BTF_MEMBER_ENC(15, 1, 0), /* int val; */ + /* struct val */ /* [3] */ + BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */ + BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */ + }; + + return libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); +} + +bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) +{ + int key_size, value_size, max_entries, map_flags; + __u32 btf_key_type_id = 0, btf_value_type_id = 0; + struct bpf_create_map_attr attr = {}; + int fd = -1, btf_fd = -1, fd_inner; + + key_size = sizeof(__u32); + value_size = sizeof(__u32); + max_entries = 1; + map_flags = 0; + + switch (map_type) { + case BPF_MAP_TYPE_STACK_TRACE: + value_size = sizeof(__u64); + break; + case BPF_MAP_TYPE_LPM_TRIE: + key_size = sizeof(__u64); + value_size = sizeof(__u64); + map_flags = BPF_F_NO_PREALLOC; + break; + case BPF_MAP_TYPE_CGROUP_STORAGE: + case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: + key_size = sizeof(struct bpf_cgroup_storage_key); + value_size = sizeof(__u64); + max_entries = 0; + break; + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + key_size = 0; + break; + case BPF_MAP_TYPE_SK_STORAGE: + btf_key_type_id = 1; + btf_value_type_id = 3; + value_size = 8; + max_entries = 0; + map_flags = BPF_F_NO_PREALLOC; + btf_fd = load_sk_storage_btf(); + if (btf_fd < 0) + return false; + break; + case BPF_MAP_TYPE_UNSPEC: + case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_ARRAY: + case BPF_MAP_TYPE_PROG_ARRAY: + case BPF_MAP_TYPE_PERF_EVENT_ARRAY: + case BPF_MAP_TYPE_PERCPU_HASH: + case BPF_MAP_TYPE_PERCPU_ARRAY: + case BPF_MAP_TYPE_CGROUP_ARRAY: + case BPF_MAP_TYPE_LRU_HASH: + case BPF_MAP_TYPE_LRU_PERCPU_HASH: + case BPF_MAP_TYPE_ARRAY_OF_MAPS: + case BPF_MAP_TYPE_HASH_OF_MAPS: + case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: + case BPF_MAP_TYPE_SOCKMAP: + case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_XSKMAP: + case BPF_MAP_TYPE_SOCKHASH: + case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: + default: + break; + } + + if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS || + map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { + /* TODO: probe for device, once libbpf has a function to create + * map-in-map for offload + */ + if (ifindex) + return false; + + fd_inner = bpf_create_map(BPF_MAP_TYPE_HASH, + sizeof(__u32), sizeof(__u32), 1, 0); + if (fd_inner < 0) + return false; + fd = bpf_create_map_in_map(map_type, NULL, sizeof(__u32), + fd_inner, 1, 0); + close(fd_inner); + } else { + /* Note: No other restriction on map type probes for offload */ + attr.map_type = map_type; + attr.key_size = key_size; + attr.value_size = value_size; + attr.max_entries = max_entries; + attr.map_flags = map_flags; + attr.map_ifindex = ifindex; + if (btf_fd >= 0) { + attr.btf_fd = btf_fd; + attr.btf_key_type_id = btf_key_type_id; + attr.btf_value_type_id = btf_value_type_id; + } + + fd = bpf_create_map_xattr(&attr); + } + if (fd >= 0) + close(fd); + if (btf_fd >= 0) + close(btf_fd); + + return fd >= 0; +} + +bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, + __u32 ifindex) +{ + struct bpf_insn insns[2] = { + BPF_EMIT_CALL(id), + BPF_EXIT_INSN() + }; + char buf[4096] = {}; + bool res; + + probe_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf), + ifindex); + res = !grep(buf, "invalid func ") && !grep(buf, "unknown func "); + + if (ifindex) { + switch (get_vendor_id(ifindex)) { + case 0x19ee: /* Netronome specific */ + res = res && !grep(buf, "not supported by FW") && + !grep(buf, "unsupported function id"); + break; + default: + break; + } + } + + return res; +} diff --git a/src/contrib/libbpf/bpf/libbpf_util.h b/src/contrib/libbpf/bpf/libbpf_util.h new file mode 100644 index 0000000..59c779c --- /dev/null +++ b/src/contrib/libbpf/bpf/libbpf_util.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2019 Facebook */ + +#ifndef __LIBBPF_LIBBPF_UTIL_H +#define __LIBBPF_LIBBPF_UTIL_H + +#include <stdbool.h> + +#ifdef __cplusplus +extern "C" { +#endif + +/* Use these barrier functions instead of smp_[rw]mb() when they are + * used in a libbpf header file. That way they can be built into the + * application that uses libbpf. + */ +#if defined(__i386__) || defined(__x86_64__) +# define libbpf_smp_rmb() asm volatile("" : : : "memory") +# define libbpf_smp_wmb() asm volatile("" : : : "memory") +# define libbpf_smp_mb() \ + asm volatile("lock; addl $0,-4(%%rsp)" : : : "memory", "cc") +/* Hinders stores to be observed before older loads. */ +# define libbpf_smp_rwmb() asm volatile("" : : : "memory") +#elif defined(__aarch64__) +# define libbpf_smp_rmb() asm volatile("dmb ishld" : : : "memory") +# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory") +# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory") +# define libbpf_smp_rwmb() libbpf_smp_mb() +#elif defined(__arm__) +/* These are only valid for armv7 and above */ +# define libbpf_smp_rmb() asm volatile("dmb ish" : : : "memory") +# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory") +# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory") +# define libbpf_smp_rwmb() libbpf_smp_mb() +#else +/* Architecture missing native barrier functions. */ +# define libbpf_smp_rmb() __sync_synchronize() +# define libbpf_smp_wmb() __sync_synchronize() +# define libbpf_smp_mb() __sync_synchronize() +# define libbpf_smp_rwmb() __sync_synchronize() +#endif + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif diff --git a/src/contrib/libbpf/bpf/netlink.c b/src/contrib/libbpf/bpf/netlink.c new file mode 100644 index 0000000..5065c1a --- /dev/null +++ b/src/contrib/libbpf/bpf/netlink.c @@ -0,0 +1,451 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2018 Facebook */ + +#include <stdlib.h> +#include <memory.h> +#include <unistd.h> +#include <linux/bpf.h> +#include <linux/rtnetlink.h> +#include <sys/socket.h> +#include <errno.h> +#include <time.h> + +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" +#include "nlattr.h" + +#ifndef SOL_NETLINK +#define SOL_NETLINK 270 +#endif + +typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t, + void *cookie); + +struct xdp_id_md { + int ifindex; + __u32 flags; + struct xdp_link_info info; +}; + +int libbpf_netlink_open(__u32 *nl_pid) +{ + struct sockaddr_nl sa; + socklen_t addrlen; + int one = 1, ret; + int sock; + + memset(&sa, 0, sizeof(sa)); + sa.nl_family = AF_NETLINK; + + sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock < 0) + return -errno; + + if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)) < 0) { + pr_warn("Netlink error reporting not supported\n"); + } + + if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { + ret = -errno; + goto cleanup; + } + + addrlen = sizeof(sa); + if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) { + ret = -errno; + goto cleanup; + } + + if (addrlen != sizeof(sa)) { + ret = -LIBBPF_ERRNO__INTERNAL; + goto cleanup; + } + + *nl_pid = sa.nl_pid; + return sock; + +cleanup: + close(sock); + return ret; +} + +static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq, + __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + bool multipart = true; + struct nlmsgerr *err; + struct nlmsghdr *nh; + char buf[4096]; + int len, ret; + + while (multipart) { + multipart = false; + len = recv(sock, buf, sizeof(buf), 0); + if (len < 0) { + ret = -errno; + goto done; + } + + if (len == 0) + break; + + for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len); + nh = NLMSG_NEXT(nh, len)) { + if (nh->nlmsg_pid != nl_pid) { + ret = -LIBBPF_ERRNO__WRNGPID; + goto done; + } + if (nh->nlmsg_seq != seq) { + ret = -LIBBPF_ERRNO__INVSEQ; + goto done; + } + if (nh->nlmsg_flags & NLM_F_MULTI) + multipart = true; + switch (nh->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(nh); + if (!err->error) + continue; + ret = err->error; + libbpf_nla_dump_errormsg(nh); + goto done; + case NLMSG_DONE: + return 0; + default: + break; + } + if (_fn) { + ret = _fn(nh, fn, cookie); + if (ret) + return ret; + } + } + } + ret = 0; +done: + return ret; +} + +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags) +{ + int sock, seq = 0, ret; + struct nlattr *nla, *nla_xdp; + struct { + struct nlmsghdr nh; + struct ifinfomsg ifinfo; + char attrbuf[64]; + } req; + __u32 nl_pid; + + sock = libbpf_netlink_open(&nl_pid); + if (sock < 0) + return sock; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_SETLINK; + req.nh.nlmsg_pid = 0; + req.nh.nlmsg_seq = ++seq; + req.ifinfo.ifi_family = AF_UNSPEC; + req.ifinfo.ifi_index = ifindex; + + /* started nested attribute for XDP */ + nla = (struct nlattr *)(((char *)&req) + + NLMSG_ALIGN(req.nh.nlmsg_len)); + nla->nla_type = NLA_F_NESTED | IFLA_XDP; + nla->nla_len = NLA_HDRLEN; + + /* add XDP fd */ + nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); + nla_xdp->nla_type = IFLA_XDP_FD; + nla_xdp->nla_len = NLA_HDRLEN + sizeof(int); + memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd)); + nla->nla_len += nla_xdp->nla_len; + + /* if user passed in any flags, add those too */ + if (flags) { + nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); + nla_xdp->nla_type = IFLA_XDP_FLAGS; + nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags); + memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags)); + nla->nla_len += nla_xdp->nla_len; + } + + req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len); + + if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) { + ret = -errno; + goto cleanup; + } + ret = bpf_netlink_recv(sock, nl_pid, seq, NULL, NULL, NULL); + +cleanup: + close(sock); + return ret; +} + +static int __dump_link_nlmsg(struct nlmsghdr *nlh, + libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie) +{ + struct nlattr *tb[IFLA_MAX + 1], *attr; + struct ifinfomsg *ifi = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi)); + attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi))); + if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_link_nlmsg(cookie, ifi, tb); +} + +static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb) +{ + struct nlattr *xdp_tb[IFLA_XDP_MAX + 1]; + struct xdp_id_md *xdp_id = cookie; + struct ifinfomsg *ifinfo = msg; + int ret; + + if (xdp_id->ifindex && xdp_id->ifindex != ifinfo->ifi_index) + return 0; + + if (!tb[IFLA_XDP]) + return 0; + + ret = libbpf_nla_parse_nested(xdp_tb, IFLA_XDP_MAX, tb[IFLA_XDP], NULL); + if (ret) + return ret; + + if (!xdp_tb[IFLA_XDP_ATTACHED]) + return 0; + + xdp_id->info.attach_mode = libbpf_nla_getattr_u8( + xdp_tb[IFLA_XDP_ATTACHED]); + + if (xdp_id->info.attach_mode == XDP_ATTACHED_NONE) + return 0; + + if (xdp_tb[IFLA_XDP_PROG_ID]) + xdp_id->info.prog_id = libbpf_nla_getattr_u32( + xdp_tb[IFLA_XDP_PROG_ID]); + + if (xdp_tb[IFLA_XDP_SKB_PROG_ID]) + xdp_id->info.skb_prog_id = libbpf_nla_getattr_u32( + xdp_tb[IFLA_XDP_SKB_PROG_ID]); + + if (xdp_tb[IFLA_XDP_DRV_PROG_ID]) + xdp_id->info.drv_prog_id = libbpf_nla_getattr_u32( + xdp_tb[IFLA_XDP_DRV_PROG_ID]); + + if (xdp_tb[IFLA_XDP_HW_PROG_ID]) + xdp_id->info.hw_prog_id = libbpf_nla_getattr_u32( + xdp_tb[IFLA_XDP_HW_PROG_ID]); + + return 0; +} + +int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, + size_t info_size, __u32 flags) +{ + struct xdp_id_md xdp_id = {}; + int sock, ret; + __u32 nl_pid; + __u32 mask; + + if (flags & ~XDP_FLAGS_MASK || !info_size) + return -EINVAL; + + /* Check whether the single {HW,DRV,SKB} mode is set */ + flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE); + mask = flags - 1; + if (flags && flags & mask) + return -EINVAL; + + sock = libbpf_netlink_open(&nl_pid); + if (sock < 0) + return sock; + + xdp_id.ifindex = ifindex; + xdp_id.flags = flags; + + ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_info, &xdp_id); + if (!ret) { + size_t sz = min(info_size, sizeof(xdp_id.info)); + + memcpy(info, &xdp_id.info, sz); + memset((void *) info + sz, 0, info_size - sz); + } + + close(sock); + return ret; +} + +static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags) +{ + if (info->attach_mode != XDP_ATTACHED_MULTI) + return info->prog_id; + if (flags & XDP_FLAGS_DRV_MODE) + return info->drv_prog_id; + if (flags & XDP_FLAGS_HW_MODE) + return info->hw_prog_id; + if (flags & XDP_FLAGS_SKB_MODE) + return info->skb_prog_id; + + return 0; +} + +int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) +{ + struct xdp_link_info info; + int ret; + + ret = bpf_get_link_xdp_info(ifindex, &info, sizeof(info), flags); + if (!ret) + *prog_id = get_xdp_id(&info, flags); + + return ret; +} + +int libbpf_nl_get_link(int sock, unsigned int nl_pid, + libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct ifinfomsg ifm; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), + .nlh.nlmsg_type = RTM_GETLINK, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .ifm.ifi_family = AF_PACKET, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return bpf_netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg, + dump_link_nlmsg, cookie); +} + +static int __dump_class_nlmsg(struct nlmsghdr *nlh, + libbpf_dump_nlmsg_t dump_class_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_class_nlmsg(cookie, t, tb); +} + +int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTCLASS, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return bpf_netlink_recv(sock, nl_pid, seq, __dump_class_nlmsg, + dump_class_nlmsg, cookie); +} + +static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh, + libbpf_dump_nlmsg_t dump_qdisc_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_qdisc_nlmsg(cookie, t, tb); +} + +int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETQDISC, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return bpf_netlink_recv(sock, nl_pid, seq, __dump_qdisc_nlmsg, + dump_qdisc_nlmsg, cookie); +} + +static int __dump_filter_nlmsg(struct nlmsghdr *nlh, + libbpf_dump_nlmsg_t dump_filter_nlmsg, + void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (libbpf_nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_filter_nlmsg(cookie, t, tb); +} + +int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTFILTER, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + .t.tcm_parent = handle, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return bpf_netlink_recv(sock, nl_pid, seq, __dump_filter_nlmsg, + dump_filter_nlmsg, cookie); +} diff --git a/src/contrib/libbpf/bpf/nlattr.c b/src/contrib/libbpf/bpf/nlattr.c new file mode 100644 index 0000000..8db44bb --- /dev/null +++ b/src/contrib/libbpf/bpf/nlattr.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * NETLINK Netlink attributes + * + * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch> + */ + +#include <errno.h> +#include "nlattr.h" +#include "libbpf_internal.h" +#include <linux/rtnetlink.h> +#include <string.h> +#include <stdio.h> + +static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = { + [LIBBPF_NLA_U8] = sizeof(uint8_t), + [LIBBPF_NLA_U16] = sizeof(uint16_t), + [LIBBPF_NLA_U32] = sizeof(uint32_t), + [LIBBPF_NLA_U64] = sizeof(uint64_t), + [LIBBPF_NLA_STRING] = 1, + [LIBBPF_NLA_FLAG] = 0, +}; + +static struct nlattr *nla_next(const struct nlattr *nla, int *remaining) +{ + int totlen = NLA_ALIGN(nla->nla_len); + + *remaining -= totlen; + return (struct nlattr *) ((char *) nla + totlen); +} + +static int nla_ok(const struct nlattr *nla, int remaining) +{ + return remaining >= sizeof(*nla) && + nla->nla_len >= sizeof(*nla) && + nla->nla_len <= remaining; +} + +static int nla_type(const struct nlattr *nla) +{ + return nla->nla_type & NLA_TYPE_MASK; +} + +static int validate_nla(struct nlattr *nla, int maxtype, + struct libbpf_nla_policy *policy) +{ + struct libbpf_nla_policy *pt; + unsigned int minlen = 0; + int type = nla_type(nla); + + if (type < 0 || type > maxtype) + return 0; + + pt = &policy[type]; + + if (pt->type > LIBBPF_NLA_TYPE_MAX) + return 0; + + if (pt->minlen) + minlen = pt->minlen; + else if (pt->type != LIBBPF_NLA_UNSPEC) + minlen = nla_attr_minlen[pt->type]; + + if (libbpf_nla_len(nla) < minlen) + return -1; + + if (pt->maxlen && libbpf_nla_len(nla) > pt->maxlen) + return -1; + + if (pt->type == LIBBPF_NLA_STRING) { + char *data = libbpf_nla_data(nla); + + if (data[libbpf_nla_len(nla) - 1] != '\0') + return -1; + } + + return 0; +} + +static inline int nlmsg_len(const struct nlmsghdr *nlh) +{ + return nlh->nlmsg_len - NLMSG_HDRLEN; +} + +/** + * Create attribute index based on a stream of attributes. + * @arg tb Index array to be filled (maxtype+1 elements). + * @arg maxtype Maximum attribute type expected and accepted. + * @arg head Head of attribute stream. + * @arg len Length of attribute stream. + * @arg policy Attribute validation policy. + * + * Iterates over the stream of attributes and stores a pointer to each + * attribute in the index array using the attribute type as index to + * the array. Attribute with a type greater than the maximum type + * specified will be silently ignored in order to maintain backwards + * compatibility. If \a policy is not NULL, the attribute will be + * validated using the specified policy. + * + * @see nla_validate + * @return 0 on success or a negative error code. + */ +int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, + int len, struct libbpf_nla_policy *policy) +{ + struct nlattr *nla; + int rem, err; + + memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); + + libbpf_nla_for_each_attr(nla, head, len, rem) { + int type = nla_type(nla); + + if (type > maxtype) + continue; + + if (policy) { + err = validate_nla(nla, maxtype, policy); + if (err < 0) + goto errout; + } + + if (tb[type]) + pr_warn("Attribute of type %#x found multiple times in message, " + "previous attribute is being ignored.\n", type); + + tb[type] = nla; + } + + err = 0; +errout: + return err; +} + +/** + * Create attribute index based on nested attribute + * @arg tb Index array to be filled (maxtype+1 elements). + * @arg maxtype Maximum attribute type expected and accepted. + * @arg nla Nested Attribute. + * @arg policy Attribute validation policy. + * + * Feeds the stream of attributes nested into the specified attribute + * to libbpf_nla_parse(). + * + * @see libbpf_nla_parse + * @return 0 on success or a negative error code. + */ +int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype, + struct nlattr *nla, + struct libbpf_nla_policy *policy) +{ + return libbpf_nla_parse(tb, maxtype, libbpf_nla_data(nla), + libbpf_nla_len(nla), policy); +} + +/* dump netlink extended ack error message */ +int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh) +{ + struct libbpf_nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = { + [NLMSGERR_ATTR_MSG] = { .type = LIBBPF_NLA_STRING }, + [NLMSGERR_ATTR_OFFS] = { .type = LIBBPF_NLA_U32 }, + }; + struct nlattr *tb[NLMSGERR_ATTR_MAX + 1], *attr; + struct nlmsgerr *err; + char *errmsg = NULL; + int hlen, alen; + + /* no TLVs, nothing to do here */ + if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) + return 0; + + err = (struct nlmsgerr *)NLMSG_DATA(nlh); + hlen = sizeof(*err); + + /* if NLM_F_CAPPED is set then the inner err msg was capped */ + if (!(nlh->nlmsg_flags & NLM_F_CAPPED)) + hlen += nlmsg_len(&err->msg); + + attr = (struct nlattr *) ((void *) err + hlen); + alen = nlh->nlmsg_len - hlen; + + if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, + extack_policy) != 0) { + pr_warn("Failed to parse extended error attributes\n"); + return 0; + } + + if (tb[NLMSGERR_ATTR_MSG]) + errmsg = (char *) libbpf_nla_data(tb[NLMSGERR_ATTR_MSG]); + + pr_warn("Kernel error message: %s\n", errmsg); + + return 0; +} diff --git a/src/contrib/libbpf/bpf/nlattr.h b/src/contrib/libbpf/bpf/nlattr.h new file mode 100644 index 0000000..6cc3ac9 --- /dev/null +++ b/src/contrib/libbpf/bpf/nlattr.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * NETLINK Netlink attributes + * + * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch> + */ + +#ifndef __LIBBPF_NLATTR_H +#define __LIBBPF_NLATTR_H + +#include <stdint.h> +#include <linux/netlink.h> +/* avoid multiple definition of netlink features */ +#define __LINUX_NETLINK_H + +/** + * Standard attribute types to specify validation policy + */ +enum { + LIBBPF_NLA_UNSPEC, /**< Unspecified type, binary data chunk */ + LIBBPF_NLA_U8, /**< 8 bit integer */ + LIBBPF_NLA_U16, /**< 16 bit integer */ + LIBBPF_NLA_U32, /**< 32 bit integer */ + LIBBPF_NLA_U64, /**< 64 bit integer */ + LIBBPF_NLA_STRING, /**< NUL terminated character string */ + LIBBPF_NLA_FLAG, /**< Flag */ + LIBBPF_NLA_MSECS, /**< Micro seconds (64bit) */ + LIBBPF_NLA_NESTED, /**< Nested attributes */ + __LIBBPF_NLA_TYPE_MAX, +}; + +#define LIBBPF_NLA_TYPE_MAX (__LIBBPF_NLA_TYPE_MAX - 1) + +/** + * @ingroup attr + * Attribute validation policy. + * + * See section @core_doc{core_attr_parse,Attribute Parsing} for more details. + */ +struct libbpf_nla_policy { + /** Type of attribute or LIBBPF_NLA_UNSPEC */ + uint16_t type; + + /** Minimal length of payload required */ + uint16_t minlen; + + /** Maximal length of payload allowed */ + uint16_t maxlen; +}; + +/** + * @ingroup attr + * Iterate over a stream of attributes + * @arg pos loop counter, set to current attribute + * @arg head head of attribute stream + * @arg len length of attribute stream + * @arg rem initialized to len, holds bytes currently remaining in stream + */ +#define libbpf_nla_for_each_attr(pos, head, len, rem) \ + for (pos = head, rem = len; \ + nla_ok(pos, rem); \ + pos = nla_next(pos, &(rem))) + +/** + * libbpf_nla_data - head of payload + * @nla: netlink attribute + */ +static inline void *libbpf_nla_data(const struct nlattr *nla) +{ + return (char *) nla + NLA_HDRLEN; +} + +static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla) +{ + return *(uint8_t *)libbpf_nla_data(nla); +} + +static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla) +{ + return *(uint32_t *)libbpf_nla_data(nla); +} + +static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla) +{ + return (const char *)libbpf_nla_data(nla); +} + +/** + * libbpf_nla_len - length of payload + * @nla: netlink attribute + */ +static inline int libbpf_nla_len(const struct nlattr *nla) +{ + return nla->nla_len - NLA_HDRLEN; +} + +int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, + int len, struct libbpf_nla_policy *policy); +int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype, + struct nlattr *nla, + struct libbpf_nla_policy *policy); + +int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh); + +#endif /* __LIBBPF_NLATTR_H */ diff --git a/src/contrib/libbpf/bpf/str_error.c b/src/contrib/libbpf/bpf/str_error.c new file mode 100644 index 0000000..b8064ee --- /dev/null +++ b/src/contrib/libbpf/bpf/str_error.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +#undef _GNU_SOURCE +#include <string.h> +#include <stdio.h> +#include "str_error.h" + +/* + * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl + * libc, while checking strerror_r() return to avoid having to check this in + * all places calling it. + */ +char *libbpf_strerror_r(int err, char *dst, int len) +{ + int ret = strerror_r(err < 0 ? -err : err, dst, len); + if (ret) + snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret); + return dst; +} diff --git a/src/contrib/libbpf/bpf/str_error.h b/src/contrib/libbpf/bpf/str_error.h new file mode 100644 index 0000000..a139334 --- /dev/null +++ b/src/contrib/libbpf/bpf/str_error.h @@ -0,0 +1,6 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __LIBBPF_STR_ERROR_H +#define __LIBBPF_STR_ERROR_H + +char *libbpf_strerror_r(int err, char *dst, int len); +#endif /* __LIBBPF_STR_ERROR_H */ diff --git a/src/contrib/libbpf/bpf/xsk.c b/src/contrib/libbpf/bpf/xsk.c new file mode 100644 index 0000000..8e0ffa8 --- /dev/null +++ b/src/contrib/libbpf/bpf/xsk.c @@ -0,0 +1,797 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * AF_XDP user-space access library. + * + * Copyright(c) 2018 - 2019 Intel Corporation. + * + * Author(s): Magnus Karlsson <magnus.karlsson@intel.com> + */ + +#include <errno.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <arpa/inet.h> +#include <asm/barrier.h> +#include <linux/compiler.h> +#include <linux/ethtool.h> +#include <linux/filter.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_xdp.h> +#include <linux/sockios.h> +#include <net/if.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/socket.h> +#include <sys/types.h> + +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" +#include "xsk.h" + +#ifndef SOL_XDP + #define SOL_XDP 283 +#endif + +#ifndef AF_XDP + #define AF_XDP 44 +#endif + +#ifndef PF_XDP + #define PF_XDP AF_XDP +#endif + +struct xsk_umem { + struct xsk_ring_prod *fill; + struct xsk_ring_cons *comp; + char *umem_area; + struct xsk_umem_config config; + int fd; + int refcount; +}; + +struct xsk_socket { + struct xsk_ring_cons *rx; + struct xsk_ring_prod *tx; + __u64 outstanding_tx; + struct xsk_umem *umem; + struct xsk_socket_config config; + int fd; + int ifindex; + int prog_fd; + int xsks_map_fd; + __u32 queue_id; + char ifname[IFNAMSIZ]; +}; + +struct xsk_nl_info { + bool xdp_prog_attached; + int ifindex; + int fd; +}; + +/* Up until and including Linux 5.3 */ +struct xdp_ring_offset_v1 { + __u64 producer; + __u64 consumer; + __u64 desc; +}; + +/* Up until and including Linux 5.3 */ +struct xdp_mmap_offsets_v1 { + struct xdp_ring_offset_v1 rx; + struct xdp_ring_offset_v1 tx; + struct xdp_ring_offset_v1 fr; + struct xdp_ring_offset_v1 cr; +}; + +int xsk_umem__fd(const struct xsk_umem *umem) +{ + return umem ? umem->fd : -EINVAL; +} + +int xsk_socket__fd(const struct xsk_socket *xsk) +{ + return xsk ? xsk->fd : -EINVAL; +} + +static bool xsk_page_aligned(void *buffer) +{ + unsigned long addr = (unsigned long)buffer; + + return !(addr & (getpagesize() - 1)); +} + +static void xsk_set_umem_config(struct xsk_umem_config *cfg, + const struct xsk_umem_config *usr_cfg) +{ + if (!usr_cfg) { + cfg->fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; + cfg->comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; + cfg->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; + cfg->frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM; + cfg->flags = XSK_UMEM__DEFAULT_FLAGS; + return; + } + + cfg->fill_size = usr_cfg->fill_size; + cfg->comp_size = usr_cfg->comp_size; + cfg->frame_size = usr_cfg->frame_size; + cfg->frame_headroom = usr_cfg->frame_headroom; + cfg->flags = usr_cfg->flags; +} + +static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, + const struct xsk_socket_config *usr_cfg) +{ + if (!usr_cfg) { + cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; + cfg->tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; + cfg->libbpf_flags = 0; + cfg->xdp_flags = 0; + cfg->bind_flags = 0; + return 0; + } + + if (usr_cfg->libbpf_flags & ~XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD) + return -EINVAL; + + cfg->rx_size = usr_cfg->rx_size; + cfg->tx_size = usr_cfg->tx_size; + cfg->libbpf_flags = usr_cfg->libbpf_flags; + cfg->xdp_flags = usr_cfg->xdp_flags; + cfg->bind_flags = usr_cfg->bind_flags; + + return 0; +} + +static void xsk_mmap_offsets_v1(struct xdp_mmap_offsets *off) +{ + struct xdp_mmap_offsets_v1 off_v1; + + /* getsockopt on a kernel <= 5.3 has no flags fields. + * Copy over the offsets to the correct places in the >=5.4 format + * and put the flags where they would have been on that kernel. + */ + memcpy(&off_v1, off, sizeof(off_v1)); + + off->rx.producer = off_v1.rx.producer; + off->rx.consumer = off_v1.rx.consumer; + off->rx.desc = off_v1.rx.desc; + off->rx.flags = off_v1.rx.consumer + sizeof(__u32); + + off->tx.producer = off_v1.tx.producer; + off->tx.consumer = off_v1.tx.consumer; + off->tx.desc = off_v1.tx.desc; + off->tx.flags = off_v1.tx.consumer + sizeof(__u32); + + off->fr.producer = off_v1.fr.producer; + off->fr.consumer = off_v1.fr.consumer; + off->fr.desc = off_v1.fr.desc; + off->fr.flags = off_v1.fr.consumer + sizeof(__u32); + + off->cr.producer = off_v1.cr.producer; + off->cr.consumer = off_v1.cr.consumer; + off->cr.desc = off_v1.cr.desc; + off->cr.flags = off_v1.cr.consumer + sizeof(__u32); +} + +static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off) +{ + socklen_t optlen; + int err; + + optlen = sizeof(*off); + err = getsockopt(fd, SOL_XDP, XDP_MMAP_OFFSETS, off, &optlen); + if (err) + return err; + + if (optlen == sizeof(*off)) + return 0; + + if (optlen == sizeof(struct xdp_mmap_offsets_v1)) { + xsk_mmap_offsets_v1(off); + return 0; + } + + return -EINVAL; +} + +int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, + __u64 size, struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *usr_config) +{ + struct xdp_mmap_offsets off; + struct xdp_umem_reg mr; + struct xsk_umem *umem; + void *map; + int err; + + if (!umem_area || !umem_ptr || !fill || !comp) + return -EFAULT; + if (!size && !xsk_page_aligned(umem_area)) + return -EINVAL; + + umem = calloc(1, sizeof(*umem)); + if (!umem) + return -ENOMEM; + + umem->fd = socket(AF_XDP, SOCK_RAW, 0); + if (umem->fd < 0) { + err = -errno; + goto out_umem_alloc; + } + + umem->umem_area = umem_area; + xsk_set_umem_config(&umem->config, usr_config); + + memset(&mr, 0, sizeof(mr)); + mr.addr = (uintptr_t)umem_area; + mr.len = size; + mr.chunk_size = umem->config.frame_size; + mr.headroom = umem->config.frame_headroom; + mr.flags = umem->config.flags; + + err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr)); + if (err) { + err = -errno; + goto out_socket; + } + err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_FILL_RING, + &umem->config.fill_size, + sizeof(umem->config.fill_size)); + if (err) { + err = -errno; + goto out_socket; + } + err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_COMPLETION_RING, + &umem->config.comp_size, + sizeof(umem->config.comp_size)); + if (err) { + err = -errno; + goto out_socket; + } + + err = xsk_get_mmap_offsets(umem->fd, &off); + if (err) { + err = -errno; + goto out_socket; + } + + map = mmap(NULL, off.fr.desc + umem->config.fill_size * sizeof(__u64), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd, + XDP_UMEM_PGOFF_FILL_RING); + if (map == MAP_FAILED) { + err = -errno; + goto out_socket; + } + + umem->fill = fill; + fill->mask = umem->config.fill_size - 1; + fill->size = umem->config.fill_size; + fill->producer = map + off.fr.producer; + fill->consumer = map + off.fr.consumer; + fill->flags = map + off.fr.flags; + fill->ring = map + off.fr.desc; + fill->cached_cons = umem->config.fill_size; + + map = mmap(NULL, off.cr.desc + umem->config.comp_size * sizeof(__u64), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd, + XDP_UMEM_PGOFF_COMPLETION_RING); + if (map == MAP_FAILED) { + err = -errno; + goto out_mmap; + } + + umem->comp = comp; + comp->mask = umem->config.comp_size - 1; + comp->size = umem->config.comp_size; + comp->producer = map + off.cr.producer; + comp->consumer = map + off.cr.consumer; + comp->flags = map + off.cr.flags; + comp->ring = map + off.cr.desc; + + *umem_ptr = umem; + return 0; + +out_mmap: + munmap(map, off.fr.desc + umem->config.fill_size * sizeof(__u64)); +out_socket: + close(umem->fd); +out_umem_alloc: + free(umem); + return err; +} + +struct xsk_umem_config_v1 { + __u32 fill_size; + __u32 comp_size; + __u32 frame_size; + __u32 frame_headroom; +}; + +int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, + __u64 size, struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *usr_config) +{ + struct xsk_umem_config config; + + memcpy(&config, usr_config, sizeof(struct xsk_umem_config_v1)); + config.flags = 0; + + return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp, + &config); +} +COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2) +DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4) + +static int xsk_load_xdp_prog(struct xsk_socket *xsk) +{ + static const int log_buf_size = 16 * 1024; + char log_buf[log_buf_size]; + int err, prog_fd; + + /* This is the C-program: + * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx) + * { + * int ret, index = ctx->rx_queue_index; + * + * // A set entry here means that the correspnding queue_id + * // has an active AF_XDP socket bound to it. + * ret = bpf_redirect_map(&xsks_map, index, XDP_PASS); + * if (ret > 0) + * return ret; + * + * // Fallback for pre-5.3 kernels, not supporting default + * // action in the flags parameter. + * if (bpf_map_lookup_elem(&xsks_map, &index)) + * return bpf_redirect_map(&xsks_map, index, 0); + * return XDP_PASS; + * } + */ + struct bpf_insn prog[] = { + /* r2 = *(u32 *)(r1 + 16) */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 16), + /* *(u32 *)(r10 - 4) = r2 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -4), + /* r1 = xskmap[] */ + BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd), + /* r3 = XDP_PASS */ + BPF_MOV64_IMM(BPF_REG_3, 2), + /* call bpf_redirect_map */ + BPF_EMIT_CALL(BPF_FUNC_redirect_map), + /* if w0 != 0 goto pc+13 */ + BPF_JMP32_IMM(BPF_JSGT, BPF_REG_0, 0, 13), + /* r2 = r10 */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + /* r2 += -4 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + /* r1 = xskmap[] */ + BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd), + /* call bpf_map_lookup_elem */ + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + /* r1 = r0 */ + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + /* r0 = XDP_PASS */ + BPF_MOV64_IMM(BPF_REG_0, 2), + /* if r1 == 0 goto pc+5 */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 5), + /* r2 = *(u32 *)(r10 - 4) */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_10, -4), + /* r1 = xskmap[] */ + BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd), + /* r3 = 0 */ + BPF_MOV64_IMM(BPF_REG_3, 0), + /* call bpf_redirect_map */ + BPF_EMIT_CALL(BPF_FUNC_redirect_map), + /* The jumps are to this instruction */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + + prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, prog, insns_cnt, + "LGPL-2.1 or BSD-2-Clause", 0, log_buf, + log_buf_size); + if (prog_fd < 0) { + pr_warn("BPF log buffer:\n%s", log_buf); + return prog_fd; + } + + err = bpf_set_link_xdp_fd(xsk->ifindex, prog_fd, xsk->config.xdp_flags); + if (err) { + close(prog_fd); + return err; + } + + xsk->prog_fd = prog_fd; + return 0; +} + +static int xsk_get_max_queues(struct xsk_socket *xsk) +{ + struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; + struct ifreq ifr = {}; + int fd, err, ret; + + fd = socket(AF_INET, SOCK_DGRAM, 0); + if (fd < 0) + return -errno; + + ifr.ifr_data = (void *)&channels; + memcpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1); + ifr.ifr_name[IFNAMSIZ - 1] = '\0'; + err = ioctl(fd, SIOCETHTOOL, &ifr); + if (err && errno != EOPNOTSUPP) { + ret = -errno; + goto out; + } + + if (err) { + /* If the device says it has no channels, then all traffic + * is sent to a single stream, so max queues = 1. + */ + ret = 1; + } else { + /* Take the max of rx, tx, combined. Drivers return + * the number of channels in different ways. + */ + ret = max(channels.max_rx, channels.max_tx); + ret = max(ret, (int)channels.max_combined); + } + +out: + close(fd); + return ret; +} + +static int xsk_create_bpf_maps(struct xsk_socket *xsk) +{ + int max_queues; + int fd; + + max_queues = xsk_get_max_queues(xsk); + if (max_queues < 0) + return max_queues; + + fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map", + sizeof(int), sizeof(int), max_queues, 0); + if (fd < 0) + return fd; + + xsk->xsks_map_fd = fd; + + return 0; +} + +static void xsk_delete_bpf_maps(struct xsk_socket *xsk) +{ + bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id); + close(xsk->xsks_map_fd); +} + +static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) +{ + __u32 i, *map_ids, num_maps, prog_len = sizeof(struct bpf_prog_info); + __u32 map_len = sizeof(struct bpf_map_info); + struct bpf_prog_info prog_info = {}; + struct bpf_map_info map_info; + int fd, err; + + err = bpf_obj_get_info_by_fd(xsk->prog_fd, &prog_info, &prog_len); + if (err) + return err; + + num_maps = prog_info.nr_map_ids; + + map_ids = calloc(prog_info.nr_map_ids, sizeof(*map_ids)); + if (!map_ids) + return -ENOMEM; + + memset(&prog_info, 0, prog_len); + prog_info.nr_map_ids = num_maps; + prog_info.map_ids = (__u64)(unsigned long)map_ids; + + err = bpf_obj_get_info_by_fd(xsk->prog_fd, &prog_info, &prog_len); + if (err) + goto out_map_ids; + + xsk->xsks_map_fd = -1; + + for (i = 0; i < prog_info.nr_map_ids; i++) { + fd = bpf_map_get_fd_by_id(map_ids[i]); + if (fd < 0) + continue; + + err = bpf_obj_get_info_by_fd(fd, &map_info, &map_len); + if (err) { + close(fd); + continue; + } + + if (!strcmp(map_info.name, "xsks_map")) { + xsk->xsks_map_fd = fd; + continue; + } + + close(fd); + } + + err = 0; + if (xsk->xsks_map_fd == -1) + err = -ENOENT; + +out_map_ids: + free(map_ids); + return err; +} + +static int xsk_set_bpf_maps(struct xsk_socket *xsk) +{ + return bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id, + &xsk->fd, 0); +} + +static int xsk_setup_xdp_prog(struct xsk_socket *xsk) +{ + __u32 prog_id = 0; + int err; + + err = bpf_get_link_xdp_id(xsk->ifindex, &prog_id, + xsk->config.xdp_flags); + if (err) + return err; + + if (!prog_id) { + err = xsk_create_bpf_maps(xsk); + if (err) + return err; + + err = xsk_load_xdp_prog(xsk); + if (err) { + xsk_delete_bpf_maps(xsk); + return err; + } + } else { + xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id); + if (xsk->prog_fd < 0) + return -errno; + err = xsk_lookup_bpf_maps(xsk); + if (err) { + close(xsk->prog_fd); + return err; + } + } + + if (xsk->rx) + err = xsk_set_bpf_maps(xsk); + if (err) { + xsk_delete_bpf_maps(xsk); + close(xsk->prog_fd); + return err; + } + + return 0; +} + +int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, + __u32 queue_id, struct xsk_umem *umem, + struct xsk_ring_cons *rx, struct xsk_ring_prod *tx, + const struct xsk_socket_config *usr_config) +{ + void *rx_map = NULL, *tx_map = NULL; + struct sockaddr_xdp sxdp = {}; + struct xdp_mmap_offsets off; + struct xsk_socket *xsk; + int err; + + if (!umem || !xsk_ptr || !(rx || tx)) + return -EFAULT; + + xsk = calloc(1, sizeof(*xsk)); + if (!xsk) + return -ENOMEM; + + err = xsk_set_xdp_socket_config(&xsk->config, usr_config); + if (err) + goto out_xsk_alloc; + + if (umem->refcount && + !(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { + pr_warn("Error: shared umems not supported by libbpf supplied XDP program.\n"); + err = -EBUSY; + goto out_xsk_alloc; + } + + if (umem->refcount++ > 0) { + xsk->fd = socket(AF_XDP, SOCK_RAW, 0); + if (xsk->fd < 0) { + err = -errno; + goto out_xsk_alloc; + } + } else { + xsk->fd = umem->fd; + } + + xsk->outstanding_tx = 0; + xsk->queue_id = queue_id; + xsk->umem = umem; + xsk->ifindex = if_nametoindex(ifname); + if (!xsk->ifindex) { + err = -errno; + goto out_socket; + } + memcpy(xsk->ifname, ifname, IFNAMSIZ - 1); + xsk->ifname[IFNAMSIZ - 1] = '\0'; + + if (rx) { + err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING, + &xsk->config.rx_size, + sizeof(xsk->config.rx_size)); + if (err) { + err = -errno; + goto out_socket; + } + } + if (tx) { + err = setsockopt(xsk->fd, SOL_XDP, XDP_TX_RING, + &xsk->config.tx_size, + sizeof(xsk->config.tx_size)); + if (err) { + err = -errno; + goto out_socket; + } + } + + err = xsk_get_mmap_offsets(xsk->fd, &off); + if (err) { + err = -errno; + goto out_socket; + } + + if (rx) { + rx_map = mmap(NULL, off.rx.desc + + xsk->config.rx_size * sizeof(struct xdp_desc), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, + xsk->fd, XDP_PGOFF_RX_RING); + if (rx_map == MAP_FAILED) { + err = -errno; + goto out_socket; + } + + rx->mask = xsk->config.rx_size - 1; + rx->size = xsk->config.rx_size; + rx->producer = rx_map + off.rx.producer; + rx->consumer = rx_map + off.rx.consumer; + rx->flags = rx_map + off.rx.flags; + rx->ring = rx_map + off.rx.desc; + } + xsk->rx = rx; + + if (tx) { + tx_map = mmap(NULL, off.tx.desc + + xsk->config.tx_size * sizeof(struct xdp_desc), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, + xsk->fd, XDP_PGOFF_TX_RING); + if (tx_map == MAP_FAILED) { + err = -errno; + goto out_mmap_rx; + } + + tx->mask = xsk->config.tx_size - 1; + tx->size = xsk->config.tx_size; + tx->producer = tx_map + off.tx.producer; + tx->consumer = tx_map + off.tx.consumer; + tx->flags = tx_map + off.tx.flags; + tx->ring = tx_map + off.tx.desc; + tx->cached_cons = xsk->config.tx_size; + } + xsk->tx = tx; + + sxdp.sxdp_family = PF_XDP; + sxdp.sxdp_ifindex = xsk->ifindex; + sxdp.sxdp_queue_id = xsk->queue_id; + if (umem->refcount > 1) { + sxdp.sxdp_flags = XDP_SHARED_UMEM; + sxdp.sxdp_shared_umem_fd = umem->fd; + } else { + sxdp.sxdp_flags = xsk->config.bind_flags; + } + + err = bind(xsk->fd, (struct sockaddr *)&sxdp, sizeof(sxdp)); + if (err) { + err = -errno; + goto out_mmap_tx; + } + + xsk->prog_fd = -1; + + if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { + err = xsk_setup_xdp_prog(xsk); + if (err) + goto out_mmap_tx; + } + + *xsk_ptr = xsk; + return 0; + +out_mmap_tx: + if (tx) + munmap(tx_map, off.tx.desc + + xsk->config.tx_size * sizeof(struct xdp_desc)); +out_mmap_rx: + if (rx) + munmap(rx_map, off.rx.desc + + xsk->config.rx_size * sizeof(struct xdp_desc)); +out_socket: + if (--umem->refcount) + close(xsk->fd); +out_xsk_alloc: + free(xsk); + return err; +} + +int xsk_umem__delete(struct xsk_umem *umem) +{ + struct xdp_mmap_offsets off; + int err; + + if (!umem) + return 0; + + if (umem->refcount) + return -EBUSY; + + err = xsk_get_mmap_offsets(umem->fd, &off); + if (!err) { + munmap(umem->fill->ring - off.fr.desc, + off.fr.desc + umem->config.fill_size * sizeof(__u64)); + munmap(umem->comp->ring - off.cr.desc, + off.cr.desc + umem->config.comp_size * sizeof(__u64)); + } + + close(umem->fd); + free(umem); + + return 0; +} + +void xsk_socket__delete(struct xsk_socket *xsk) +{ + size_t desc_sz = sizeof(struct xdp_desc); + struct xdp_mmap_offsets off; + int err; + + if (!xsk) + return; + + if (xsk->prog_fd != -1) { + xsk_delete_bpf_maps(xsk); + close(xsk->prog_fd); + } + + err = xsk_get_mmap_offsets(xsk->fd, &off); + if (!err) { + if (xsk->rx) { + munmap(xsk->rx->ring - off.rx.desc, + off.rx.desc + xsk->config.rx_size * desc_sz); + } + if (xsk->tx) { + munmap(xsk->tx->ring - off.tx.desc, + off.tx.desc + xsk->config.tx_size * desc_sz); + } + + } + + xsk->umem->refcount--; + /* Do not close an fd that also has an associated umem connected + * to it. + */ + if (xsk->fd != xsk->umem->fd) + close(xsk->fd); + free(xsk); +} diff --git a/src/contrib/libbpf/bpf/xsk.h b/src/contrib/libbpf/bpf/xsk.h new file mode 100644 index 0000000..584f682 --- /dev/null +++ b/src/contrib/libbpf/bpf/xsk.h @@ -0,0 +1,246 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * AF_XDP user-space access library. + * + * Copyright(c) 2018 - 2019 Intel Corporation. + * + * Author(s): Magnus Karlsson <magnus.karlsson@intel.com> + */ + +#ifndef __LIBBPF_XSK_H +#define __LIBBPF_XSK_H + +#include <stdio.h> +#include <stdint.h> +#include <linux/if_xdp.h> + +#include "libbpf.h" +#include "libbpf_util.h" + +#ifdef __cplusplus +extern "C" { +#endif + +/* Do not access these members directly. Use the functions below. */ +#define DEFINE_XSK_RING(name) \ +struct name { \ + __u32 cached_prod; \ + __u32 cached_cons; \ + __u32 mask; \ + __u32 size; \ + __u32 *producer; \ + __u32 *consumer; \ + void *ring; \ + __u32 *flags; \ +} + +DEFINE_XSK_RING(xsk_ring_prod); +DEFINE_XSK_RING(xsk_ring_cons); + +/* For a detailed explanation on the memory barriers associated with the + * ring, please take a look at net/xdp/xsk_queue.h. + */ + +struct xsk_umem; +struct xsk_socket; + +static inline __u64 *xsk_ring_prod__fill_addr(struct xsk_ring_prod *fill, + __u32 idx) +{ + __u64 *addrs = (__u64 *)fill->ring; + + return &addrs[idx & fill->mask]; +} + +static inline const __u64 * +xsk_ring_cons__comp_addr(const struct xsk_ring_cons *comp, __u32 idx) +{ + const __u64 *addrs = (const __u64 *)comp->ring; + + return &addrs[idx & comp->mask]; +} + +static inline struct xdp_desc *xsk_ring_prod__tx_desc(struct xsk_ring_prod *tx, + __u32 idx) +{ + struct xdp_desc *descs = (struct xdp_desc *)tx->ring; + + return &descs[idx & tx->mask]; +} + +static inline const struct xdp_desc * +xsk_ring_cons__rx_desc(const struct xsk_ring_cons *rx, __u32 idx) +{ + const struct xdp_desc *descs = (const struct xdp_desc *)rx->ring; + + return &descs[idx & rx->mask]; +} + +static inline int xsk_ring_prod__needs_wakeup(const struct xsk_ring_prod *r) +{ + return *r->flags & XDP_RING_NEED_WAKEUP; +} + +static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb) +{ + __u32 free_entries = r->cached_cons - r->cached_prod; + + if (free_entries >= nb) + return free_entries; + + /* Refresh the local tail pointer. + * cached_cons is r->size bigger than the real consumer pointer so + * that this addition can be avoided in the more frequently + * executed code that computs free_entries in the beginning of + * this function. Without this optimization it whould have been + * free_entries = r->cached_prod - r->cached_cons + r->size. + */ + r->cached_cons = *r->consumer + r->size; + + return r->cached_cons - r->cached_prod; +} + +static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb) +{ + __u32 entries = r->cached_prod - r->cached_cons; + + if (entries == 0) { + r->cached_prod = *r->producer; + entries = r->cached_prod - r->cached_cons; + } + + return (entries > nb) ? nb : entries; +} + +static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod, + size_t nb, __u32 *idx) +{ + if (xsk_prod_nb_free(prod, nb) < nb) + return 0; + + *idx = prod->cached_prod; + prod->cached_prod += nb; + + return nb; +} + +static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb) +{ + /* Make sure everything has been written to the ring before indicating + * this to the kernel by writing the producer pointer. + */ + libbpf_smp_wmb(); + + *prod->producer += nb; +} + +static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons, + size_t nb, __u32 *idx) +{ + size_t entries = xsk_cons_nb_avail(cons, nb); + + if (entries > 0) { + /* Make sure we do not speculatively read the data before + * we have received the packet buffers from the ring. + */ + libbpf_smp_rmb(); + + *idx = cons->cached_cons; + cons->cached_cons += entries; + } + + return entries; +} + +static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, size_t nb) +{ + /* Make sure data has been read before indicating we are done + * with the entries by updating the consumer pointer. + */ + libbpf_smp_rwmb(); + + *cons->consumer += nb; +} + +static inline void *xsk_umem__get_data(void *umem_area, __u64 addr) +{ + return &((char *)umem_area)[addr]; +} + +static inline __u64 xsk_umem__extract_addr(__u64 addr) +{ + return addr & XSK_UNALIGNED_BUF_ADDR_MASK; +} + +static inline __u64 xsk_umem__extract_offset(__u64 addr) +{ + return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT; +} + +static inline __u64 xsk_umem__add_offset_to_addr(__u64 addr) +{ + return xsk_umem__extract_addr(addr) + xsk_umem__extract_offset(addr); +} + +LIBBPF_API int xsk_umem__fd(const struct xsk_umem *umem); +LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk); + +#define XSK_RING_CONS__DEFAULT_NUM_DESCS 2048 +#define XSK_RING_PROD__DEFAULT_NUM_DESCS 2048 +#define XSK_UMEM__DEFAULT_FRAME_SHIFT 12 /* 4096 bytes */ +#define XSK_UMEM__DEFAULT_FRAME_SIZE (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT) +#define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0 +#define XSK_UMEM__DEFAULT_FLAGS 0 + +struct xsk_umem_config { + __u32 fill_size; + __u32 comp_size; + __u32 frame_size; + __u32 frame_headroom; + __u32 flags; +}; + +/* Flags for the libbpf_flags field. */ +#define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0) + +struct xsk_socket_config { + __u32 rx_size; + __u32 tx_size; + __u32 libbpf_flags; + __u32 xdp_flags; + __u16 bind_flags; +}; + +/* Set config to NULL to get the default configuration. */ +LIBBPF_API int xsk_umem__create(struct xsk_umem **umem, + void *umem_area, __u64 size, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *config); +LIBBPF_API int xsk_umem__create_v0_0_2(struct xsk_umem **umem, + void *umem_area, __u64 size, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *config); +LIBBPF_API int xsk_umem__create_v0_0_4(struct xsk_umem **umem, + void *umem_area, __u64 size, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *config); +LIBBPF_API int xsk_socket__create(struct xsk_socket **xsk, + const char *ifname, __u32 queue_id, + struct xsk_umem *umem, + struct xsk_ring_cons *rx, + struct xsk_ring_prod *tx, + const struct xsk_socket_config *config); + +/* Returns 0 for success and -EBUSY if the umem is still in use. */ +LIBBPF_API int xsk_umem__delete(struct xsk_umem *umem); +LIBBPF_API void xsk_socket__delete(struct xsk_socket *xsk); + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* __LIBBPF_XSK_H */ diff --git a/src/contrib/libbpf/include/asm/barrier.h b/src/contrib/libbpf/include/asm/barrier.h new file mode 100644 index 0000000..1fc6aee --- /dev/null +++ b/src/contrib/libbpf/include/asm/barrier.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __ASM_BARRIER_H +#define __ASM_BARRIER_H + +#include <linux/compiler.h> + +#endif diff --git a/src/contrib/libbpf/include/linux/compiler.h b/src/contrib/libbpf/include/linux/compiler.h new file mode 100644 index 0000000..26336dc --- /dev/null +++ b/src/contrib/libbpf/include/linux/compiler.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LINUX_COMPILER_H +#define __LINUX_COMPILER_H + +#define likely(x) __builtin_expect(!!(x), 1) +#define unlikely(x) __builtin_expect(!!(x), 0) + +#define READ_ONCE(x) (*(volatile typeof(x) *)&x) +#define WRITE_ONCE(x, v) (*(volatile typeof(x) *)&x) = (v) + +#define barrier() asm volatile("" ::: "memory") + +#if defined(__x86_64__) + +# define smp_rmb() barrier() +# define smp_wmb() barrier() +# define smp_mb() asm volatile("lock; addl $0,-132(%%rsp)" ::: "memory", "cc") + +# define smp_store_release(p, v) \ +do { \ + barrier(); \ + WRITE_ONCE(*p, v); \ +} while (0) + +# define smp_load_acquire(p) \ +({ \ + typeof(*p) ___p = READ_ONCE(*p); \ + barrier(); \ + ___p; \ +}) + +#elif defined(__aarch64__) + +# define smp_rmb() asm volatile("dmb ishld" ::: "memory") +# define smp_wmb() asm volatile("dmb ishst" ::: "memory") +# define smp_mb() asm volatile("dmb ish" ::: "memory") + +#endif + +#ifndef smp_mb +# define smp_mb() __sync_synchronize() +#endif + +#ifndef smp_rmb +# define smp_rmb() smp_mb() +#endif + +#ifndef smp_wmb +# define smp_wmb() smp_mb() +#endif + +#ifndef smp_store_release +# define smp_store_release(p, v) \ +do { \ + smp_mb(); \ + WRITE_ONCE(*p, v); \ +} while (0) +#endif + +#ifndef smp_load_acquire +# define smp_load_acquire(p) \ +({ \ + typeof(*p) ___p = READ_ONCE(*p); \ + smp_mb(); \ + ___p; \ +}) +#endif + +#endif /* __LINUX_COMPILER_H */ diff --git a/src/contrib/libbpf/include/linux/err.h b/src/contrib/libbpf/include/linux/err.h new file mode 100644 index 0000000..1b1dafb --- /dev/null +++ b/src/contrib/libbpf/include/linux/err.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LINUX_ERR_H +#define __LINUX_ERR_H + +#include <linux/types.h> +#include <asm/errno.h> + +#define MAX_ERRNO 4095 + +#define IS_ERR_VALUE(x) ((x) >= (unsigned long)-MAX_ERRNO) + +static inline void * ERR_PTR(long error_) +{ + return (void *) error_; +} + +static inline long PTR_ERR(const void *ptr) +{ + return (long) ptr; +} + +static inline bool IS_ERR(const void *ptr) +{ + return IS_ERR_VALUE((unsigned long)ptr); +} + +static inline bool IS_ERR_OR_NULL(const void *ptr) +{ + return (!ptr) || IS_ERR_VALUE((unsigned long)ptr); +} + +static inline long PTR_ERR_OR_ZERO(const void *ptr) +{ + return IS_ERR(ptr) ? PTR_ERR(ptr) : 0; +} + +#endif diff --git a/src/contrib/libbpf/include/linux/filter.h b/src/contrib/libbpf/include/linux/filter.h new file mode 100644 index 0000000..b0700e2 --- /dev/null +++ b/src/contrib/libbpf/include/linux/filter.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LINUX_FILTER_H +#define __LINUX_FILTER_H + +#include <linux/bpf.h> + +#define BPF_ALU64_IMM(OP, DST, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +#define BPF_MOV64_IMM(DST, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +#define BPF_EXIT_INSN() \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_EXIT, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = 0 }) + +#define BPF_EMIT_CALL(FUNC) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_CALL, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = ((FUNC) - BPF_FUNC_unspec) }) + +#define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +#define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + +#define BPF_MOV64_REG(DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = 0, \ + .imm = 0 }) + +#define BPF_MOV32_IMM(DST, IMM) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_MOV | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = IMM }) + +#define BPF_LD_IMM64_RAW_FULL(DST, SRC, OFF1, OFF2, IMM1, IMM2) \ + ((struct bpf_insn) { \ + .code = BPF_LD | BPF_DW | BPF_IMM, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF1, \ + .imm = IMM1 }), \ + ((struct bpf_insn) { \ + .code = 0, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = OFF2, \ + .imm = IMM2 }) + +#define BPF_LD_MAP_FD(DST, MAP_FD) \ + BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_FD, 0, 0, \ + MAP_FD, 0) + +#define BPF_LD_MAP_VALUE(DST, MAP_FD, VALUE_OFF) \ + BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_VALUE, 0, 0, \ + MAP_FD, VALUE_OFF) + +#define BPF_JMP_IMM(OP, DST, IMM, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + +#define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + +#endif diff --git a/src/contrib/libbpf/include/linux/kernel.h b/src/contrib/libbpf/include/linux/kernel.h new file mode 100644 index 0000000..a4a7a9d --- /dev/null +++ b/src/contrib/libbpf/include/linux/kernel.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LINUX_KERNEL_H +#define __LINUX_KERNEL_H + +#ifndef offsetof +#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) +#endif + +#ifndef container_of +#define container_of(ptr, type, member) ({ \ + const typeof(((type *)0)->member) * __mptr = (ptr); \ + (type *)((char *)__mptr - offsetof(type, member)); }) +#endif + +#ifndef max +#define max(x, y) ({ \ + typeof(x) _max1 = (x); \ + typeof(y) _max2 = (y); \ + (void) (&_max1 == &_max2); \ + _max1 > _max2 ? _max1 : _max2; }) +#endif + +#ifndef min +#define min(x, y) ({ \ + typeof(x) _min1 = (x); \ + typeof(y) _min2 = (y); \ + (void) (&_min1 == &_min2); \ + _min1 < _min2 ? _min1 : _min2; }) +#endif + +#ifndef roundup +#define roundup(x, y) ( \ +{ \ + const typeof(y) __y = y; \ + (((x) + (__y - 1)) / __y) * __y; \ +} \ +) +#endif + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) +#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) + +#endif diff --git a/src/contrib/libbpf/include/linux/list.h b/src/contrib/libbpf/include/linux/list.h new file mode 100644 index 0000000..e3814f7 --- /dev/null +++ b/src/contrib/libbpf/include/linux/list.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LINUX_LIST_H +#define __LINUX_LIST_H + +#define LIST_HEAD_INIT(name) { &(name), &(name) } +#define LIST_HEAD(name) \ + struct list_head name = LIST_HEAD_INIT(name) + +#define POISON_POINTER_DELTA 0 +#define LIST_POISON1 ((void *) 0x100 + POISON_POINTER_DELTA) +#define LIST_POISON2 ((void *) 0x200 + POISON_POINTER_DELTA) + + +static inline void INIT_LIST_HEAD(struct list_head *list) +{ + list->next = list; + list->prev = list; +} + +static inline void __list_add(struct list_head *new, + struct list_head *prev, + struct list_head *next) +{ + next->prev = new; + new->next = next; + new->prev = prev; + prev->next = new; +} + +/** + * list_add - add a new entry + * @new: new entry to be added + * @head: list head to add it after + * + * Insert a new entry after the specified head. + * This is good for implementing stacks. + */ +static inline void list_add(struct list_head *new, struct list_head *head) +{ + __list_add(new, head, head->next); +} + +/* + * Delete a list entry by making the prev/next entries + * point to each other. + * + * This is only for internal list manipulation where we know + * the prev/next entries already! + */ +static inline void __list_del(struct list_head * prev, struct list_head * next) +{ + next->prev = prev; + prev->next = next; +} + +/** + * list_del - deletes entry from list. + * @entry: the element to delete from the list. + * Note: list_empty() on entry does not return true after this, the entry is + * in an undefined state. + */ +static inline void __list_del_entry(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); +} + +static inline void list_del(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); + entry->next = LIST_POISON1; + entry->prev = LIST_POISON2; +} + +#define list_entry(ptr, type, member) \ + container_of(ptr, type, member) +#define list_first_entry(ptr, type, member) \ + list_entry((ptr)->next, type, member) +#define list_next_entry(pos, member) \ + list_entry((pos)->member.next, typeof(*(pos)), member) + +#endif diff --git a/src/contrib/libbpf/include/linux/overflow.h b/src/contrib/libbpf/include/linux/overflow.h new file mode 100644 index 0000000..53d7580 --- /dev/null +++ b/src/contrib/libbpf/include/linux/overflow.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LINUX_OVERFLOW_H +#define __LINUX_OVERFLOW_H + +#define is_signed_type(type) (((type)(-1)) < (type)1) +#define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type))) +#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) +#define type_min(T) ((T)((T)-type_max(T)-(T)1)) + +#ifndef unlikely +#define unlikely(x) __builtin_expect(!!(x), 0) +#endif + +#ifdef __GNUC__ +#define GCC_VERSION (__GNUC__ * 10000 \ + + __GNUC_MINOR__ * 100 \ + + __GNUC_PATCHLEVEL__) +#if GCC_VERSION >= 50100 +#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 +#endif +#endif + +#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW + +#define check_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + __builtin_mul_overflow(__a, __b, __d); \ +}) + +#else + +/* + * If one of a or b is a compile-time constant, this avoids a division. + */ +#define __unsigned_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = __a * __b; \ + __builtin_constant_p(__b) ? \ + __b > 0 && __a > type_max(typeof(__a)) / __b : \ + __a > 0 && __b > type_max(typeof(__b)) / __a; \ +}) + +/* + * Signed multiplication is rather hard. gcc always follows C99, so + * division is truncated towards 0. This means that we can write the + * overflow check like this: + * + * (a > 0 && (b > MAX/a || b < MIN/a)) || + * (a < -1 && (b > MIN/a || b < MAX/a) || + * (a == -1 && b == MIN) + * + * The redundant casts of -1 are to silence an annoying -Wtype-limits + * (included in -Wextra) warning: When the type is u8 or u16, the + * __b_c_e in check_mul_overflow obviously selects + * __unsigned_mul_overflow, but unfortunately gcc still parses this + * code and warns about the limited range of __b. + */ + +#define __signed_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + typeof(a) __tmax = type_max(typeof(a)); \ + typeof(a) __tmin = type_min(typeof(a)); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = (__u64)__a * (__u64)__b; \ + (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ + (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ + (__b == (typeof(__b))-1 && __a == __tmin); \ +}) + +#define check_mul_overflow(a, b, d) \ + __builtin_choose_expr(is_signed_type(typeof(a)), \ + __signed_mul_overflow(a, b, d), \ + __unsigned_mul_overflow(a, b, d)) + + +#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ + +#endif diff --git a/src/contrib/libbpf/include/linux/ring_buffer.h b/src/contrib/libbpf/include/linux/ring_buffer.h new file mode 100644 index 0000000..fc4677b --- /dev/null +++ b/src/contrib/libbpf/include/linux/ring_buffer.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef _TOOLS_LINUX_RING_BUFFER_H_ +#define _TOOLS_LINUX_RING_BUFFER_H_ + +#include <linux/compiler.h> + +static inline __u64 ring_buffer_read_head(struct perf_event_mmap_page *base) +{ + return smp_load_acquire(&base->data_head); +} + +static inline void ring_buffer_write_tail(struct perf_event_mmap_page *base, + __u64 tail) +{ + smp_store_release(&base->data_tail, tail); +} + +#endif /* _TOOLS_LINUX_RING_BUFFER_H_ */ diff --git a/src/contrib/libbpf/include/linux/types.h b/src/contrib/libbpf/include/linux/types.h new file mode 100644 index 0000000..bae1ed8 --- /dev/null +++ b/src/contrib/libbpf/include/linux/types.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LINUX_TYPES_H +#define __LINUX_TYPES_H + +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> + +#include <asm/types.h> +#include <asm/posix_types.h> + +#define __bitwise__ +#define __bitwise __bitwise__ + +typedef __u16 __bitwise __le16; +typedef __u16 __bitwise __be16; +typedef __u32 __bitwise __le32; +typedef __u32 __bitwise __be32; +typedef __u64 __bitwise __le64; +typedef __u64 __bitwise __be64; + +#ifndef __aligned_u64 +# define __aligned_u64 __u64 __attribute__((aligned(8))) +#endif + +struct list_head { + struct list_head *next, *prev; +}; + +#endif diff --git a/src/contrib/libbpf/include/uapi/linux/bpf.h b/src/contrib/libbpf/include/uapi/linux/bpf.h new file mode 100644 index 0000000..dbbcf0b --- /dev/null +++ b/src/contrib/libbpf/include/uapi/linux/bpf.h @@ -0,0 +1,3692 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef _UAPI__LINUX_BPF_H__ +#define _UAPI__LINUX_BPF_H__ + +#include <linux/types.h> +#include <linux/bpf_common.h> + +/* Extended instruction set based on top of classic BPF */ + +/* instruction classes */ +#define BPF_JMP32 0x06 /* jmp mode in word width */ +#define BPF_ALU64 0x07 /* alu mode in double word width */ + +/* ld/ldx fields */ +#define BPF_DW 0x18 /* double word (64-bit) */ +#define BPF_XADD 0xc0 /* exclusive add */ + +/* alu/jmp fields */ +#define BPF_MOV 0xb0 /* mov reg to reg */ +#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */ + +/* change endianness of a register */ +#define BPF_END 0xd0 /* flags for endianness conversion: */ +#define BPF_TO_LE 0x00 /* convert to little-endian */ +#define BPF_TO_BE 0x08 /* convert to big-endian */ +#define BPF_FROM_LE BPF_TO_LE +#define BPF_FROM_BE BPF_TO_BE + +/* jmp encodings */ +#define BPF_JNE 0x50 /* jump != */ +#define BPF_JLT 0xa0 /* LT is unsigned, '<' */ +#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */ +#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ +#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ +#define BPF_JSLT 0xc0 /* SLT is signed, '<' */ +#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ +#define BPF_CALL 0x80 /* function call */ +#define BPF_EXIT 0x90 /* function return */ + +/* Register numbers */ +enum { + BPF_REG_0 = 0, + BPF_REG_1, + BPF_REG_2, + BPF_REG_3, + BPF_REG_4, + BPF_REG_5, + BPF_REG_6, + BPF_REG_7, + BPF_REG_8, + BPF_REG_9, + BPF_REG_10, + __MAX_BPF_REG, +}; + +/* BPF has 10 general purpose 64-bit registers and stack frame. */ +#define MAX_BPF_REG __MAX_BPF_REG + +struct bpf_insn { + __u8 code; /* opcode */ + __u8 dst_reg:4; /* dest register */ + __u8 src_reg:4; /* source register */ + __s16 off; /* signed offset */ + __s32 imm; /* signed immediate constant */ +}; + +/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ +struct bpf_lpm_trie_key { + __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ + __u8 data[0]; /* Arbitrary size */ +}; + +struct bpf_cgroup_storage_key { + __u64 cgroup_inode_id; /* cgroup inode id */ + __u32 attach_type; /* program attach type */ +}; + +/* BPF syscall commands, see bpf(2) man-page for details. */ +enum bpf_cmd { + BPF_MAP_CREATE, + BPF_MAP_LOOKUP_ELEM, + BPF_MAP_UPDATE_ELEM, + BPF_MAP_DELETE_ELEM, + BPF_MAP_GET_NEXT_KEY, + BPF_PROG_LOAD, + BPF_OBJ_PIN, + BPF_OBJ_GET, + BPF_PROG_ATTACH, + BPF_PROG_DETACH, + BPF_PROG_TEST_RUN, + BPF_PROG_GET_NEXT_ID, + BPF_MAP_GET_NEXT_ID, + BPF_PROG_GET_FD_BY_ID, + BPF_MAP_GET_FD_BY_ID, + BPF_OBJ_GET_INFO_BY_FD, + BPF_PROG_QUERY, + BPF_RAW_TRACEPOINT_OPEN, + BPF_BTF_LOAD, + BPF_BTF_GET_FD_BY_ID, + BPF_TASK_FD_QUERY, + BPF_MAP_LOOKUP_AND_DELETE_ELEM, + BPF_MAP_FREEZE, + BPF_BTF_GET_NEXT_ID, +}; + +enum bpf_map_type { + BPF_MAP_TYPE_UNSPEC, + BPF_MAP_TYPE_HASH, + BPF_MAP_TYPE_ARRAY, + BPF_MAP_TYPE_PROG_ARRAY, + BPF_MAP_TYPE_PERF_EVENT_ARRAY, + BPF_MAP_TYPE_PERCPU_HASH, + BPF_MAP_TYPE_PERCPU_ARRAY, + BPF_MAP_TYPE_STACK_TRACE, + BPF_MAP_TYPE_CGROUP_ARRAY, + BPF_MAP_TYPE_LRU_HASH, + BPF_MAP_TYPE_LRU_PERCPU_HASH, + BPF_MAP_TYPE_LPM_TRIE, + BPF_MAP_TYPE_ARRAY_OF_MAPS, + BPF_MAP_TYPE_HASH_OF_MAPS, + BPF_MAP_TYPE_DEVMAP, + BPF_MAP_TYPE_SOCKMAP, + BPF_MAP_TYPE_CPUMAP, + BPF_MAP_TYPE_XSKMAP, + BPF_MAP_TYPE_SOCKHASH, + BPF_MAP_TYPE_CGROUP_STORAGE, + BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + BPF_MAP_TYPE_QUEUE, + BPF_MAP_TYPE_STACK, + BPF_MAP_TYPE_SK_STORAGE, + BPF_MAP_TYPE_DEVMAP_HASH, +}; + +/* Note that tracing related programs such as + * BPF_PROG_TYPE_{KPROBE,TRACEPOINT,PERF_EVENT,RAW_TRACEPOINT} + * are not subject to a stable API since kernel internal data + * structures can change from release to release and may + * therefore break existing tracing BPF programs. Tracing BPF + * programs correspond to /a/ specific kernel which is to be + * analyzed, and not /a/ specific kernel /and/ all future ones. + */ +enum bpf_prog_type { + BPF_PROG_TYPE_UNSPEC, + BPF_PROG_TYPE_SOCKET_FILTER, + BPF_PROG_TYPE_KPROBE, + BPF_PROG_TYPE_SCHED_CLS, + BPF_PROG_TYPE_SCHED_ACT, + BPF_PROG_TYPE_TRACEPOINT, + BPF_PROG_TYPE_XDP, + BPF_PROG_TYPE_PERF_EVENT, + BPF_PROG_TYPE_CGROUP_SKB, + BPF_PROG_TYPE_CGROUP_SOCK, + BPF_PROG_TYPE_LWT_IN, + BPF_PROG_TYPE_LWT_OUT, + BPF_PROG_TYPE_LWT_XMIT, + BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_CGROUP_DEVICE, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_RAW_TRACEPOINT, + BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_PROG_TYPE_LWT_SEG6LOCAL, + BPF_PROG_TYPE_LIRC_MODE2, + BPF_PROG_TYPE_SK_REUSEPORT, + BPF_PROG_TYPE_FLOW_DISSECTOR, + BPF_PROG_TYPE_CGROUP_SYSCTL, + BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + BPF_PROG_TYPE_CGROUP_SOCKOPT, + BPF_PROG_TYPE_TRACING, +}; + +enum bpf_attach_type { + BPF_CGROUP_INET_INGRESS, + BPF_CGROUP_INET_EGRESS, + BPF_CGROUP_INET_SOCK_CREATE, + BPF_CGROUP_SOCK_OPS, + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_DEVICE, + BPF_SK_MSG_VERDICT, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET4_POST_BIND, + BPF_CGROUP_INET6_POST_BIND, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + BPF_LIRC_MODE2, + BPF_FLOW_DISSECTOR, + BPF_CGROUP_SYSCTL, + BPF_CGROUP_UDP4_RECVMSG, + BPF_CGROUP_UDP6_RECVMSG, + BPF_CGROUP_GETSOCKOPT, + BPF_CGROUP_SETSOCKOPT, + BPF_TRACE_RAW_TP, + BPF_TRACE_FENTRY, + BPF_TRACE_FEXIT, + __MAX_BPF_ATTACH_TYPE +}; + +#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE + +/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command + * + * NONE(default): No further bpf programs allowed in the subtree. + * + * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, + * the program in this cgroup yields to sub-cgroup program. + * + * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, + * that cgroup program gets run in addition to the program in this cgroup. + * + * Only one program is allowed to be attached to a cgroup with + * NONE or BPF_F_ALLOW_OVERRIDE flag. + * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will + * release old program and attach the new one. Attach flags has to match. + * + * Multiple programs are allowed to be attached to a cgroup with + * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order + * (those that were attached first, run first) + * The programs of sub-cgroup are executed first, then programs of + * this cgroup and then programs of parent cgroup. + * When children program makes decision (like picking TCP CA or sock bind) + * parent program has a chance to override it. + * + * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups. + * A cgroup with NONE doesn't allow any programs in sub-cgroups. + * Ex1: + * cgrp1 (MULTI progs A, B) -> + * cgrp2 (OVERRIDE prog C) -> + * cgrp3 (MULTI prog D) -> + * cgrp4 (OVERRIDE prog E) -> + * cgrp5 (NONE prog F) + * the event in cgrp5 triggers execution of F,D,A,B in that order. + * if prog F is detached, the execution is E,D,A,B + * if prog F and D are detached, the execution is E,A,B + * if prog F, E and D are detached, the execution is C,A,B + * + * All eligible programs are executed regardless of return code from + * earlier programs. + */ +#define BPF_F_ALLOW_OVERRIDE (1U << 0) +#define BPF_F_ALLOW_MULTI (1U << 1) + +/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the + * verifier will perform strict alignment checking as if the kernel + * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set, + * and NET_IP_ALIGN defined to 2. + */ +#define BPF_F_STRICT_ALIGNMENT (1U << 0) + +/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROF_LOAD command, the + * verifier will allow any alignment whatsoever. On platforms + * with strict alignment requirements for loads ands stores (such + * as sparc and mips) the verifier validates that all loads and + * stores provably follow this requirement. This flag turns that + * checking and enforcement off. + * + * It is mostly used for testing when we want to validate the + * context and memory access aspects of the verifier, but because + * of an unaligned access the alignment check would trigger before + * the one we are interested in. + */ +#define BPF_F_ANY_ALIGNMENT (1U << 1) + +/* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose. + * Verifier does sub-register def/use analysis and identifies instructions whose + * def only matters for low 32-bit, high 32-bit is never referenced later + * through implicit zero extension. Therefore verifier notifies JIT back-ends + * that it is safe to ignore clearing high 32-bit for these instructions. This + * saves some back-ends a lot of code-gen. However such optimization is not + * necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends + * hence hasn't used verifier's analysis result. But, we really want to have a + * way to be able to verify the correctness of the described optimization on + * x86_64 on which testsuites are frequently exercised. + * + * So, this flag is introduced. Once it is set, verifier will randomize high + * 32-bit for those instructions who has been identified as safe to ignore them. + * Then, if verifier is not doing correct analysis, such randomization will + * regress tests to expose bugs. + */ +#define BPF_F_TEST_RND_HI32 (1U << 2) + +/* The verifier internal test flag. Behavior is undefined */ +#define BPF_F_TEST_STATE_FREQ (1U << 3) + +/* When BPF ldimm64's insn[0].src_reg != 0 then this can have + * two extensions: + * + * insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE + * insn[0].imm: map fd map fd + * insn[1].imm: 0 offset into value + * insn[0].off: 0 0 + * insn[1].off: 0 0 + * ldimm64 rewrite: address of map address of map[0]+offset + * verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE + */ +#define BPF_PSEUDO_MAP_FD 1 +#define BPF_PSEUDO_MAP_VALUE 2 + +/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative + * offset to another bpf function + */ +#define BPF_PSEUDO_CALL 1 + +/* flags for BPF_MAP_UPDATE_ELEM command */ +#define BPF_ANY 0 /* create new element or update existing */ +#define BPF_NOEXIST 1 /* create new element if it didn't exist */ +#define BPF_EXIST 2 /* update existing element */ +#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */ + +/* flags for BPF_MAP_CREATE command */ +#define BPF_F_NO_PREALLOC (1U << 0) +/* Instead of having one common LRU list in the + * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list + * which can scale and perform better. + * Note, the LRU nodes (including free nodes) cannot be moved + * across different LRU lists. + */ +#define BPF_F_NO_COMMON_LRU (1U << 1) +/* Specify numa node during map creation */ +#define BPF_F_NUMA_NODE (1U << 2) + +#define BPF_OBJ_NAME_LEN 16U + +/* Flags for accessing BPF object from syscall side. */ +#define BPF_F_RDONLY (1U << 3) +#define BPF_F_WRONLY (1U << 4) + +/* Flag for stack_map, store build_id+offset instead of pointer */ +#define BPF_F_STACK_BUILD_ID (1U << 5) + +/* Zero-initialize hash function seed. This should only be used for testing. */ +#define BPF_F_ZERO_SEED (1U << 6) + +/* Flags for accessing BPF object from program side. */ +#define BPF_F_RDONLY_PROG (1U << 7) +#define BPF_F_WRONLY_PROG (1U << 8) + +/* Clone map from listener for newly accepted socket */ +#define BPF_F_CLONE (1U << 9) + +/* Enable memory-mapping BPF map */ +#define BPF_F_MMAPABLE (1U << 10) + +/* flags for BPF_PROG_QUERY */ +#define BPF_F_QUERY_EFFECTIVE (1U << 0) + +enum bpf_stack_build_id_status { + /* user space need an empty entry to identify end of a trace */ + BPF_STACK_BUILD_ID_EMPTY = 0, + /* with valid build_id and offset */ + BPF_STACK_BUILD_ID_VALID = 1, + /* couldn't get build_id, fallback to ip */ + BPF_STACK_BUILD_ID_IP = 2, +}; + +#define BPF_BUILD_ID_SIZE 20 +struct bpf_stack_build_id { + __s32 status; + unsigned char build_id[BPF_BUILD_ID_SIZE]; + union { + __u64 offset; + __u64 ip; + }; +}; + +union bpf_attr { + struct { /* anonymous struct used by BPF_MAP_CREATE command */ + __u32 map_type; /* one of enum bpf_map_type */ + __u32 key_size; /* size of key in bytes */ + __u32 value_size; /* size of value in bytes */ + __u32 max_entries; /* max number of entries in a map */ + __u32 map_flags; /* BPF_MAP_CREATE related + * flags defined above. + */ + __u32 inner_map_fd; /* fd pointing to the inner map */ + __u32 numa_node; /* numa node (effective only if + * BPF_F_NUMA_NODE is set). + */ + char map_name[BPF_OBJ_NAME_LEN]; + __u32 map_ifindex; /* ifindex of netdev to create on */ + __u32 btf_fd; /* fd pointing to a BTF type data */ + __u32 btf_key_type_id; /* BTF type_id of the key */ + __u32 btf_value_type_id; /* BTF type_id of the value */ + }; + + struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ + __u32 map_fd; + __aligned_u64 key; + union { + __aligned_u64 value; + __aligned_u64 next_key; + }; + __u64 flags; + }; + + struct { /* anonymous struct used by BPF_PROG_LOAD command */ + __u32 prog_type; /* one of enum bpf_prog_type */ + __u32 insn_cnt; + __aligned_u64 insns; + __aligned_u64 license; + __u32 log_level; /* verbosity level of verifier */ + __u32 log_size; /* size of user buffer */ + __aligned_u64 log_buf; /* user supplied buffer */ + __u32 kern_version; /* not used */ + __u32 prog_flags; + char prog_name[BPF_OBJ_NAME_LEN]; + __u32 prog_ifindex; /* ifindex of netdev to prep for */ + /* For some prog types expected attach type must be known at + * load time to verify attach type specific parts of prog + * (context accesses, allowed helpers, etc). + */ + __u32 expected_attach_type; + __u32 prog_btf_fd; /* fd pointing to BTF type data */ + __u32 func_info_rec_size; /* userspace bpf_func_info size */ + __aligned_u64 func_info; /* func info */ + __u32 func_info_cnt; /* number of bpf_func_info records */ + __u32 line_info_rec_size; /* userspace bpf_line_info size */ + __aligned_u64 line_info; /* line info */ + __u32 line_info_cnt; /* number of bpf_line_info records */ + __u32 attach_btf_id; /* in-kernel BTF type id to attach to */ + __u32 attach_prog_fd; /* 0 to attach to vmlinux */ + }; + + struct { /* anonymous struct used by BPF_OBJ_* commands */ + __aligned_u64 pathname; + __u32 bpf_fd; + __u32 file_flags; + }; + + struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ + __u32 target_fd; /* container object to attach to */ + __u32 attach_bpf_fd; /* eBPF program to attach */ + __u32 attach_type; + __u32 attach_flags; + }; + + struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ + __u32 prog_fd; + __u32 retval; + __u32 data_size_in; /* input: len of data_in */ + __u32 data_size_out; /* input/output: len of data_out + * returns ENOSPC if data_out + * is too small. + */ + __aligned_u64 data_in; + __aligned_u64 data_out; + __u32 repeat; + __u32 duration; + __u32 ctx_size_in; /* input: len of ctx_in */ + __u32 ctx_size_out; /* input/output: len of ctx_out + * returns ENOSPC if ctx_out + * is too small. + */ + __aligned_u64 ctx_in; + __aligned_u64 ctx_out; + } test; + + struct { /* anonymous struct used by BPF_*_GET_*_ID */ + union { + __u32 start_id; + __u32 prog_id; + __u32 map_id; + __u32 btf_id; + }; + __u32 next_id; + __u32 open_flags; + }; + + struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ + __u32 bpf_fd; + __u32 info_len; + __aligned_u64 info; + } info; + + struct { /* anonymous struct used by BPF_PROG_QUERY command */ + __u32 target_fd; /* container object to query */ + __u32 attach_type; + __u32 query_flags; + __u32 attach_flags; + __aligned_u64 prog_ids; + __u32 prog_cnt; + } query; + + struct { + __u64 name; + __u32 prog_fd; + } raw_tracepoint; + + struct { /* anonymous struct for BPF_BTF_LOAD */ + __aligned_u64 btf; + __aligned_u64 btf_log_buf; + __u32 btf_size; + __u32 btf_log_size; + __u32 btf_log_level; + }; + + struct { + __u32 pid; /* input: pid */ + __u32 fd; /* input: fd */ + __u32 flags; /* input: flags */ + __u32 buf_len; /* input/output: buf len */ + __aligned_u64 buf; /* input/output: + * tp_name for tracepoint + * symbol for kprobe + * filename for uprobe + */ + __u32 prog_id; /* output: prod_id */ + __u32 fd_type; /* output: BPF_FD_TYPE_* */ + __u64 probe_offset; /* output: probe_offset */ + __u64 probe_addr; /* output: probe_addr */ + } task_fd_query; +} __attribute__((aligned(8))); + +/* The description below is an attempt at providing documentation to eBPF + * developers about the multiple available eBPF helper functions. It can be + * parsed and used to produce a manual page. The workflow is the following, + * and requires the rst2man utility: + * + * $ ./scripts/bpf_helpers_doc.py \ + * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst + * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7 + * $ man /tmp/bpf-helpers.7 + * + * Note that in order to produce this external documentation, some RST + * formatting is used in the descriptions to get "bold" and "italics" in + * manual pages. Also note that the few trailing white spaces are + * intentional, removing them would break paragraphs for rst2man. + * + * Start of BPF helper function descriptions: + * + * void *bpf_map_lookup_elem(struct bpf_map *map, const void *key) + * Description + * Perform a lookup in *map* for an entry associated to *key*. + * Return + * Map value associated to *key*, or **NULL** if no entry was + * found. + * + * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) + * Description + * Add or update the value of the entry associated to *key* in + * *map* with *value*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * Flag value **BPF_NOEXIST** cannot be used for maps of types + * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all + * elements always exist), the helper would return an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_delete_elem(struct bpf_map *map, const void *key) + * Description + * Delete entry with *key* from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr) + * Description + * For tracing programs, safely attempt to read *size* bytes from + * kernel space address *unsafe_ptr* and store the data in *dst*. + * + * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel() + * instead. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_ktime_get_ns(void) + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Return + * Current *ktime*. + * + * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...) + * Description + * This helper is a "printk()-like" facility for debugging. It + * prints a message defined by format *fmt* (of size *fmt_size*) + * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if + * available. It can take up to three additional **u64** + * arguments (as an eBPF helpers, the total number of arguments is + * limited to five). + * + * Each time the helper is called, it appends a line to the trace. + * Lines are discarded while *\/sys/kernel/debug/tracing/trace* is + * open, use *\/sys/kernel/debug/tracing/trace_pipe* to avoid this. + * The format of the trace is customizable, and the exact output + * one will get depends on the options set in + * *\/sys/kernel/debug/tracing/trace_options* (see also the + * *README* file under the same directory). However, it usually + * defaults to something like: + * + * :: + * + * telnet-470 [001] .N.. 419421.045894: 0x00000001: <formatted msg> + * + * In the above: + * + * * ``telnet`` is the name of the current task. + * * ``470`` is the PID of the current task. + * * ``001`` is the CPU number on which the task is + * running. + * * In ``.N..``, each character refers to a set of + * options (whether irqs are enabled, scheduling + * options, whether hard/softirqs are running, level of + * preempt_disabled respectively). **N** means that + * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED** + * are set. + * * ``419421.045894`` is a timestamp. + * * ``0x00000001`` is a fake value used by BPF for the + * instruction pointer register. + * * ``<formatted msg>`` is the message formatted with + * *fmt*. + * + * The conversion specifiers supported by *fmt* are similar, but + * more limited than for printk(). They are **%d**, **%i**, + * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**, + * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size + * of field, padding with zeroes, etc.) is available, and the + * helper will return **-EINVAL** (but print nothing) if it + * encounters an unknown specifier. + * + * Also, note that **bpf_trace_printk**\ () is slow, and should + * only be used for debugging purposes. For this reason, a notice + * bloc (spanning several lines) is printed to kernel logs and + * states that the helper should not be used "for production use" + * the first time this helper is used (or more precisely, when + * **trace_printk**\ () buffers are allocated). For passing values + * to user space, perf events should be preferred. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. + * + * u32 bpf_get_prandom_u32(void) + * Description + * Get a pseudo-random number. + * + * From a security point of view, this helper uses its own + * pseudo-random internal state, and cannot be used to infer the + * seed of other random functions in the kernel. However, it is + * essential to note that the generator used by the helper is not + * cryptographically secure. + * Return + * A random 32-bit unsigned value. + * + * u32 bpf_get_smp_processor_id(void) + * Description + * Get the SMP (symmetric multiprocessing) processor id. Note that + * all programs run with preemption disabled, which means that the + * SMP processor id is stable during all the execution of the + * program. + * Return + * The SMP id of the processor running the program. + * + * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. *flags* are a combination of + * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the + * checksum for the packet after storing the bytes) and + * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ + * **->swhash** and *skb*\ **->l4hash** to 0). + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size) + * Description + * Recompute the layer 3 (e.g. IP) checksum for the packet + * associated to *skb*. Computation is incremental, so the helper + * must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored in *size*. + * Alternatively, it is possible to store the difference between + * the previous and the new values of the header field in *to*, by + * setting *from* and *size* to 0. For both methods, *offset* + * indicates the location of the IP checksum within the packet. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags) + * Description + * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the + * packet associated to *skb*. Computation is incremental, so the + * helper must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored on the lowest + * four bits of *flags*. Alternatively, it is possible to store + * the difference between the previous and the new values of the + * header field in *to*, by setting *from* and the four lowest + * bits of *flags* to 0. For both methods, *offset* indicates the + * location of the IP checksum within the packet. In addition to + * the size of the field, *flags* can be added (bitwise OR) actual + * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left + * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and + * for updates resulting in a null checksum the value is set to + * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates + * the checksum is to be computed against a pseudo-header. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index) + * Description + * This special helper is used to trigger a "tail call", or in + * other words, to jump into another eBPF program. The same stack + * frame is used (but values on stack and in registers for the + * caller are not accessible to the callee). This mechanism allows + * for program chaining, either for raising the maximum number of + * available eBPF instructions, or to execute given programs in + * conditional blocks. For security reasons, there is an upper + * limit to the number of successive tail calls that can be + * performed. + * + * Upon call of this helper, the program attempts to jump into a + * program referenced at index *index* in *prog_array_map*, a + * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes + * *ctx*, a pointer to the context. + * + * If the call succeeds, the kernel immediately runs the first + * instruction of the new program. This is not a function call, + * and it never returns to the previous program. If the call + * fails, then the helper has no effect, and the caller continues + * to run its subsequent instructions. A call can fail if the + * destination program for the jump does not exist (i.e. *index* + * is superior to the number of entries in *prog_array_map*), or + * if the maximum number of tail calls has been reached for this + * chain of programs. This limit is defined in the kernel by the + * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), + * which is currently set to 32. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags) + * Description + * Clone and redirect the packet associated to *skb* to another + * net device of index *ifindex*. Both ingress and egress + * interfaces can be used for redirection. The **BPF_F_INGRESS** + * value in *flags* is used to make the distinction (ingress path + * is selected if the flag is present, egress path otherwise). + * This is the only flag supported for now. + * + * In comparison with **bpf_redirect**\ () helper, + * **bpf_clone_redirect**\ () has the associated cost of + * duplicating the packet buffer, but this can be executed out of + * the eBPF program. Conversely, **bpf_redirect**\ () is more + * efficient, but it is handled through an action code where the + * redirection happens only after the eBPF program has returned. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_get_current_pid_tgid(void) + * Return + * A 64-bit integer containing the current tgid and pid, and + * created as such: + * *current_task*\ **->tgid << 32 \|** + * *current_task*\ **->pid**. + * + * u64 bpf_get_current_uid_gid(void) + * Return + * A 64-bit integer containing the current GID and UID, and + * created as such: *current_gid* **<< 32 \|** *current_uid*. + * + * int bpf_get_current_comm(void *buf, u32 size_of_buf) + * Description + * Copy the **comm** attribute of the current task into *buf* of + * *size_of_buf*. The **comm** attribute contains the name of + * the executable (excluding the path) for the current task. The + * *size_of_buf* must be strictly positive. On success, the + * helper makes sure that the *buf* is NUL-terminated. On failure, + * it is filled with zeroes. + * Return + * 0 on success, or a negative error in case of failure. + * + * u32 bpf_get_cgroup_classid(struct sk_buff *skb) + * Description + * Retrieve the classid for the current task, i.e. for the net_cls + * cgroup to which *skb* belongs. + * + * This helper can be used on TC egress path, but not on ingress. + * + * The net_cls cgroup provides an interface to tag network packets + * based on a user-provided identifier for all traffic coming from + * the tasks belonging to the related cgroup. See also the related + * kernel documentation, available from the Linux sources in file + * *Documentation/admin-guide/cgroup-v1/net_cls.rst*. + * + * The Linux kernel has two versions for cgroups: there are + * cgroups v1 and cgroups v2. Both are available to users, who can + * use a mixture of them, but note that the net_cls cgroup is for + * cgroup v1 only. This makes it incompatible with BPF programs + * run on cgroups, which is a cgroup-v2-only feature (a socket can + * only hold data for one version of cgroups at a time). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to + * "**y**" or to "**m**". + * Return + * The classid, or 0 for the default unconfigured classid. + * + * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) + * Description + * Push a *vlan_tci* (VLAN tag control information) of protocol + * *vlan_proto* to the packet associated to *skb*, then update + * the checksum. Note that if *vlan_proto* is different from + * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to + * be **ETH_P_8021Q**. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_vlan_pop(struct sk_buff *skb) + * Description + * Pop a VLAN header from the packet associated to *skb*. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Get tunnel metadata. This helper takes a pointer *key* to an + * empty **struct bpf_tunnel_key** of **size**, that will be + * filled with tunnel metadata for the packet associated to *skb*. + * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which + * indicates that the tunnel is based on IPv6 protocol instead of + * IPv4. + * + * The **struct bpf_tunnel_key** is an object that generalizes the + * principal parameters used by various tunneling protocols into a + * single struct. This way, it can be used to easily make a + * decision based on the contents of the encapsulation header, + * "summarized" in this struct. In particular, it holds the IP + * address of the remote end (IPv4 or IPv6, depending on the case) + * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also, + * this struct exposes the *key*\ **->tunnel_id**, which is + * generally mapped to a VNI (Virtual Network Identifier), making + * it programmable together with the **bpf_skb_set_tunnel_key**\ + * () helper. + * + * Let's imagine that the following code is part of a program + * attached to the TC ingress interface, on one end of a GRE + * tunnel, and is supposed to filter out all messages coming from + * remote ends with IPv4 address other than 10.0.0.1: + * + * :: + * + * int ret; + * struct bpf_tunnel_key key = {}; + * + * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + * if (ret < 0) + * return TC_ACT_SHOT; // drop packet + * + * if (key.remote_ipv4 != 0x0a000001) + * return TC_ACT_SHOT; // drop packet + * + * return TC_ACT_OK; // accept packet + * + * This interface can also be used with all encapsulation devices + * that can operate in "collect metadata" mode: instead of having + * one network device per specific configuration, the "collect + * metadata" mode only requires a single device where the + * configuration can be extracted from this helper. + * + * This can be used together with various tunnels such as VXLan, + * Geneve, GRE or IP in IP (IPIP). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Populate tunnel metadata for packet associated to *skb.* The + * tunnel metadata is set to the contents of *key*, of *size*. The + * *flags* can be set to a combination of the following values: + * + * **BPF_F_TUNINFO_IPV6** + * Indicate that the tunnel is based on IPv6 protocol + * instead of IPv4. + * **BPF_F_ZERO_CSUM_TX** + * For IPv4 packets, add a flag to tunnel metadata + * indicating that checksum computation should be skipped + * and checksum set to zeroes. + * **BPF_F_DONT_FRAGMENT** + * Add a flag to tunnel metadata indicating that the + * packet should not be fragmented. + * **BPF_F_SEQ_NUMBER** + * Add a flag to tunnel metadata indicating that a + * sequence number should be added to tunnel header before + * sending the packet. This flag was added for GRE + * encapsulation, but might be used with other protocols + * as well in the future. + * + * Here is a typical usage on the transmit path: + * + * :: + * + * struct bpf_tunnel_key key; + * populate key ... + * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0); + * + * See also the description of the **bpf_skb_get_tunnel_key**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_perf_event_read(struct bpf_map *map, u64 flags) + * Description + * Read the value of a perf event counter. This helper relies on a + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of + * the perf event counter is selected when *map* is updated with + * perf event file descriptors. The *map* is an array whose size + * is the number of available CPUs, and each cell contains a value + * relative to one CPU. The value to retrieve is indicated by + * *flags*, that contains the index of the CPU to look up, masked + * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * Note that before Linux 4.13, only hardware perf event can be + * retrieved. + * + * Also, be aware that the newer helper + * **bpf_perf_event_read_value**\ () is recommended over + * **bpf_perf_event_read**\ () in general. The latter has some ABI + * quirks where error and counter value are used as a return code + * (which is wrong to do since ranges may overlap). This issue is + * fixed with **bpf_perf_event_read_value**\ (), which at the same + * time provides more features over the **bpf_perf_event_read**\ + * () interface. Please refer to the description of + * **bpf_perf_event_read_value**\ () for details. + * Return + * The value of the perf event counter read from the map, or a + * negative error code in case of failure. + * + * int bpf_redirect(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_clone_redirect**\ + * (), except that the packet is not cloned, which provides + * increased performance. + * + * Except for XDP, both ingress and egress interfaces can be used + * for redirection. The **BPF_F_INGRESS** value in *flags* is used + * to make the distinction (ingress path is selected if the flag + * is present, egress path otherwise). Currently, XDP only + * supports redirection to the egress interface, and accepts no + * flag at all. + * + * The same effect can be attained with the more generic + * **bpf_redirect_map**\ (), which requires specific maps to be + * used but offers better performance. + * Return + * For XDP, the helper returns **XDP_REDIRECT** on success or + * **XDP_ABORTED** on error. For other program types, the values + * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on + * error. + * + * u32 bpf_get_route_realm(struct sk_buff *skb) + * Description + * Retrieve the realm or the route, that is to say the + * **tclassid** field of the destination for the *skb*. The + * indentifier retrieved is a user-provided tag, similar to the + * one used with the net_cls cgroup (see description for + * **bpf_get_cgroup_classid**\ () helper), but here this tag is + * held by a route (a destination entry), not by a task. + * + * Retrieving this identifier works with the clsact TC egress hook + * (see also **tc-bpf(8)**), or alternatively on conventional + * classful egress qdiscs, but not on TC ingress path. In case of + * clsact TC egress hook, this has the advantage that, internally, + * the destination entry has not been dropped yet in the transmit + * path. Therefore, the destination entry does not need to be + * artificially held via **netif_keep_dst**\ () for a classful + * qdisc until the *skb* is freed. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_IP_ROUTE_CLASSID** configuration option. + * Return + * The realm of the route for the packet associated to *skb*, or 0 + * if none was found. + * + * int bpf_perf_event_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * The context of the program *ctx* needs also be passed to the + * helper. + * + * On user space, a program willing to read the values needs to + * call **perf_event_open**\ () on the perf event (either for + * one or for all CPUs) and to store the file descriptor into the + * *map*. This must be done before the eBPF program can send data + * into it. An example is available in file + * *samples/bpf/trace_output_user.c* in the Linux kernel source + * tree (the eBPF program counterpart is in + * *samples/bpf/trace_output_kern.c*). + * + * **bpf_perf_event_output**\ () achieves better performance + * than **bpf_trace_printk**\ () for sharing data with user + * space, and is much better suitable for streaming data from eBPF + * programs. + * + * Note that this helper is not restricted to tracing use cases + * and can be used with programs attached to TC or XDP as well, + * where it allows for passing data to user space listeners. Data + * can be: + * + * * Only custom structs, + * * Only the packet payload, or + * * A combination of both. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len) + * Description + * This helper was provided as an easy way to load data from a + * packet. It can be used to load *len* bytes from *offset* from + * the packet associated to *skb*, into the buffer pointed by + * *to*. + * + * Since Linux 4.7, usage of this helper has mostly been replaced + * by "direct packet access", enabling packet data to be + * manipulated with *skb*\ **->data** and *skb*\ **->data_end** + * pointing respectively to the first byte of packet data and to + * the byte after the last byte of packet data. However, it + * remains useful if one wishes to read large quantities of data + * at once from a packet into the eBPF stack. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags) + * Description + * Walk a user or a kernel stack and return its id. To achieve + * this, the helper needs *ctx*, which is a pointer to the context + * on which the tracing program is executed, and a pointer to a + * *map* of type **BPF_MAP_TYPE_STACK_TRACE**. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * a combination of the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_FAST_STACK_CMP** + * Compare stacks by hash only. + * **BPF_F_REUSE_STACKID** + * If two different stacks hash into the same *stackid*, + * discard the old one. + * + * The stack id retrieved is a 32 bit long integer handle which + * can be further combined with other data (including other stack + * ids) and used as a key into maps. This can be useful for + * generating a variety of graphs (such as flame graphs or off-cpu + * graphs). + * + * For walking a stack, this helper is an improvement over + * **bpf_probe_read**\ (), which can be used with unrolled loops + * but is not efficient and consumes a lot of eBPF instructions. + * Instead, **bpf_get_stackid**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * Return + * The positive or null stack id on success, or a negative error + * in case of failure. + * + * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed) + * Description + * Compute a checksum difference, from the raw buffer pointed by + * *from*, of length *from_size* (that must be a multiple of 4), + * towards the raw buffer pointed by *to*, of size *to_size* + * (same remark). An optional *seed* can be added to the value + * (this can be cascaded, the seed may come from a previous call + * to the helper). + * + * This is flexible enough to be used in several ways: + * + * * With *from_size* == 0, *to_size* > 0 and *seed* set to + * checksum, it can be used when pushing new data. + * * With *from_size* > 0, *to_size* == 0 and *seed* set to + * checksum, it can be used when removing data from a packet. + * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it + * can be used to compute a diff. Note that *from_size* and + * *to_size* do not need to be equal. + * + * This helper can be used in combination with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to + * which one can feed in the difference computed with + * **bpf_csum_diff**\ (). + * Return + * The checksum result, or a negative error code in case of + * failure. + * + * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) + * Description + * Retrieve tunnel options metadata for the packet associated to + * *skb*, and store the raw tunnel option data to the buffer *opt* + * of *size*. + * + * This helper can be used with encapsulation devices that can + * operate in "collect metadata" mode (please refer to the related + * note in the description of **bpf_skb_get_tunnel_key**\ () for + * more details). A particular example where this can be used is + * in combination with the Geneve encapsulation protocol, where it + * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper) + * and retrieving arbitrary TLVs (Type-Length-Value headers) from + * the eBPF program. This allows for full customization of these + * headers. + * Return + * The size of the option data retrieved. + * + * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) + * Description + * Set tunnel options metadata for the packet associated to *skb* + * to the option data contained in the raw buffer *opt* of *size*. + * + * See also the description of the **bpf_skb_get_tunnel_opt**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags) + * Description + * Change the protocol of the *skb* to *proto*. Currently + * supported are transition from IPv4 to IPv6, and from IPv6 to + * IPv4. The helper takes care of the groundwork for the + * transition, including resizing the socket buffer. The eBPF + * program is expected to fill the new headers, if any, via + * **skb_store_bytes**\ () and to recompute the checksums with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ + * (). The main case for this helper is to perform NAT64 + * operations out of an eBPF program. + * + * Internally, the GSO type is marked as dodgy so that headers are + * checked and segments are recalculated by the GSO/GRO engine. + * The size for GSO target is adapted as well. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_type(struct sk_buff *skb, u32 type) + * Description + * Change the packet type for the packet associated to *skb*. This + * comes down to setting *skb*\ **->pkt_type** to *type*, except + * the eBPF program does not have a write access to *skb*\ + * **->pkt_type** beside this helper. Using a helper here allows + * for graceful handling of errors. + * + * The major use case is to change incoming *skb*s to + * **PACKET_HOST** in a programmatic way instead of having to + * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for + * example. + * + * Note that *type* only allows certain values. At this time, they + * are: + * + * **PACKET_HOST** + * Packet is for us. + * **PACKET_BROADCAST** + * Send packet to all. + * **PACKET_MULTICAST** + * Send packet to group. + * **PACKET_OTHERHOST** + * Send packet to someone else. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index) + * Description + * Check whether *skb* is a descendant of the cgroup2 held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* failed the cgroup2 descendant test. + * * 1, if the *skb* succeeded the cgroup2 descendant test. + * * A negative error code, if an error occurred. + * + * u32 bpf_get_hash_recalc(struct sk_buff *skb) + * Description + * Retrieve the hash of the packet, *skb*\ **->hash**. If it is + * not set, in particular if the hash was cleared due to mangling, + * recompute this hash. Later accesses to the hash can be done + * directly with *skb*\ **->hash**. + * + * Calling **bpf_set_hash_invalid**\ (), changing a packet + * prototype with **bpf_skb_change_proto**\ (), or calling + * **bpf_skb_store_bytes**\ () with the + * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear + * the hash and to trigger a new computation for the next call to + * **bpf_get_hash_recalc**\ (). + * Return + * The 32-bit hash. + * + * u64 bpf_get_current_task(void) + * Return + * A pointer to the current task struct. + * + * int bpf_probe_write_user(void *dst, const void *src, u32 len) + * Description + * Attempt in a safe way to write *len* bytes from the buffer + * *src* to *dst* in memory. It only works for threads that are in + * user context, and *dst* must be a valid user space address. + * + * This helper should not be used to implement any kind of + * security mechanism because of TOC-TOU attacks, but rather to + * debug, divert, and manipulate execution of semi-cooperative + * processes. + * + * Keep in mind that this feature is meant for experiments, and it + * has a risk of crashing the system and running programs. + * Therefore, when an eBPF program using this helper is attached, + * a warning including PID and process name is printed to kernel + * logs. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index) + * Description + * Check whether the probe is being run is the context of a given + * subset of the cgroup2 hierarchy. The cgroup2 to test is held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* task belongs to the cgroup2. + * * 1, if the *skb* task does not belong to the cgroup2. + * * A negative error code, if an error occurred. + * + * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Resize (trim or grow) the packet associated to *skb* to the + * new *len*. The *flags* are reserved for future usage, and must + * be left at zero. + * + * The basic idea is that the helper performs the needed work to + * change the size of the packet, then the eBPF program rewrites + * the rest via helpers like **bpf_skb_store_bytes**\ (), + * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ () + * and others. This helper is a slow path utility intended for + * replies with control messages. And because it is targeted for + * slow path, the helper itself can afford to be slow: it + * implicitly linearizes, unclones and drops offloads from the + * *skb*. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_pull_data(struct sk_buff *skb, u32 len) + * Description + * Pull in non-linear data in case the *skb* is non-linear and not + * all of *len* are part of the linear section. Make *len* bytes + * from *skb* readable and writable. If a zero value is passed for + * *len*, then the whole length of the *skb* is pulled. + * + * This helper is only needed for reading and writing with direct + * packet access. + * + * For direct packet access, testing that offsets to access + * are within packet boundaries (test on *skb*\ **->data_end**) is + * susceptible to fail if offsets are invalid, or if the requested + * data is in non-linear parts of the *skb*. On failure the + * program can just bail out, or in the case of a non-linear + * buffer, use a helper to make the data available. The + * **bpf_skb_load_bytes**\ () helper is a first solution to access + * the data. Another one consists in using **bpf_skb_pull_data** + * to pull in once the non-linear parts, then retesting and + * eventually access the data. + * + * At the same time, this also makes sure the *skb* is uncloned, + * which is a necessary condition for direct write. As this needs + * to be an invariant for the write part only, the verifier + * detects writes and adds a prologue that is calling + * **bpf_skb_pull_data()** to effectively unclone the *skb* from + * the very beginning in case it is indeed cloned. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * s64 bpf_csum_update(struct sk_buff *skb, __wsum csum) + * Description + * Add the checksum *csum* into *skb*\ **->csum** in case the + * driver has supplied a checksum for the entire packet into that + * field. Return an error otherwise. This helper is intended to be + * used in combination with **bpf_csum_diff**\ (), in particular + * when the checksum needs to be updated after data has been + * written into the packet through direct packet access. + * Return + * The checksum on success, or a negative error code in case of + * failure. + * + * void bpf_set_hash_invalid(struct sk_buff *skb) + * Description + * Invalidate the current *skb*\ **->hash**. It can be used after + * mangling on headers through direct packet access, in order to + * indicate that the hash is outdated and to trigger a + * recalculation the next time the kernel tries to access this + * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * + * int bpf_get_numa_node_id(void) + * Description + * Return the id of the current NUMA node. The primary use case + * for this helper is the selection of sockets for the local NUMA + * node, when the program is attached to sockets using the + * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**), + * but the helper is also available to other eBPF program types, + * similarly to **bpf_get_smp_processor_id**\ (). + * Return + * The id of current NUMA node. + * + * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Grows headroom of packet associated to *skb* and adjusts the + * offset of the MAC header accordingly, adding *len* bytes of + * space. It automatically extends and reallocates memory as + * required. + * + * This helper can be used on a layer 3 *skb* to push a MAC header + * for redirection into a layer 2 device. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that + * it is possible to use a negative value for *delta*. This helper + * can be used to prepare the packet for pushing or popping + * headers. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe kernel address + * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for + * more details. + * + * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str() + * instead. + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * u64 bpf_get_socket_cookie(struct sk_buff *skb) + * Description + * If the **struct sk_buff** pointed by *skb* has a known socket, + * retrieve the cookie (generated by the kernel) of this socket. + * If no cookie has been set yet, generate a new cookie. Once + * generated, the socket cookie remains stable for the life of the + * socket. This helper can be useful for monitoring per socket + * networking traffic statistics as it provides a global socket + * identifier that can be assumed unique. + * Return + * A 8-byte long non-decreasing number on success, or 0 if the + * socket field is missing inside *skb*. + * + * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) + * Description + * Equivalent to bpf_get_socket_cookie() helper that accepts + * *skb*, but gets socket from **struct bpf_sock_addr** context. + * Return + * A 8-byte long non-decreasing number. + * + * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) + * Description + * Equivalent to bpf_get_socket_cookie() helper that accepts + * *skb*, but gets socket from **struct bpf_sock_ops** context. + * Return + * A 8-byte long non-decreasing number. + * + * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Return + * The owner UID of the socket associated to *skb*. If the socket + * is **NULL**, or if it is not a full socket (i.e. if it is a + * time-wait or a request socket instead), **overflowuid** value + * is returned (note that **overflowuid** might also be the actual + * UID value for the socket). + * + * u32 bpf_set_hash(struct sk_buff *skb, u32 hash) + * Description + * Set the full hash for *skb* (set the field *skb*\ **->hash**) + * to value *hash*. + * Return + * 0 + * + * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) + * Description + * Emulate a call to **setsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **setsockopt(2)** for more information. + * The option value of length *optlen* is pointed by *optval*. + * + * This helper actually implements a subset of **setsockopt()**. + * It supports the following *level*\ s: + * + * * **SOL_SOCKET**, which supports the following *optname*\ s: + * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * * **IPPROTO_TCP**, which supports the following *optname*\ s: + * **TCP_CONGESTION**, **TCP_BPF_IW**, + * **TCP_BPF_SNDCWND_CLAMP**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags) + * Description + * Grow or shrink the room for data in the packet associated to + * *skb* by *len_diff*, and according to the selected *mode*. + * + * There are two supported modes at this time: + * + * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer + * (room space is added or removed below the layer 2 header). + * + * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer + * (room space is added or removed below the layer 3 header). + * + * The following flags are supported at this time: + * + * * **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size. + * Adjusting mss in this way is not allowed for datagrams. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4**, + * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6**: + * Any new space is reserved to hold a tunnel header. + * Configure skb offsets and other fields accordingly. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L4_GRE**, + * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP**: + * Use with ENCAP_L3 flags to further specify the tunnel type. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L2**\ (*len*): + * Use with ENCAP_L3/L4 flags to further specify the tunnel + * type; *len* is the length of the inner MAC header. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the endpoint referenced by *map* at + * index *key*. Depending on its type, this *map* can contain + * references to net devices (for forwarding packets through other + * ports), or to CPUs (for redirecting XDP frames to another CPU; + * but this is only implemented for native XDP (with driver + * support) as of this writing). + * + * The lower two bits of *flags* are used as the return code if + * the map lookup fails. This is so that the return value can be + * one of the XDP program return codes up to XDP_TX, as chosen by + * the caller. Any higher bits in the *flags* argument must be + * unset. + * + * When used to redirect packets to net devices, this helper + * provides a high performance increase over **bpf_redirect**\ (). + * This is due to various implementation details of the underlying + * mechanisms, one of which is the fact that **bpf_redirect_map**\ + * () tries to send packet as a "bulk" to the device. + * Return + * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * + * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a *map* referencing sockets. The + * *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust the address pointed by *xdp_md*\ **->data_meta** by + * *delta* (which can be positive or negative). Note that this + * operation modifies the address stored in *xdp_md*\ **->data**, + * so the latter must be loaded only after the helper has been + * called. + * + * The use of *xdp_md*\ **->data_meta** is optional and programs + * are not required to use it. The rationale is that when the + * packet is processed with XDP (e.g. as DoS filter), it is + * possible to push further meta data along with it before passing + * to the stack, and to give the guarantee that an ingress eBPF + * program attached as a TC classifier on the same device can pick + * this up for further post-processing. Since TC works with socket + * buffers, it remains possible to set from XDP the **mark** or + * **priority** pointers, or other pointers for the socket buffer. + * Having this scratch space generic and programmable allows for + * more flexibility as the user is free to store whatever meta + * data they need. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * Read the value of a perf event counter, and store it into *buf* + * of size *buf_size*. This helper relies on a *map* of type + * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event + * counter is selected when *map* is updated with perf event file + * descriptors. The *map* is an array whose size is the number of + * available CPUs, and each cell contains a value relative to one + * CPU. The value to retrieve is indicated by *flags*, that + * contains the index of the CPU to look up, masked with + * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * This helper behaves in a way close to + * **bpf_perf_event_read**\ () helper, save that instead of + * just returning the value observed, it fills the *buf* + * structure. This allows for additional data to be retrieved: in + * particular, the enabled and running times (in *buf*\ + * **->enabled** and *buf*\ **->running**, respectively) are + * copied. In general, **bpf_perf_event_read_value**\ () is + * recommended over **bpf_perf_event_read**\ (), which has some + * ABI issues and provides fewer functionalities. + * + * These values are interesting, because hardware PMU (Performance + * Monitoring Unit) counters are limited resources. When there are + * more PMU based perf events opened than available counters, + * kernel will multiplex these events so each event gets certain + * percentage (but not all) of the PMU time. In case that + * multiplexing happens, the number of samples or counter value + * will not reflect the case compared to when no multiplexing + * occurs. This makes comparison between different runs difficult. + * Typically, the counter value should be normalized before + * comparing to other experiments. The usual normalization is done + * as follows. + * + * :: + * + * normalized_counter = counter * t_enabled / t_running + * + * Where t_enabled is the time enabled for event and t_running is + * the time running for event since last normalization. The + * enabled and running times are accumulated since the perf event + * open. To achieve scaling factor between two invocations of an + * eBPF program, users can can use CPU id as the key (which is + * typical for perf array usage model) to remember the previous + * value and do the calculation inside the eBPF program. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * For en eBPF program attached to a perf event, retrieve the + * value of the event counter associated to *ctx* and store it in + * the structure pointed by *buf* and of size *buf_size*. Enabled + * and running times are also stored in the structure (see + * description of helper **bpf_perf_event_read_value**\ () for + * more details). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen) + * Description + * Emulate a call to **getsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **getsockopt(2)** for more information. + * The retrieved value is stored in the structure pointed by + * *opval* and of length *optlen*. + * + * This helper actually implements a subset of **getsockopt()**. + * It supports the following *level*\ s: + * + * * **IPPROTO_TCP**, which supports *optname* + * **TCP_CONGESTION**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_override_return(struct pt_regs *regs, u64 rc) + * Description + * Used for error injection, this helper uses kprobes to override + * the return value of the probed function, and to set it to *rc*. + * The first argument is the context *regs* on which the kprobe + * works. + * + * This helper works by setting setting the PC (program counter) + * to an override function which is run in place of the original + * probed function. This means the probed function is not run at + * all. The replacement function just returns with the required + * value. + * + * This helper has security implications, and thus is subject to + * restrictions. It is only available if the kernel was compiled + * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration + * option, and in this case it only works on functions tagged with + * **ALLOW_ERROR_INJECTION** in the kernel code. + * + * Also, the helper is only available for the architectures having + * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, + * x86 architecture is the only one to support this feature. + * Return + * 0 + * + * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval) + * Description + * Attempt to set the value of the **bpf_sock_ops_cb_flags** field + * for the full TCP socket associated to *bpf_sock_ops* to + * *argval*. + * + * The primary use of this field is to determine if there should + * be calls to eBPF programs of type + * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP + * code. A program of the same type can change its value, per + * connection and as necessary, when the connection is + * established. This field is directly accessible for reading, but + * this helper must be used for updates in order to return an + * error if an eBPF program tries to set a callback that is not + * supported in the current kernel. + * + * *argval* is a flag array which can combine these flags: + * + * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) + * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) + * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT) + * + * Therefore, this function can be used to clear a callback flag by + * setting the appropriate bit to zero. e.g. to disable the RTO + * callback: + * + * **bpf_sock_ops_cb_flags_set(bpf_sock,** + * **bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)** + * + * Here are some examples of where one could call such eBPF + * program: + * + * * When RTO fires. + * * When a packet is retransmitted. + * * When the connection terminates. + * * When a packet is sent. + * * When a packet is received. + * Return + * Code **-EINVAL** if the socket is not a full TCP socket; + * otherwise, a positive number containing the bits that could not + * be set is returned (which comes down to 0 if all bits were set + * as required). + * + * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, apply the verdict of the eBPF program to + * the next *bytes* (number of bytes) of message *msg*. + * + * For example, this helper can be used in the following cases: + * + * * A single **sendmsg**\ () or **sendfile**\ () system call + * contains multiple logical messages that the eBPF program is + * supposed to read and for which it should apply a verdict. + * * An eBPF program only cares to read the first *bytes* of a + * *msg*. If the message has a large payload, then setting up + * and calling the eBPF program repeatedly for all bytes, even + * though the verdict is already known, would create unnecessary + * overhead. + * + * When called from within an eBPF program, the helper sets a + * counter internal to the BPF infrastructure, that is used to + * apply the last verdict to the next *bytes*. If *bytes* is + * smaller than the current data being processed from a + * **sendmsg**\ () or **sendfile**\ () system call, the first + * *bytes* will be sent and the eBPF program will be re-run with + * the pointer for start of data pointing to byte number *bytes* + * **+ 1**. If *bytes* is larger than the current data being + * processed, then the eBPF verdict will be applied to multiple + * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are + * consumed. + * + * Note that if a socket closes with the internal counter holding + * a non-zero value, this is not a problem because data is not + * being buffered for *bytes* and is sent as it is received. + * Return + * 0 + * + * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, prevent the execution of the verdict eBPF + * program for message *msg* until *bytes* (byte number) have been + * accumulated. + * + * This can be used when one needs a specific number of bytes + * before a verdict can be assigned, even if the data spans + * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme + * case would be a user calling **sendmsg**\ () repeatedly with + * 1-byte long message segments. Obviously, this is bad for + * performance, but it is still valid. If the eBPF program needs + * *bytes* bytes to validate a header, this helper can be used to + * prevent the eBPF program to be called again until *bytes* have + * been accumulated. + * Return + * 0 + * + * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags) + * Description + * For socket policies, pull in non-linear data from user space + * for *msg* and set pointers *msg*\ **->data** and *msg*\ + * **->data_end** to *start* and *end* bytes offsets into *msg*, + * respectively. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it can only parse data that the (**data**, **data_end**) + * pointers have already consumed. For **sendmsg**\ () hooks this + * is likely the first scatterlist element. But for calls relying + * on the **sendpage** handler (e.g. **sendfile**\ ()) this will + * be the range (**0**, **0**) because the data is shared with + * user space and by default the objective is to avoid allowing + * user space to modify data while (or after) eBPF verdict is + * being decided. This helper can be used to pull in data and to + * set the start and end pointer to given values. Data will be + * copied if necessary (i.e. if data was not linear and if start + * and end pointers do not point to the same chunk). + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) + * Description + * Bind the socket associated to *ctx* to the address pointed by + * *addr*, of length *addr_len*. This allows for making outgoing + * connection from the desired IP address, which can be useful for + * example when all processes inside a cgroup should use one + * single IP address on a host that has multiple IP configured. + * + * This helper works for IPv4 and IPv6, TCP and UDP sockets. The + * domain (*addr*\ **->sa_family**) must be **AF_INET** (or + * **AF_INET6**). Looking for a free port to bind to can be + * expensive, therefore binding to port is not permitted by the + * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively) + * must be set to zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is + * only possible to shrink the packet as of this writing, + * therefore *delta* must be a negative integer. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags) + * Description + * Retrieve the XFRM state (IP transform framework, see also + * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*. + * + * The retrieved value is stored in the **struct bpf_xfrm_state** + * pointed by *xfrm_state* and of length *size*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_XFRM** configuration option. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stack(void *ctx, void *buf, u32 size, u64 flags) + * Description + * Return a user or a kernel stack in bpf program provided buffer. + * To achieve this, the helper needs *ctx*, which is a pointer + * to the context on which the tracing program is executed. + * To store the stacktrace, the bpf program provides *buf* with + * a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_USER_BUILD_ID** + * Collect buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **bpf_get_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * Return + * A non-negative value equal to or less than *size* on success, + * or a negative error in case of failure. + * + * int bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header) + * Description + * This helper is similar to **bpf_skb_load_bytes**\ () in that + * it provides an easy way to load *len* bytes from *offset* + * from the packet associated to *skb*, into the buffer pointed + * by *to*. The difference to **bpf_skb_load_bytes**\ () is that + * a fifth argument *start_header* exists in order to select a + * base offset to start from. *start_header* can be one of: + * + * **BPF_HDR_START_MAC** + * Base offset to load data from is *skb*'s mac header. + * **BPF_HDR_START_NET** + * Base offset to load data from is *skb*'s network header. + * + * In general, "direct packet access" is the preferred method to + * access packet data, however, this helper is in particular useful + * in socket filters where *skb*\ **->data** does not always point + * to the start of the mac header and where "direct packet access" + * is not available. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags) + * Description + * Do FIB lookup in kernel tables using parameters in *params*. + * If lookup is successful and result shows packet is to be + * forwarded, the neighbor tables are searched for the nexthop. + * If successful (ie., FIB lookup shows forwarding and nexthop + * is resolved), the nexthop address is returned in ipv4_dst + * or ipv6_dst based on family, smac is set to mac address of + * egress device, dmac is set to nexthop mac address, rt_metric + * is set to metric from route (IPv4/IPv6 only), and ifindex + * is set to the device index of the nexthop from the FIB lookup. + * + * *plen* argument is the size of the passed in struct. + * *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_FIB_LOOKUP_DIRECT** + * Do a direct table lookup vs full lookup using FIB + * rules. + * **BPF_FIB_LOOKUP_OUTPUT** + * Perform lookup from an egress perspective (default is + * ingress). + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** tc cls_act programs. + * Return + * * < 0 if any input argument is invalid + * * 0 on success (packet is forwarded, nexthop neighbor exists) + * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the + * packet is not forwarded or needs assist from full stack + * + * int bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a sockhash *map* referencing sockets. + * The *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * skb socket level. If the sk_buff *skb* is allowed to pass (i.e. + * if the verdeict eBPF program returns **SK_PASS**), redirect it + * to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) + * Description + * Encapsulate the packet associated to *skb* within a Layer 3 + * protocol header. This header is provided in the buffer at + * address *hdr*, with *len* its size in bytes. *type* indicates + * the protocol of the header and can be one of: + * + * **BPF_LWT_ENCAP_SEG6** + * IPv6 encapsulation with Segment Routing Header + * (**struct ipv6_sr_hdr**). *hdr* only contains the SRH, + * the IPv6 header is computed by the kernel. + * **BPF_LWT_ENCAP_SEG6_INLINE** + * Only works if *skb* contains an IPv6 packet. Insert a + * Segment Routing Header (**struct ipv6_sr_hdr**) inside + * the IPv6 header. + * **BPF_LWT_ENCAP_IP** + * IP encapsulation (GRE/GUE/IPIP/etc). The outer header + * must be IPv4 or IPv6, followed by zero or more + * additional headers, up to **LWT_BPF_MAX_HEADROOM** + * total bytes in all prepended headers. Please note that + * if **skb_is_gso**\ (*skb*) is true, no more than two + * headers can be prepended, and the inner header, if + * present, should be either GRE or UDP/GUE. + * + * **BPF_LWT_ENCAP_SEG6**\ \* types can be called by BPF programs + * of type **BPF_PROG_TYPE_LWT_IN**; **BPF_LWT_ENCAP_IP** type can + * be called by bpf programs of types **BPF_PROG_TYPE_LWT_IN** and + * **BPF_PROG_TYPE_LWT_XMIT**. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. Only the flags, tag and TLVs + * inside the outermost IPv6 Segment Routing Header can be + * modified through this helper. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta) + * Description + * Adjust the size allocated to TLVs in the outermost IPv6 + * Segment Routing Header contained in the packet associated to + * *skb*, at position *offset* by *delta* bytes. Only offsets + * after the segments are accepted. *delta* can be as well + * positive (growing) as negative (shrinking). + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len) + * Description + * Apply an IPv6 Segment Routing action of type *action* to the + * packet associated to *skb*. Each action takes a parameter + * contained at address *param*, and of length *param_len* bytes. + * *action* can be one of: + * + * **SEG6_LOCAL_ACTION_END_X** + * End.X action: Endpoint with Layer-3 cross-connect. + * Type of *param*: **struct in6_addr**. + * **SEG6_LOCAL_ACTION_END_T** + * End.T action: Endpoint with specific IPv6 table lookup. + * Type of *param*: **int**. + * **SEG6_LOCAL_ACTION_END_B6** + * End.B6 action: Endpoint bound to an SRv6 policy. + * Type of *param*: **struct ipv6_sr_hdr**. + * **SEG6_LOCAL_ACTION_END_B6_ENCAP** + * End.B6.Encap action: Endpoint bound to an SRv6 + * encapsulation policy. + * Type of *param*: **struct ipv6_sr_hdr**. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_rc_repeat(void *ctx) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. + * + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * Return + * 0 + * + * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown**\ () again with the same values, or calling + * **bpf_rc_repeat**\ (). + * + * Some protocols include a toggle bit, in case the button was + * released and pressed again between consecutive scancodes. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * Return + * 0 + * + * u64 bpf_skb_cgroup_id(struct sk_buff *skb) + * Description + * Return the cgroup v2 id of the socket associated with the *skb*. + * This is roughly similar to the **bpf_get_cgroup_classid**\ () + * helper for cgroup v1 by providing a tag resp. identifier that + * can be matched on or used for map lookups e.g. to implement + * policy. The cgroup v2 id of a given path in the hierarchy is + * exposed in user space through the f_handle API in order to get + * to the same 64-bit id. + * + * This helper can be used on TC egress path, but not on ingress, + * and is available only if the kernel was compiled with the + * **CONFIG_SOCK_CGROUP_DATA** configuration option. + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * u64 bpf_get_current_cgroup_id(void) + * Return + * A 64-bit integer containing the current cgroup id based + * on the cgroup within which the current task is running. + * + * void *bpf_get_local_storage(void *map, u64 flags) + * Description + * Get the pointer to the local storage area. + * The type and the size of the local storage is defined + * by the *map* argument. + * The *flags* meaning is specific for each map type, + * and has to be 0 for cgroup local storage. + * + * Depending on the BPF program type, a local storage area + * can be shared between multiple instances of the BPF program, + * running simultaneously. + * + * A user should care about the synchronization by himself. + * For example, by using the **BPF_STX_XADD** instruction to alter + * the shared data. + * Return + * A pointer to the local storage area. + * + * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) + * Description + * Select a **SO_REUSEPORT** socket from a + * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*. + * It checks the selected socket is matching the incoming + * request in the socket buffer. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *skb* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *skb*, then return value will be same as that + * of **bpf_skb_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *skb*. + * + * The format of returned id and helper limitations are same as in + * **bpf_skb_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + * + * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + * + * int bpf_sk_release(struct bpf_sock *sock) + * Description + * Release the reference held by *sock*. *sock* must be a + * non-**NULL** pointer that was returned from + * **bpf_sk_lookup_xxx**\ (). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is + * removed to make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_pop_elem(struct bpf_map *map, void *value) + * Description + * Pop an element from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_peek_elem(struct bpf_map *map, void *value) + * Description + * Get an element from *map* without removing it. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) + * Description + * For socket policies, insert *len* bytes into *msg* at offset + * *start*. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it may want to insert metadata or options into the *msg*. + * This can later be read and used by any of the lower layer BPF + * hooks. + * + * This helper may fail if under memory pressure (a malloc + * fails) in these cases BPF programs will get an appropriate + * error and BPF programs will need to handle them. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) + * Description + * Will remove *len* bytes from a *msg* starting at byte *start*. + * This may result in **ENOMEM** errors under certain situations if + * an allocation and copy are required due to a full ring buffer. + * However, the helper will try to avoid doing the allocation + * if possible. Other errors can occur if input parameters are + * invalid either due to *start* byte not being valid part of *msg* + * payload and/or *pop* value being to large. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded pointer movement. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * Return + * 0 + * + * int bpf_spin_lock(struct bpf_spin_lock *lock) + * Description + * Acquire a spinlock represented by the pointer *lock*, which is + * stored as part of a value of a map. Taking the lock allows to + * safely update the rest of the fields in that value. The + * spinlock can (and must) later be released with a call to + * **bpf_spin_unlock**\ (\ *lock*\ ). + * + * Spinlocks in BPF programs come with a number of restrictions + * and constraints: + * + * * **bpf_spin_lock** objects are only allowed inside maps of + * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this + * list could be extended in the future). + * * BTF description of the map is mandatory. + * * The BPF program can take ONE lock at a time, since taking two + * or more could cause dead locks. + * * Only one **struct bpf_spin_lock** is allowed per map element. + * * When the lock is taken, calls (either BPF to BPF or helpers) + * are not allowed. + * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not + * allowed inside a spinlock-ed region. + * * The BPF program MUST call **bpf_spin_unlock**\ () to release + * the lock, on all execution paths, before it returns. + * * The BPF program can access **struct bpf_spin_lock** only via + * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ () + * helpers. Loading or storing data into the **struct + * bpf_spin_lock** *lock*\ **;** field of a map is not allowed. + * * To use the **bpf_spin_lock**\ () helper, the BTF description + * of the map value must be a struct and have **struct + * bpf_spin_lock** *anyname*\ **;** field at the top level. + * Nested lock inside another struct is not allowed. + * * The **struct bpf_spin_lock** *lock* field in a map value must + * be aligned on a multiple of 4 bytes in that value. + * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy + * the **bpf_spin_lock** field to user space. + * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from + * a BPF program, do not update the **bpf_spin_lock** field. + * * **bpf_spin_lock** cannot be on the stack or inside a + * networking packet (it can only be inside of a map values). + * * **bpf_spin_lock** is available to root only. + * * Tracing programs and socket filter programs cannot use + * **bpf_spin_lock**\ () due to insufficient preemption checks + * (but this may change in the future). + * * **bpf_spin_lock** is not allowed in inner maps of map-in-map. + * Return + * 0 + * + * int bpf_spin_unlock(struct bpf_spin_lock *lock) + * Description + * Release the *lock* previously locked by a call to + * **bpf_spin_lock**\ (\ *lock*\ ). + * Return + * 0 + * + * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_sock** pointer such + * that all the fields in this **bpf_sock** can be accessed. + * Return + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + * + * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_tcp_sock** pointer from a + * **struct bpf_sock** pointer. + * Return + * A **struct bpf_tcp_sock** pointer on success, or **NULL** in + * case of failure. + * + * int bpf_skb_ecn_set_ce(struct sk_buff *skb) + * Description + * Set ECN (Explicit Congestion Notification) field of IP header + * to **CE** (Congestion Encountered) if current value is **ECT** + * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6 + * and IPv4. + * Return + * 1 if the **CE** flag is set (either by the current helper call + * or because it was already present), 0 if it is not set. + * + * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk) + * Description + * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state. + * **bpf_sk_release**\ () is unnecessary and not allowed. + * Return + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + * + * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * This function is identical to **bpf_sk_lookup_tcp**\ (), except + * that it also returns timewait or request sockets. Use + * **bpf_sk_fullsock**\ () or **bpf_tcp_sock**\ () to access the + * full structure. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + * + * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK for + * the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains **sizeof**\ (**struct tcphdr**). + * + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative + * error otherwise. + * + * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags) + * Description + * Get name of sysctl in /proc/sys/ and copy it into provided by + * program buffer *buf* of size *buf_len*. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * + * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is + * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name + * only (e.g. "tcp_mem"). + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get current value of sysctl as it is presented in /proc/sys + * (incl. newline, etc), and copy it as a string into provided + * by program buffer *buf* of size *buf_len*. + * + * The whole value is copied, no matter what file position user + * space issued e.g. sys_read at. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if current value was unavailable, e.g. because + * sysctl is uninitialized and read returns -EIO for it. + * + * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get new value being written by user space to sysctl (before + * the actual write happens) and copy it as a string into + * provided by program buffer *buf* of size *buf_len*. + * + * User space may write new value at file position > 0. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if sysctl is being read. + * + * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len) + * Description + * Override new value being written by user space to sysctl with + * value provided by program in buffer *buf* of size *buf_len*. + * + * *buf* should contain a string in same form as provided by user + * space on sysctl write. + * + * User space may write new value at file position > 0. To override + * the whole sysctl value file position should be set to zero. + * Return + * 0 on success. + * + * **-E2BIG** if the *buf_len* is too big. + * + * **-EINVAL** if sysctl is being read. + * + * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to a long integer according to the given base + * and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)) followed by a single + * optional '**-**' sign. + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtol**\ (3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + * + * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to an unsigned long integer according to the + * given base and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)). + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtoul**\ (3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + * + * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * Description + * Get a bpf-local-storage from a *sk*. + * + * Logically, it could be thought of getting the value from + * a *map* with *sk* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *sk*) except this + * helper enforces the key must be a full socket and the map must + * be a **BPF_MAP_TYPE_SK_STORAGE** also. + * + * Underneath, the value is stored locally at *sk* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf-local-storages residing at *sk*. + * + * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf-local-storage will be + * created if one does not exist. *value* can be used + * together with **BPF_SK_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf-local-storage. If *value* is + * **NULL**, the new bpf-local-storage will be zero initialized. + * Return + * A bpf-local-storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf-local-storage. + * + * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * Description + * Delete a bpf-local-storage from a *sk*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf-local-storage cannot be found. + * + * int bpf_send_signal(u32 sig) + * Description + * Send signal *sig* to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. + * + * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header. + * + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** SYN cookie cannot be issued due to error + * + * **-ENOENT** SYN cookie should not be issued (no SYN flood) + * + * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies + * + * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 + * + * int bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct sk_buff. + * + * This helper is similar to **bpf_perf_event_output**\ () but + * restricted to raw_tracepoint bpf programs. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Safely attempt to read *size* bytes from user space address + * *unsafe_ptr* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Safely attempt to read *size* bytes from kernel space address + * *unsafe_ptr* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe user address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, the length of the copied string is returned. This + * makes this helper useful in tracing programs for reading + * strings, and more importantly to get its length at runtime. See + * the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_user_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read_user()** helper here + * instead to read the string would require to estimate the length + * at compile time, and would often result in copying more memory + * than necessary. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr* + * to *dst*. Same semantics as with bpf_probe_read_user_str() apply. + * Return + * On success, the strictly positive length of the string, including + * the trailing NUL character. On error, a negative value. + */ +#define __BPF_FUNC_MAPPER(FN) \ + FN(unspec), \ + FN(map_lookup_elem), \ + FN(map_update_elem), \ + FN(map_delete_elem), \ + FN(probe_read), \ + FN(ktime_get_ns), \ + FN(trace_printk), \ + FN(get_prandom_u32), \ + FN(get_smp_processor_id), \ + FN(skb_store_bytes), \ + FN(l3_csum_replace), \ + FN(l4_csum_replace), \ + FN(tail_call), \ + FN(clone_redirect), \ + FN(get_current_pid_tgid), \ + FN(get_current_uid_gid), \ + FN(get_current_comm), \ + FN(get_cgroup_classid), \ + FN(skb_vlan_push), \ + FN(skb_vlan_pop), \ + FN(skb_get_tunnel_key), \ + FN(skb_set_tunnel_key), \ + FN(perf_event_read), \ + FN(redirect), \ + FN(get_route_realm), \ + FN(perf_event_output), \ + FN(skb_load_bytes), \ + FN(get_stackid), \ + FN(csum_diff), \ + FN(skb_get_tunnel_opt), \ + FN(skb_set_tunnel_opt), \ + FN(skb_change_proto), \ + FN(skb_change_type), \ + FN(skb_under_cgroup), \ + FN(get_hash_recalc), \ + FN(get_current_task), \ + FN(probe_write_user), \ + FN(current_task_under_cgroup), \ + FN(skb_change_tail), \ + FN(skb_pull_data), \ + FN(csum_update), \ + FN(set_hash_invalid), \ + FN(get_numa_node_id), \ + FN(skb_change_head), \ + FN(xdp_adjust_head), \ + FN(probe_read_str), \ + FN(get_socket_cookie), \ + FN(get_socket_uid), \ + FN(set_hash), \ + FN(setsockopt), \ + FN(skb_adjust_room), \ + FN(redirect_map), \ + FN(sk_redirect_map), \ + FN(sock_map_update), \ + FN(xdp_adjust_meta), \ + FN(perf_event_read_value), \ + FN(perf_prog_read_value), \ + FN(getsockopt), \ + FN(override_return), \ + FN(sock_ops_cb_flags_set), \ + FN(msg_redirect_map), \ + FN(msg_apply_bytes), \ + FN(msg_cork_bytes), \ + FN(msg_pull_data), \ + FN(bind), \ + FN(xdp_adjust_tail), \ + FN(skb_get_xfrm_state), \ + FN(get_stack), \ + FN(skb_load_bytes_relative), \ + FN(fib_lookup), \ + FN(sock_hash_update), \ + FN(msg_redirect_hash), \ + FN(sk_redirect_hash), \ + FN(lwt_push_encap), \ + FN(lwt_seg6_store_bytes), \ + FN(lwt_seg6_adjust_srh), \ + FN(lwt_seg6_action), \ + FN(rc_repeat), \ + FN(rc_keydown), \ + FN(skb_cgroup_id), \ + FN(get_current_cgroup_id), \ + FN(get_local_storage), \ + FN(sk_select_reuseport), \ + FN(skb_ancestor_cgroup_id), \ + FN(sk_lookup_tcp), \ + FN(sk_lookup_udp), \ + FN(sk_release), \ + FN(map_push_elem), \ + FN(map_pop_elem), \ + FN(map_peek_elem), \ + FN(msg_push_data), \ + FN(msg_pop_data), \ + FN(rc_pointer_rel), \ + FN(spin_lock), \ + FN(spin_unlock), \ + FN(sk_fullsock), \ + FN(tcp_sock), \ + FN(skb_ecn_set_ce), \ + FN(get_listener_sock), \ + FN(skc_lookup_tcp), \ + FN(tcp_check_syncookie), \ + FN(sysctl_get_name), \ + FN(sysctl_get_current_value), \ + FN(sysctl_get_new_value), \ + FN(sysctl_set_new_value), \ + FN(strtol), \ + FN(strtoul), \ + FN(sk_storage_get), \ + FN(sk_storage_delete), \ + FN(send_signal), \ + FN(tcp_gen_syncookie), \ + FN(skb_output), \ + FN(probe_read_user), \ + FN(probe_read_kernel), \ + FN(probe_read_user_str), \ + FN(probe_read_kernel_str), + +/* integer value in 'imm' field of BPF_CALL instruction selects which helper + * function eBPF program intends to call + */ +#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x +enum bpf_func_id { + __BPF_FUNC_MAPPER(__BPF_ENUM_FN) + __BPF_FUNC_MAX_ID, +}; +#undef __BPF_ENUM_FN + +/* All flags used by eBPF helper functions, placed here. */ + +/* BPF_FUNC_skb_store_bytes flags. */ +#define BPF_F_RECOMPUTE_CSUM (1ULL << 0) +#define BPF_F_INVALIDATE_HASH (1ULL << 1) + +/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags. + * First 4 bits are for passing the header field size. + */ +#define BPF_F_HDR_FIELD_MASK 0xfULL + +/* BPF_FUNC_l4_csum_replace flags. */ +#define BPF_F_PSEUDO_HDR (1ULL << 4) +#define BPF_F_MARK_MANGLED_0 (1ULL << 5) +#define BPF_F_MARK_ENFORCE (1ULL << 6) + +/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ +#define BPF_F_INGRESS (1ULL << 0) + +/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ +#define BPF_F_TUNINFO_IPV6 (1ULL << 0) + +/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */ +#define BPF_F_SKIP_FIELD_MASK 0xffULL +#define BPF_F_USER_STACK (1ULL << 8) +/* flags used by BPF_FUNC_get_stackid only. */ +#define BPF_F_FAST_STACK_CMP (1ULL << 9) +#define BPF_F_REUSE_STACKID (1ULL << 10) +/* flags used by BPF_FUNC_get_stack only. */ +#define BPF_F_USER_BUILD_ID (1ULL << 11) + +/* BPF_FUNC_skb_set_tunnel_key flags. */ +#define BPF_F_ZERO_CSUM_TX (1ULL << 1) +#define BPF_F_DONT_FRAGMENT (1ULL << 2) +#define BPF_F_SEQ_NUMBER (1ULL << 3) + +/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and + * BPF_FUNC_perf_event_read_value flags. + */ +#define BPF_F_INDEX_MASK 0xffffffffULL +#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK +/* BPF_FUNC_perf_event_output for sk_buff input context. */ +#define BPF_F_CTXLEN_MASK (0xfffffULL << 32) + +/* Current network namespace */ +#define BPF_F_CURRENT_NETNS (-1L) + +/* BPF_FUNC_skb_adjust_room flags. */ +#define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0) + +#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff +#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56 + +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1) +#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2) +#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3) +#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4) +#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \ + BPF_ADJ_ROOM_ENCAP_L2_MASK) \ + << BPF_ADJ_ROOM_ENCAP_L2_SHIFT) + +/* BPF_FUNC_sysctl_get_name flags. */ +#define BPF_F_SYSCTL_BASE_NAME (1ULL << 0) + +/* BPF_FUNC_sk_storage_get flags */ +#define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0) + +/* Mode for BPF_FUNC_skb_adjust_room helper. */ +enum bpf_adj_room_mode { + BPF_ADJ_ROOM_NET, + BPF_ADJ_ROOM_MAC, +}; + +/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */ +enum bpf_hdr_start_off { + BPF_HDR_START_MAC, + BPF_HDR_START_NET, +}; + +/* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */ +enum bpf_lwt_encap_mode { + BPF_LWT_ENCAP_SEG6, + BPF_LWT_ENCAP_SEG6_INLINE, + BPF_LWT_ENCAP_IP, +}; + +#define __bpf_md_ptr(type, name) \ +union { \ + type name; \ + __u64 :64; \ +} __attribute__((aligned(8))) + +/* user accessible mirror of in-kernel sk_buff. + * new fields can only be added to the end of this structure + */ +struct __sk_buff { + __u32 len; + __u32 pkt_type; + __u32 mark; + __u32 queue_mapping; + __u32 protocol; + __u32 vlan_present; + __u32 vlan_tci; + __u32 vlan_proto; + __u32 priority; + __u32 ingress_ifindex; + __u32 ifindex; + __u32 tc_index; + __u32 cb[5]; + __u32 hash; + __u32 tc_classid; + __u32 data; + __u32 data_end; + __u32 napi_id; + + /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */ + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + /* ... here. */ + + __u32 data_meta; + __bpf_md_ptr(struct bpf_flow_keys *, flow_keys); + __u64 tstamp; + __u32 wire_len; + __u32 gso_segs; + __bpf_md_ptr(struct bpf_sock *, sk); +}; + +struct bpf_tunnel_key { + __u32 tunnel_id; + union { + __u32 remote_ipv4; + __u32 remote_ipv6[4]; + }; + __u8 tunnel_tos; + __u8 tunnel_ttl; + __u16 tunnel_ext; /* Padding, future use. */ + __u32 tunnel_label; +}; + +/* user accessible mirror of in-kernel xfrm_state. + * new fields can only be added to the end of this structure + */ +struct bpf_xfrm_state { + __u32 reqid; + __u32 spi; /* Stored in network byte order */ + __u16 family; + __u16 ext; /* Padding, future use. */ + union { + __u32 remote_ipv4; /* Stored in network byte order */ + __u32 remote_ipv6[4]; /* Stored in network byte order */ + }; +}; + +/* Generic BPF return codes which all BPF program types may support. + * The values are binary compatible with their TC_ACT_* counter-part to + * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT + * programs. + * + * XDP is handled seprately, see XDP_*. + */ +enum bpf_ret_code { + BPF_OK = 0, + /* 1 reserved */ + BPF_DROP = 2, + /* 3-6 reserved */ + BPF_REDIRECT = 7, + /* >127 are reserved for prog type specific return codes. + * + * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and + * BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been + * changed and should be routed based on its new L3 header. + * (This is an L3 redirect, as opposed to L2 redirect + * represented by BPF_REDIRECT above). + */ + BPF_LWT_REROUTE = 128, +}; + +struct bpf_sock { + __u32 bound_dev_if; + __u32 family; + __u32 type; + __u32 protocol; + __u32 mark; + __u32 priority; + /* IP address also allows 1 and 2 bytes access */ + __u32 src_ip4; + __u32 src_ip6[4]; + __u32 src_port; /* host byte order */ + __u32 dst_port; /* network byte order */ + __u32 dst_ip4; + __u32 dst_ip6[4]; + __u32 state; +}; + +struct bpf_tcp_sock { + __u32 snd_cwnd; /* Sending congestion window */ + __u32 srtt_us; /* smoothed round trip time << 3 in usecs */ + __u32 rtt_min; + __u32 snd_ssthresh; /* Slow start size threshold */ + __u32 rcv_nxt; /* What we want to receive next */ + __u32 snd_nxt; /* Next sequence we send */ + __u32 snd_una; /* First byte we want an ack for */ + __u32 mss_cache; /* Cached effective mss, not including SACKS */ + __u32 ecn_flags; /* ECN status bits. */ + __u32 rate_delivered; /* saved rate sample: packets delivered */ + __u32 rate_interval_us; /* saved rate sample: time elapsed */ + __u32 packets_out; /* Packets which are "in flight" */ + __u32 retrans_out; /* Retransmitted packets out */ + __u32 total_retrans; /* Total retransmits for entire connection */ + __u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn + * total number of segments in. + */ + __u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn + * total number of data segments in. + */ + __u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut + * The total number of segments sent. + */ + __u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut + * total number of data segments sent. + */ + __u32 lost_out; /* Lost packets */ + __u32 sacked_out; /* SACK'd packets */ + __u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived + * sum(delta(rcv_nxt)), or how many bytes + * were acked. + */ + __u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked + * sum(delta(snd_una)), or how many bytes + * were acked. + */ + __u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups + * total number of DSACK blocks received + */ + __u32 delivered; /* Total data packets delivered incl. rexmits */ + __u32 delivered_ce; /* Like the above but only ECE marked packets */ + __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */ +}; + +struct bpf_sock_tuple { + union { + struct { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + } ipv4; + struct { + __be32 saddr[4]; + __be32 daddr[4]; + __be16 sport; + __be16 dport; + } ipv6; + }; +}; + +struct bpf_xdp_sock { + __u32 queue_id; +}; + +#define XDP_PACKET_HEADROOM 256 + +/* User return codes for XDP prog type. + * A valid XDP program must return one of these defined values. All other + * return codes are reserved for future use. Unknown return codes will + * result in packet drops and a warning via bpf_warn_invalid_xdp_action(). + */ +enum xdp_action { + XDP_ABORTED = 0, + XDP_DROP, + XDP_PASS, + XDP_TX, + XDP_REDIRECT, +}; + +/* user accessible metadata for XDP packet hook + * new fields must be added to the end of this structure + */ +struct xdp_md { + __u32 data; + __u32 data_end; + __u32 data_meta; + /* Below access go through struct xdp_rxq_info */ + __u32 ingress_ifindex; /* rxq->dev->ifindex */ + __u32 rx_queue_index; /* rxq->queue_index */ +}; + +enum sk_action { + SK_DROP = 0, + SK_PASS, +}; + +/* user accessible metadata for SK_MSG packet hook, new fields must + * be added to the end of this structure + */ +struct sk_msg_md { + __bpf_md_ptr(void *, data); + __bpf_md_ptr(void *, data_end); + + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + __u32 size; /* Total size of sk_msg */ +}; + +struct sk_reuseport_md { + /* + * Start of directly accessible data. It begins from + * the tcp/udp header. + */ + __bpf_md_ptr(void *, data); + /* End of directly accessible data */ + __bpf_md_ptr(void *, data_end); + /* + * Total length of packet (starting from the tcp/udp header). + * Note that the directly accessible bytes (data_end - data) + * could be less than this "len". Those bytes could be + * indirectly read by a helper "bpf_skb_load_bytes()". + */ + __u32 len; + /* + * Eth protocol in the mac header (network byte order). e.g. + * ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD) + */ + __u32 eth_protocol; + __u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */ + __u32 bind_inany; /* Is sock bound to an INANY address? */ + __u32 hash; /* A hash of the packet 4 tuples */ +}; + +#define BPF_TAG_SIZE 8 + +struct bpf_prog_info { + __u32 type; + __u32 id; + __u8 tag[BPF_TAG_SIZE]; + __u32 jited_prog_len; + __u32 xlated_prog_len; + __aligned_u64 jited_prog_insns; + __aligned_u64 xlated_prog_insns; + __u64 load_time; /* ns since boottime */ + __u32 created_by_uid; + __u32 nr_map_ids; + __aligned_u64 map_ids; + char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 gpl_compatible:1; + __u32 :31; /* alignment pad */ + __u64 netns_dev; + __u64 netns_ino; + __u32 nr_jited_ksyms; + __u32 nr_jited_func_lens; + __aligned_u64 jited_ksyms; + __aligned_u64 jited_func_lens; + __u32 btf_id; + __u32 func_info_rec_size; + __aligned_u64 func_info; + __u32 nr_func_info; + __u32 nr_line_info; + __aligned_u64 line_info; + __aligned_u64 jited_line_info; + __u32 nr_jited_line_info; + __u32 line_info_rec_size; + __u32 jited_line_info_rec_size; + __u32 nr_prog_tags; + __aligned_u64 prog_tags; + __u64 run_time_ns; + __u64 run_cnt; +} __attribute__((aligned(8))); + +struct bpf_map_info { + __u32 type; + __u32 id; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 map_flags; + char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 :32; + __u64 netns_dev; + __u64 netns_ino; + __u32 btf_id; + __u32 btf_key_type_id; + __u32 btf_value_type_id; +} __attribute__((aligned(8))); + +struct bpf_btf_info { + __aligned_u64 btf; + __u32 btf_size; + __u32 id; +} __attribute__((aligned(8))); + +/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed + * by user and intended to be used by socket (e.g. to bind to, depends on + * attach attach type). + */ +struct bpf_sock_addr { + __u32 user_family; /* Allows 4-byte read, but no write. */ + __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write. + * Stored in network byte order. + */ + __u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. + * Stored in network byte order. + */ + __u32 user_port; /* Allows 4-byte read and write. + * Stored in network byte order + */ + __u32 family; /* Allows 4-byte read, but no write */ + __u32 type; /* Allows 4-byte read, but no write */ + __u32 protocol; /* Allows 4-byte read, but no write */ + __u32 msg_src_ip4; /* Allows 1,2,4-byte read and 4-byte write. + * Stored in network byte order. + */ + __u32 msg_src_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. + * Stored in network byte order. + */ + __bpf_md_ptr(struct bpf_sock *, sk); +}; + +/* User bpf_sock_ops struct to access socket values and specify request ops + * and their replies. + * Some of this fields are in network (bigendian) byte order and may need + * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h). + * New fields can only be added at the end of this structure + */ +struct bpf_sock_ops { + __u32 op; + union { + __u32 args[4]; /* Optionally passed to bpf program */ + __u32 reply; /* Returned by bpf program */ + __u32 replylong[4]; /* Optionally returned by bpf prog */ + }; + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + __u32 is_fullsock; /* Some TCP fields are only valid if + * there is a full socket. If not, the + * fields read as zero. + */ + __u32 snd_cwnd; + __u32 srtt_us; /* Averaged RTT << 3 in usecs */ + __u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */ + __u32 state; + __u32 rtt_min; + __u32 snd_ssthresh; + __u32 rcv_nxt; + __u32 snd_nxt; + __u32 snd_una; + __u32 mss_cache; + __u32 ecn_flags; + __u32 rate_delivered; + __u32 rate_interval_us; + __u32 packets_out; + __u32 retrans_out; + __u32 total_retrans; + __u32 segs_in; + __u32 data_segs_in; + __u32 segs_out; + __u32 data_segs_out; + __u32 lost_out; + __u32 sacked_out; + __u32 sk_txhash; + __u64 bytes_received; + __u64 bytes_acked; + __bpf_md_ptr(struct bpf_sock *, sk); +}; + +/* Definitions for bpf_sock_ops_cb_flags */ +#define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0) +#define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1) +#define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2) +#define BPF_SOCK_OPS_RTT_CB_FLAG (1<<3) +#define BPF_SOCK_OPS_ALL_CB_FLAGS 0xF /* Mask of all currently + * supported cb flags + */ + +/* List of known BPF sock_ops operators. + * New entries can only be added at the end + */ +enum { + BPF_SOCK_OPS_VOID, + BPF_SOCK_OPS_TIMEOUT_INIT, /* Should return SYN-RTO value to use or + * -1 if default value should be used + */ + BPF_SOCK_OPS_RWND_INIT, /* Should return initial advertized + * window (in packets) or -1 if default + * value should be used + */ + BPF_SOCK_OPS_TCP_CONNECT_CB, /* Calls BPF program right before an + * active connection is initialized + */ + BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, /* Calls BPF program when an + * active connection is + * established + */ + BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, /* Calls BPF program when a + * passive connection is + * established + */ + BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control + * needs ECN + */ + BPF_SOCK_OPS_BASE_RTT, /* Get base RTT. The correct value is + * based on the path and may be + * dependent on the congestion control + * algorithm. In general it indicates + * a congestion threshold. RTTs above + * this indicate congestion + */ + BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered. + * Arg1: value of icsk_retransmits + * Arg2: value of icsk_rto + * Arg3: whether RTO has expired + */ + BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted. + * Arg1: sequence number of 1st byte + * Arg2: # segments + * Arg3: return value of + * tcp_transmit_skb (0 => success) + */ + BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state. + * Arg1: old_state + * Arg2: new_state + */ + BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after + * socket transition to LISTEN state. + */ + BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + */ +}; + +/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect + * changes between the TCP and BPF versions. Ideally this should never happen. + * If it does, we need to add code to convert them before calling + * the BPF sock_ops function. + */ +enum { + BPF_TCP_ESTABLISHED = 1, + BPF_TCP_SYN_SENT, + BPF_TCP_SYN_RECV, + BPF_TCP_FIN_WAIT1, + BPF_TCP_FIN_WAIT2, + BPF_TCP_TIME_WAIT, + BPF_TCP_CLOSE, + BPF_TCP_CLOSE_WAIT, + BPF_TCP_LAST_ACK, + BPF_TCP_LISTEN, + BPF_TCP_CLOSING, /* Now a valid state */ + BPF_TCP_NEW_SYN_RECV, + + BPF_TCP_MAX_STATES /* Leave at the end! */ +}; + +#define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ +#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */ + +struct bpf_perf_event_value { + __u64 counter; + __u64 enabled; + __u64 running; +}; + +#define BPF_DEVCG_ACC_MKNOD (1ULL << 0) +#define BPF_DEVCG_ACC_READ (1ULL << 1) +#define BPF_DEVCG_ACC_WRITE (1ULL << 2) + +#define BPF_DEVCG_DEV_BLOCK (1ULL << 0) +#define BPF_DEVCG_DEV_CHAR (1ULL << 1) + +struct bpf_cgroup_dev_ctx { + /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */ + __u32 access_type; + __u32 major; + __u32 minor; +}; + +struct bpf_raw_tracepoint_args { + __u64 args[0]; +}; + +/* DIRECT: Skip the FIB rules and go to FIB table associated with device + * OUTPUT: Do lookup from egress perspective; default is ingress + */ +#define BPF_FIB_LOOKUP_DIRECT (1U << 0) +#define BPF_FIB_LOOKUP_OUTPUT (1U << 1) + +enum { + BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */ + BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */ + BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */ + BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */ + BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */ + BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */ + BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ + BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ + BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ +}; + +struct bpf_fib_lookup { + /* input: network family for lookup (AF_INET, AF_INET6) + * output: network family of egress nexthop + */ + __u8 family; + + /* set if lookup is to consider L4 data - e.g., FIB rules */ + __u8 l4_protocol; + __be16 sport; + __be16 dport; + + /* total length of packet from network header - used for MTU check */ + __u16 tot_len; + + /* input: L3 device index for lookup + * output: device index from FIB lookup + */ + __u32 ifindex; + + union { + /* inputs to lookup */ + __u8 tos; /* AF_INET */ + __be32 flowinfo; /* AF_INET6, flow_label + priority */ + + /* output: metric of fib result (IPv4/IPv6 only) */ + __u32 rt_metric; + }; + + union { + __be32 ipv4_src; + __u32 ipv6_src[4]; /* in6_addr; network order */ + }; + + /* input to bpf_fib_lookup, ipv{4,6}_dst is destination address in + * network header. output: bpf_fib_lookup sets to gateway address + * if FIB lookup returns gateway route + */ + union { + __be32 ipv4_dst; + __u32 ipv6_dst[4]; /* in6_addr; network order */ + }; + + /* output */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + __u8 smac[6]; /* ETH_ALEN */ + __u8 dmac[6]; /* ETH_ALEN */ +}; + +enum bpf_task_fd_type { + BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_KPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_KRETPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_UPROBE, /* filename + offset */ + BPF_FD_TYPE_URETPROBE, /* filename + offset */ +}; + +#define BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG (1U << 0) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL (1U << 1) +#define BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP (1U << 2) + +struct bpf_flow_keys { + __u16 nhoff; + __u16 thoff; + __u16 addr_proto; /* ETH_P_* of valid addrs */ + __u8 is_frag; + __u8 is_first_frag; + __u8 is_encap; + __u8 ip_proto; + __be16 n_proto; + __be16 sport; + __be16 dport; + union { + struct { + __be32 ipv4_src; + __be32 ipv4_dst; + }; + struct { + __u32 ipv6_src[4]; /* in6_addr; network order */ + __u32 ipv6_dst[4]; /* in6_addr; network order */ + }; + }; + __u32 flags; + __be32 flow_label; +}; + +struct bpf_func_info { + __u32 insn_off; + __u32 type_id; +}; + +#define BPF_LINE_INFO_LINE_NUM(line_col) ((line_col) >> 10) +#define BPF_LINE_INFO_LINE_COL(line_col) ((line_col) & 0x3ff) + +struct bpf_line_info { + __u32 insn_off; + __u32 file_name_off; + __u32 line_off; + __u32 line_col; +}; + +struct bpf_spin_lock { + __u32 val; +}; + +struct bpf_sysctl { + __u32 write; /* Sysctl is being read (= 0) or written (= 1). + * Allows 1,2,4-byte read, but no write. + */ + __u32 file_pos; /* Sysctl file position to read from, write to. + * Allows 1,2,4-byte read an 4-byte write. + */ +}; + +struct bpf_sockopt { + __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(void *, optval); + __bpf_md_ptr(void *, optval_end); + + __s32 level; + __s32 optname; + __s32 optlen; + __s32 retval; +}; + +#endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/src/contrib/libbpf/include/uapi/linux/bpf_common.h b/src/contrib/libbpf/include/uapi/linux/bpf_common.h new file mode 100644 index 0000000..ee97668 --- /dev/null +++ b/src/contrib/libbpf/include/uapi/linux/bpf_common.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_BPF_COMMON_H__ +#define _UAPI__LINUX_BPF_COMMON_H__ + +/* Instruction classes */ +#define BPF_CLASS(code) ((code) & 0x07) +#define BPF_LD 0x00 +#define BPF_LDX 0x01 +#define BPF_ST 0x02 +#define BPF_STX 0x03 +#define BPF_ALU 0x04 +#define BPF_JMP 0x05 +#define BPF_RET 0x06 +#define BPF_MISC 0x07 + +/* ld/ldx fields */ +#define BPF_SIZE(code) ((code) & 0x18) +#define BPF_W 0x00 /* 32-bit */ +#define BPF_H 0x08 /* 16-bit */ +#define BPF_B 0x10 /* 8-bit */ +/* eBPF BPF_DW 0x18 64-bit */ +#define BPF_MODE(code) ((code) & 0xe0) +#define BPF_IMM 0x00 +#define BPF_ABS 0x20 +#define BPF_IND 0x40 +#define BPF_MEM 0x60 +#define BPF_LEN 0x80 +#define BPF_MSH 0xa0 + +/* alu/jmp fields */ +#define BPF_OP(code) ((code) & 0xf0) +#define BPF_ADD 0x00 +#define BPF_SUB 0x10 +#define BPF_MUL 0x20 +#define BPF_DIV 0x30 +#define BPF_OR 0x40 +#define BPF_AND 0x50 +#define BPF_LSH 0x60 +#define BPF_RSH 0x70 +#define BPF_NEG 0x80 +#define BPF_MOD 0x90 +#define BPF_XOR 0xa0 + +#define BPF_JA 0x00 +#define BPF_JEQ 0x10 +#define BPF_JGT 0x20 +#define BPF_JGE 0x30 +#define BPF_JSET 0x40 +#define BPF_SRC(code) ((code) & 0x08) +#define BPF_K 0x00 +#define BPF_X 0x08 + +#ifndef BPF_MAXINSNS +#define BPF_MAXINSNS 4096 +#endif + +#endif /* _UAPI__LINUX_BPF_COMMON_H__ */ diff --git a/src/contrib/libbpf/include/uapi/linux/btf.h b/src/contrib/libbpf/include/uapi/linux/btf.h new file mode 100644 index 0000000..63ae4a3 --- /dev/null +++ b/src/contrib/libbpf/include/uapi/linux/btf.h @@ -0,0 +1,165 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2018 Facebook */ +#ifndef _UAPI__LINUX_BTF_H__ +#define _UAPI__LINUX_BTF_H__ + +#include <linux/types.h> + +#define BTF_MAGIC 0xeB9F +#define BTF_VERSION 1 + +struct btf_header { + __u16 magic; + __u8 version; + __u8 flags; + __u32 hdr_len; + + /* All offsets are in bytes relative to the end of this header */ + __u32 type_off; /* offset of type section */ + __u32 type_len; /* length of type section */ + __u32 str_off; /* offset of string section */ + __u32 str_len; /* length of string section */ +}; + +/* Max # of type identifier */ +#define BTF_MAX_TYPE 0x0000ffff +/* Max offset into the string section */ +#define BTF_MAX_NAME_OFFSET 0x0000ffff +/* Max # of struct/union/enum members or func args */ +#define BTF_MAX_VLEN 0xffff + +struct btf_type { + __u32 name_off; + /* "info" bits arrangement + * bits 0-15: vlen (e.g. # of struct's members) + * bits 16-23: unused + * bits 24-27: kind (e.g. int, ptr, array...etc) + * bits 28-30: unused + * bit 31: kind_flag, currently used by + * struct, union and fwd + */ + __u32 info; + /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC. + * "size" tells the size of the type it is describing. + * + * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, + * FUNC, FUNC_PROTO and VAR. + * "type" is a type_id referring to another type. + */ + union { + __u32 size; + __u32 type; + }; +}; + +#define BTF_INFO_KIND(info) (((info) >> 24) & 0x0f) +#define BTF_INFO_VLEN(info) ((info) & 0xffff) +#define BTF_INFO_KFLAG(info) ((info) >> 31) + +#define BTF_KIND_UNKN 0 /* Unknown */ +#define BTF_KIND_INT 1 /* Integer */ +#define BTF_KIND_PTR 2 /* Pointer */ +#define BTF_KIND_ARRAY 3 /* Array */ +#define BTF_KIND_STRUCT 4 /* Struct */ +#define BTF_KIND_UNION 5 /* Union */ +#define BTF_KIND_ENUM 6 /* Enumeration */ +#define BTF_KIND_FWD 7 /* Forward */ +#define BTF_KIND_TYPEDEF 8 /* Typedef */ +#define BTF_KIND_VOLATILE 9 /* Volatile */ +#define BTF_KIND_CONST 10 /* Const */ +#define BTF_KIND_RESTRICT 11 /* Restrict */ +#define BTF_KIND_FUNC 12 /* Function */ +#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ +#define BTF_KIND_VAR 14 /* Variable */ +#define BTF_KIND_DATASEC 15 /* Section */ +#define BTF_KIND_MAX BTF_KIND_DATASEC +#define NR_BTF_KINDS (BTF_KIND_MAX + 1) + +/* For some specific BTF_KIND, "struct btf_type" is immediately + * followed by extra data. + */ + +/* BTF_KIND_INT is followed by a u32 and the following + * is the 32 bits arrangement: + */ +#define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) +#define BTF_INT_OFFSET(VAL) (((VAL) & 0x00ff0000) >> 16) +#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff) + +/* Attributes stored in the BTF_INT_ENCODING */ +#define BTF_INT_SIGNED (1 << 0) +#define BTF_INT_CHAR (1 << 1) +#define BTF_INT_BOOL (1 << 2) + +/* BTF_KIND_ENUM is followed by multiple "struct btf_enum". + * The exact number of btf_enum is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_enum { + __u32 name_off; + __s32 val; +}; + +/* BTF_KIND_ARRAY is followed by one "struct btf_array" */ +struct btf_array { + __u32 type; + __u32 index_type; + __u32 nelems; +}; + +/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed + * by multiple "struct btf_member". The exact number + * of btf_member is stored in the vlen (of the info in + * "struct btf_type"). + */ +struct btf_member { + __u32 name_off; + __u32 type; + /* If the type info kind_flag is set, the btf_member offset + * contains both member bitfield size and bit offset. The + * bitfield size is set for bitfield members. If the type + * info kind_flag is not set, the offset contains only bit + * offset. + */ + __u32 offset; +}; + +/* If the struct/union type info kind_flag is set, the + * following two macros are used to access bitfield_size + * and bit_offset from btf_member.offset. + */ +#define BTF_MEMBER_BITFIELD_SIZE(val) ((val) >> 24) +#define BTF_MEMBER_BIT_OFFSET(val) ((val) & 0xffffff) + +/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param". + * The exact number of btf_param is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_param { + __u32 name_off; + __u32 type; +}; + +enum { + BTF_VAR_STATIC = 0, + BTF_VAR_GLOBAL_ALLOCATED, +}; + +/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe + * additional information related to the variable such as its linkage. + */ +struct btf_var { + __u32 linkage; +}; + +/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo" + * to describe all BTF_KIND_VAR types it contains along with it's + * in-section offset as well as size. + */ +struct btf_var_secinfo { + __u32 type; + __u32 offset; + __u32 size; +}; + +#endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/src/contrib/libbpf/include/uapi/linux/if_link.h b/src/contrib/libbpf/include/uapi/linux/if_link.h new file mode 100644 index 0000000..8aec876 --- /dev/null +++ b/src/contrib/libbpf/include/uapi/linux/if_link.h @@ -0,0 +1,1033 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_IF_LINK_H +#define _UAPI_LINUX_IF_LINK_H + +#include <linux/types.h> +#include <linux/netlink.h> + +/* This struct should be in sync with struct rtnl_link_stats64 */ +struct rtnl_link_stats { + __u32 rx_packets; /* total packets received */ + __u32 tx_packets; /* total packets transmitted */ + __u32 rx_bytes; /* total bytes received */ + __u32 tx_bytes; /* total bytes transmitted */ + __u32 rx_errors; /* bad packets received */ + __u32 tx_errors; /* packet transmit problems */ + __u32 rx_dropped; /* no space in linux buffers */ + __u32 tx_dropped; /* no space available in linux */ + __u32 multicast; /* multicast packets received */ + __u32 collisions; + + /* detailed rx_errors: */ + __u32 rx_length_errors; + __u32 rx_over_errors; /* receiver ring buff overflow */ + __u32 rx_crc_errors; /* recved pkt with crc error */ + __u32 rx_frame_errors; /* recv'd frame alignment error */ + __u32 rx_fifo_errors; /* recv'r fifo overrun */ + __u32 rx_missed_errors; /* receiver missed packet */ + + /* detailed tx_errors */ + __u32 tx_aborted_errors; + __u32 tx_carrier_errors; + __u32 tx_fifo_errors; + __u32 tx_heartbeat_errors; + __u32 tx_window_errors; + + /* for cslip etc */ + __u32 rx_compressed; + __u32 tx_compressed; + + __u32 rx_nohandler; /* dropped, no handler found */ +}; + +/* The main device statistics structure */ +struct rtnl_link_stats64 { + __u64 rx_packets; /* total packets received */ + __u64 tx_packets; /* total packets transmitted */ + __u64 rx_bytes; /* total bytes received */ + __u64 tx_bytes; /* total bytes transmitted */ + __u64 rx_errors; /* bad packets received */ + __u64 tx_errors; /* packet transmit problems */ + __u64 rx_dropped; /* no space in linux buffers */ + __u64 tx_dropped; /* no space available in linux */ + __u64 multicast; /* multicast packets received */ + __u64 collisions; + + /* detailed rx_errors: */ + __u64 rx_length_errors; + __u64 rx_over_errors; /* receiver ring buff overflow */ + __u64 rx_crc_errors; /* recved pkt with crc error */ + __u64 rx_frame_errors; /* recv'd frame alignment error */ + __u64 rx_fifo_errors; /* recv'r fifo overrun */ + __u64 rx_missed_errors; /* receiver missed packet */ + + /* detailed tx_errors */ + __u64 tx_aborted_errors; + __u64 tx_carrier_errors; + __u64 tx_fifo_errors; + __u64 tx_heartbeat_errors; + __u64 tx_window_errors; + + /* for cslip etc */ + __u64 rx_compressed; + __u64 tx_compressed; + + __u64 rx_nohandler; /* dropped, no handler found */ +}; + +/* The struct should be in sync with struct ifmap */ +struct rtnl_link_ifmap { + __u64 mem_start; + __u64 mem_end; + __u64 base_addr; + __u16 irq; + __u8 dma; + __u8 port; +}; + +/* + * IFLA_AF_SPEC + * Contains nested attributes for address family specific attributes. + * Each address family may create a attribute with the address family + * number as type and create its own attribute structure in it. + * + * Example: + * [IFLA_AF_SPEC] = { + * [AF_INET] = { + * [IFLA_INET_CONF] = ..., + * }, + * [AF_INET6] = { + * [IFLA_INET6_FLAGS] = ..., + * [IFLA_INET6_CONF] = ..., + * } + * } + */ + +enum { + IFLA_UNSPEC, + IFLA_ADDRESS, + IFLA_BROADCAST, + IFLA_IFNAME, + IFLA_MTU, + IFLA_LINK, + IFLA_QDISC, + IFLA_STATS, + IFLA_COST, +#define IFLA_COST IFLA_COST + IFLA_PRIORITY, +#define IFLA_PRIORITY IFLA_PRIORITY + IFLA_MASTER, +#define IFLA_MASTER IFLA_MASTER + IFLA_WIRELESS, /* Wireless Extension event - see wireless.h */ +#define IFLA_WIRELESS IFLA_WIRELESS + IFLA_PROTINFO, /* Protocol specific information for a link */ +#define IFLA_PROTINFO IFLA_PROTINFO + IFLA_TXQLEN, +#define IFLA_TXQLEN IFLA_TXQLEN + IFLA_MAP, +#define IFLA_MAP IFLA_MAP + IFLA_WEIGHT, +#define IFLA_WEIGHT IFLA_WEIGHT + IFLA_OPERSTATE, + IFLA_LINKMODE, + IFLA_LINKINFO, +#define IFLA_LINKINFO IFLA_LINKINFO + IFLA_NET_NS_PID, + IFLA_IFALIAS, + IFLA_NUM_VF, /* Number of VFs if device is SR-IOV PF */ + IFLA_VFINFO_LIST, + IFLA_STATS64, + IFLA_VF_PORTS, + IFLA_PORT_SELF, + IFLA_AF_SPEC, + IFLA_GROUP, /* Group the device belongs to */ + IFLA_NET_NS_FD, + IFLA_EXT_MASK, /* Extended info mask, VFs, etc */ + IFLA_PROMISCUITY, /* Promiscuity count: > 0 means acts PROMISC */ +#define IFLA_PROMISCUITY IFLA_PROMISCUITY + IFLA_NUM_TX_QUEUES, + IFLA_NUM_RX_QUEUES, + IFLA_CARRIER, + IFLA_PHYS_PORT_ID, + IFLA_CARRIER_CHANGES, + IFLA_PHYS_SWITCH_ID, + IFLA_LINK_NETNSID, + IFLA_PHYS_PORT_NAME, + IFLA_PROTO_DOWN, + IFLA_GSO_MAX_SEGS, + IFLA_GSO_MAX_SIZE, + IFLA_PAD, + IFLA_XDP, + IFLA_EVENT, + IFLA_NEW_NETNSID, + IFLA_IF_NETNSID, + IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */ + IFLA_CARRIER_UP_COUNT, + IFLA_CARRIER_DOWN_COUNT, + IFLA_NEW_IFINDEX, + IFLA_MIN_MTU, + IFLA_MAX_MTU, + IFLA_PROP_LIST, + IFLA_ALT_IFNAME, /* Alternative ifname */ + __IFLA_MAX +}; + + +#define IFLA_MAX (__IFLA_MAX - 1) + +/* backwards compatibility for userspace */ +#ifndef __KERNEL__ +#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) +#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg)) +#endif + +enum { + IFLA_INET_UNSPEC, + IFLA_INET_CONF, + __IFLA_INET_MAX, +}; + +#define IFLA_INET_MAX (__IFLA_INET_MAX - 1) + +/* ifi_flags. + + IFF_* flags. + + The only change is: + IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are + more not changeable by user. They describe link media + characteristics and set by device driver. + + Comments: + - Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid + - If neither of these three flags are set; + the interface is NBMA. + + - IFF_MULTICAST does not mean anything special: + multicasts can be used on all not-NBMA links. + IFF_MULTICAST means that this media uses special encapsulation + for multicast frames. Apparently, all IFF_POINTOPOINT and + IFF_BROADCAST devices are able to use multicasts too. + */ + +/* IFLA_LINK. + For usual devices it is equal ifi_index. + If it is a "virtual interface" (f.e. tunnel), ifi_link + can point to real physical interface (f.e. for bandwidth calculations), + or maybe 0, what means, that real media is unknown (usual + for IPIP tunnels, when route to endpoint is allowed to change) + */ + +/* Subtype attributes for IFLA_PROTINFO */ +enum { + IFLA_INET6_UNSPEC, + IFLA_INET6_FLAGS, /* link flags */ + IFLA_INET6_CONF, /* sysctl parameters */ + IFLA_INET6_STATS, /* statistics */ + IFLA_INET6_MCAST, /* MC things. What of them? */ + IFLA_INET6_CACHEINFO, /* time values and max reasm size */ + IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */ + IFLA_INET6_TOKEN, /* device token */ + IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */ + __IFLA_INET6_MAX +}; + +#define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1) + +enum in6_addr_gen_mode { + IN6_ADDR_GEN_MODE_EUI64, + IN6_ADDR_GEN_MODE_NONE, + IN6_ADDR_GEN_MODE_STABLE_PRIVACY, + IN6_ADDR_GEN_MODE_RANDOM, +}; + +/* Bridge section */ + +enum { + IFLA_BR_UNSPEC, + IFLA_BR_FORWARD_DELAY, + IFLA_BR_HELLO_TIME, + IFLA_BR_MAX_AGE, + IFLA_BR_AGEING_TIME, + IFLA_BR_STP_STATE, + IFLA_BR_PRIORITY, + IFLA_BR_VLAN_FILTERING, + IFLA_BR_VLAN_PROTOCOL, + IFLA_BR_GROUP_FWD_MASK, + IFLA_BR_ROOT_ID, + IFLA_BR_BRIDGE_ID, + IFLA_BR_ROOT_PORT, + IFLA_BR_ROOT_PATH_COST, + IFLA_BR_TOPOLOGY_CHANGE, + IFLA_BR_TOPOLOGY_CHANGE_DETECTED, + IFLA_BR_HELLO_TIMER, + IFLA_BR_TCN_TIMER, + IFLA_BR_TOPOLOGY_CHANGE_TIMER, + IFLA_BR_GC_TIMER, + IFLA_BR_GROUP_ADDR, + IFLA_BR_FDB_FLUSH, + IFLA_BR_MCAST_ROUTER, + IFLA_BR_MCAST_SNOOPING, + IFLA_BR_MCAST_QUERY_USE_IFADDR, + IFLA_BR_MCAST_QUERIER, + IFLA_BR_MCAST_HASH_ELASTICITY, + IFLA_BR_MCAST_HASH_MAX, + IFLA_BR_MCAST_LAST_MEMBER_CNT, + IFLA_BR_MCAST_STARTUP_QUERY_CNT, + IFLA_BR_MCAST_LAST_MEMBER_INTVL, + IFLA_BR_MCAST_MEMBERSHIP_INTVL, + IFLA_BR_MCAST_QUERIER_INTVL, + IFLA_BR_MCAST_QUERY_INTVL, + IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, + IFLA_BR_MCAST_STARTUP_QUERY_INTVL, + IFLA_BR_NF_CALL_IPTABLES, + IFLA_BR_NF_CALL_IP6TABLES, + IFLA_BR_NF_CALL_ARPTABLES, + IFLA_BR_VLAN_DEFAULT_PVID, + IFLA_BR_PAD, + IFLA_BR_VLAN_STATS_ENABLED, + IFLA_BR_MCAST_STATS_ENABLED, + IFLA_BR_MCAST_IGMP_VERSION, + IFLA_BR_MCAST_MLD_VERSION, + IFLA_BR_VLAN_STATS_PER_PORT, + IFLA_BR_MULTI_BOOLOPT, + __IFLA_BR_MAX, +}; + +#define IFLA_BR_MAX (__IFLA_BR_MAX - 1) + +struct ifla_bridge_id { + __u8 prio[2]; + __u8 addr[6]; /* ETH_ALEN */ +}; + +enum { + BRIDGE_MODE_UNSPEC, + BRIDGE_MODE_HAIRPIN, +}; + +enum { + IFLA_BRPORT_UNSPEC, + IFLA_BRPORT_STATE, /* Spanning tree state */ + IFLA_BRPORT_PRIORITY, /* " priority */ + IFLA_BRPORT_COST, /* " cost */ + IFLA_BRPORT_MODE, /* mode (hairpin) */ + IFLA_BRPORT_GUARD, /* bpdu guard */ + IFLA_BRPORT_PROTECT, /* root port protection */ + IFLA_BRPORT_FAST_LEAVE, /* multicast fast leave */ + IFLA_BRPORT_LEARNING, /* mac learning */ + IFLA_BRPORT_UNICAST_FLOOD, /* flood unicast traffic */ + IFLA_BRPORT_PROXYARP, /* proxy ARP */ + IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */ + IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ + IFLA_BRPORT_ROOT_ID, /* designated root */ + IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ + IFLA_BRPORT_DESIGNATED_PORT, + IFLA_BRPORT_DESIGNATED_COST, + IFLA_BRPORT_ID, + IFLA_BRPORT_NO, + IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, + IFLA_BRPORT_CONFIG_PENDING, + IFLA_BRPORT_MESSAGE_AGE_TIMER, + IFLA_BRPORT_FORWARD_DELAY_TIMER, + IFLA_BRPORT_HOLD_TIMER, + IFLA_BRPORT_FLUSH, + IFLA_BRPORT_MULTICAST_ROUTER, + IFLA_BRPORT_PAD, + IFLA_BRPORT_MCAST_FLOOD, + IFLA_BRPORT_MCAST_TO_UCAST, + IFLA_BRPORT_VLAN_TUNNEL, + IFLA_BRPORT_BCAST_FLOOD, + IFLA_BRPORT_GROUP_FWD_MASK, + IFLA_BRPORT_NEIGH_SUPPRESS, + IFLA_BRPORT_ISOLATED, + IFLA_BRPORT_BACKUP_PORT, + __IFLA_BRPORT_MAX +}; +#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) + +struct ifla_cacheinfo { + __u32 max_reasm_len; + __u32 tstamp; /* ipv6InterfaceTable updated timestamp */ + __u32 reachable_time; + __u32 retrans_time; +}; + +enum { + IFLA_INFO_UNSPEC, + IFLA_INFO_KIND, + IFLA_INFO_DATA, + IFLA_INFO_XSTATS, + IFLA_INFO_SLAVE_KIND, + IFLA_INFO_SLAVE_DATA, + __IFLA_INFO_MAX, +}; + +#define IFLA_INFO_MAX (__IFLA_INFO_MAX - 1) + +/* VLAN section */ + +enum { + IFLA_VLAN_UNSPEC, + IFLA_VLAN_ID, + IFLA_VLAN_FLAGS, + IFLA_VLAN_EGRESS_QOS, + IFLA_VLAN_INGRESS_QOS, + IFLA_VLAN_PROTOCOL, + __IFLA_VLAN_MAX, +}; + +#define IFLA_VLAN_MAX (__IFLA_VLAN_MAX - 1) + +struct ifla_vlan_flags { + __u32 flags; + __u32 mask; +}; + +enum { + IFLA_VLAN_QOS_UNSPEC, + IFLA_VLAN_QOS_MAPPING, + __IFLA_VLAN_QOS_MAX +}; + +#define IFLA_VLAN_QOS_MAX (__IFLA_VLAN_QOS_MAX - 1) + +struct ifla_vlan_qos_mapping { + __u32 from; + __u32 to; +}; + +/* MACVLAN section */ +enum { + IFLA_MACVLAN_UNSPEC, + IFLA_MACVLAN_MODE, + IFLA_MACVLAN_FLAGS, + IFLA_MACVLAN_MACADDR_MODE, + IFLA_MACVLAN_MACADDR, + IFLA_MACVLAN_MACADDR_DATA, + IFLA_MACVLAN_MACADDR_COUNT, + __IFLA_MACVLAN_MAX, +}; + +#define IFLA_MACVLAN_MAX (__IFLA_MACVLAN_MAX - 1) + +enum macvlan_mode { + MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */ + MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */ + MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */ + MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */ + MACVLAN_MODE_SOURCE = 16,/* use source MAC address list to assign */ +}; + +enum macvlan_macaddr_mode { + MACVLAN_MACADDR_ADD, + MACVLAN_MACADDR_DEL, + MACVLAN_MACADDR_FLUSH, + MACVLAN_MACADDR_SET, +}; + +#define MACVLAN_FLAG_NOPROMISC 1 + +/* VRF section */ +enum { + IFLA_VRF_UNSPEC, + IFLA_VRF_TABLE, + __IFLA_VRF_MAX +}; + +#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1) + +enum { + IFLA_VRF_PORT_UNSPEC, + IFLA_VRF_PORT_TABLE, + __IFLA_VRF_PORT_MAX +}; + +#define IFLA_VRF_PORT_MAX (__IFLA_VRF_PORT_MAX - 1) + +/* MACSEC section */ +enum { + IFLA_MACSEC_UNSPEC, + IFLA_MACSEC_SCI, + IFLA_MACSEC_PORT, + IFLA_MACSEC_ICV_LEN, + IFLA_MACSEC_CIPHER_SUITE, + IFLA_MACSEC_WINDOW, + IFLA_MACSEC_ENCODING_SA, + IFLA_MACSEC_ENCRYPT, + IFLA_MACSEC_PROTECT, + IFLA_MACSEC_INC_SCI, + IFLA_MACSEC_ES, + IFLA_MACSEC_SCB, + IFLA_MACSEC_REPLAY_PROTECT, + IFLA_MACSEC_VALIDATION, + IFLA_MACSEC_PAD, + __IFLA_MACSEC_MAX, +}; + +#define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1) + +/* XFRM section */ +enum { + IFLA_XFRM_UNSPEC, + IFLA_XFRM_LINK, + IFLA_XFRM_IF_ID, + __IFLA_XFRM_MAX +}; + +#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1) + +enum macsec_validation_type { + MACSEC_VALIDATE_DISABLED = 0, + MACSEC_VALIDATE_CHECK = 1, + MACSEC_VALIDATE_STRICT = 2, + __MACSEC_VALIDATE_END, + MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1, +}; + +/* IPVLAN section */ +enum { + IFLA_IPVLAN_UNSPEC, + IFLA_IPVLAN_MODE, + IFLA_IPVLAN_FLAGS, + __IFLA_IPVLAN_MAX +}; + +#define IFLA_IPVLAN_MAX (__IFLA_IPVLAN_MAX - 1) + +enum ipvlan_mode { + IPVLAN_MODE_L2 = 0, + IPVLAN_MODE_L3, + IPVLAN_MODE_L3S, + IPVLAN_MODE_MAX +}; + +#define IPVLAN_F_PRIVATE 0x01 +#define IPVLAN_F_VEPA 0x02 + +/* VXLAN section */ +enum { + IFLA_VXLAN_UNSPEC, + IFLA_VXLAN_ID, + IFLA_VXLAN_GROUP, /* group or remote address */ + IFLA_VXLAN_LINK, + IFLA_VXLAN_LOCAL, + IFLA_VXLAN_TTL, + IFLA_VXLAN_TOS, + IFLA_VXLAN_LEARNING, + IFLA_VXLAN_AGEING, + IFLA_VXLAN_LIMIT, + IFLA_VXLAN_PORT_RANGE, /* source port */ + IFLA_VXLAN_PROXY, + IFLA_VXLAN_RSC, + IFLA_VXLAN_L2MISS, + IFLA_VXLAN_L3MISS, + IFLA_VXLAN_PORT, /* destination port */ + IFLA_VXLAN_GROUP6, + IFLA_VXLAN_LOCAL6, + IFLA_VXLAN_UDP_CSUM, + IFLA_VXLAN_UDP_ZERO_CSUM6_TX, + IFLA_VXLAN_UDP_ZERO_CSUM6_RX, + IFLA_VXLAN_REMCSUM_TX, + IFLA_VXLAN_REMCSUM_RX, + IFLA_VXLAN_GBP, + IFLA_VXLAN_REMCSUM_NOPARTIAL, + IFLA_VXLAN_COLLECT_METADATA, + IFLA_VXLAN_LABEL, + IFLA_VXLAN_GPE, + IFLA_VXLAN_TTL_INHERIT, + IFLA_VXLAN_DF, + __IFLA_VXLAN_MAX +}; +#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) + +struct ifla_vxlan_port_range { + __be16 low; + __be16 high; +}; + +enum ifla_vxlan_df { + VXLAN_DF_UNSET = 0, + VXLAN_DF_SET, + VXLAN_DF_INHERIT, + __VXLAN_DF_END, + VXLAN_DF_MAX = __VXLAN_DF_END - 1, +}; + +/* GENEVE section */ +enum { + IFLA_GENEVE_UNSPEC, + IFLA_GENEVE_ID, + IFLA_GENEVE_REMOTE, + IFLA_GENEVE_TTL, + IFLA_GENEVE_TOS, + IFLA_GENEVE_PORT, /* destination port */ + IFLA_GENEVE_COLLECT_METADATA, + IFLA_GENEVE_REMOTE6, + IFLA_GENEVE_UDP_CSUM, + IFLA_GENEVE_UDP_ZERO_CSUM6_TX, + IFLA_GENEVE_UDP_ZERO_CSUM6_RX, + IFLA_GENEVE_LABEL, + IFLA_GENEVE_TTL_INHERIT, + IFLA_GENEVE_DF, + __IFLA_GENEVE_MAX +}; +#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) + +enum ifla_geneve_df { + GENEVE_DF_UNSET = 0, + GENEVE_DF_SET, + GENEVE_DF_INHERIT, + __GENEVE_DF_END, + GENEVE_DF_MAX = __GENEVE_DF_END - 1, +}; + +/* PPP section */ +enum { + IFLA_PPP_UNSPEC, + IFLA_PPP_DEV_FD, + __IFLA_PPP_MAX +}; +#define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1) + +/* GTP section */ + +enum ifla_gtp_role { + GTP_ROLE_GGSN = 0, + GTP_ROLE_SGSN, +}; + +enum { + IFLA_GTP_UNSPEC, + IFLA_GTP_FD0, + IFLA_GTP_FD1, + IFLA_GTP_PDP_HASHSIZE, + IFLA_GTP_ROLE, + __IFLA_GTP_MAX, +}; +#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) + +/* Bonding section */ + +enum { + IFLA_BOND_UNSPEC, + IFLA_BOND_MODE, + IFLA_BOND_ACTIVE_SLAVE, + IFLA_BOND_MIIMON, + IFLA_BOND_UPDELAY, + IFLA_BOND_DOWNDELAY, + IFLA_BOND_USE_CARRIER, + IFLA_BOND_ARP_INTERVAL, + IFLA_BOND_ARP_IP_TARGET, + IFLA_BOND_ARP_VALIDATE, + IFLA_BOND_ARP_ALL_TARGETS, + IFLA_BOND_PRIMARY, + IFLA_BOND_PRIMARY_RESELECT, + IFLA_BOND_FAIL_OVER_MAC, + IFLA_BOND_XMIT_HASH_POLICY, + IFLA_BOND_RESEND_IGMP, + IFLA_BOND_NUM_PEER_NOTIF, + IFLA_BOND_ALL_SLAVES_ACTIVE, + IFLA_BOND_MIN_LINKS, + IFLA_BOND_LP_INTERVAL, + IFLA_BOND_PACKETS_PER_SLAVE, + IFLA_BOND_AD_LACP_RATE, + IFLA_BOND_AD_SELECT, + IFLA_BOND_AD_INFO, + IFLA_BOND_AD_ACTOR_SYS_PRIO, + IFLA_BOND_AD_USER_PORT_KEY, + IFLA_BOND_AD_ACTOR_SYSTEM, + IFLA_BOND_TLB_DYNAMIC_LB, + IFLA_BOND_PEER_NOTIF_DELAY, + __IFLA_BOND_MAX, +}; + +#define IFLA_BOND_MAX (__IFLA_BOND_MAX - 1) + +enum { + IFLA_BOND_AD_INFO_UNSPEC, + IFLA_BOND_AD_INFO_AGGREGATOR, + IFLA_BOND_AD_INFO_NUM_PORTS, + IFLA_BOND_AD_INFO_ACTOR_KEY, + IFLA_BOND_AD_INFO_PARTNER_KEY, + IFLA_BOND_AD_INFO_PARTNER_MAC, + __IFLA_BOND_AD_INFO_MAX, +}; + +#define IFLA_BOND_AD_INFO_MAX (__IFLA_BOND_AD_INFO_MAX - 1) + +enum { + IFLA_BOND_SLAVE_UNSPEC, + IFLA_BOND_SLAVE_STATE, + IFLA_BOND_SLAVE_MII_STATUS, + IFLA_BOND_SLAVE_LINK_FAILURE_COUNT, + IFLA_BOND_SLAVE_PERM_HWADDR, + IFLA_BOND_SLAVE_QUEUE_ID, + IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, + IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, + IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, + __IFLA_BOND_SLAVE_MAX, +}; + +#define IFLA_BOND_SLAVE_MAX (__IFLA_BOND_SLAVE_MAX - 1) + +/* SR-IOV virtual function management section */ + +enum { + IFLA_VF_INFO_UNSPEC, + IFLA_VF_INFO, + __IFLA_VF_INFO_MAX, +}; + +#define IFLA_VF_INFO_MAX (__IFLA_VF_INFO_MAX - 1) + +enum { + IFLA_VF_UNSPEC, + IFLA_VF_MAC, /* Hardware queue specific attributes */ + IFLA_VF_VLAN, /* VLAN ID and QoS */ + IFLA_VF_TX_RATE, /* Max TX Bandwidth Allocation */ + IFLA_VF_SPOOFCHK, /* Spoof Checking on/off switch */ + IFLA_VF_LINK_STATE, /* link state enable/disable/auto switch */ + IFLA_VF_RATE, /* Min and Max TX Bandwidth Allocation */ + IFLA_VF_RSS_QUERY_EN, /* RSS Redirection Table and Hash Key query + * on/off switch + */ + IFLA_VF_STATS, /* network device statistics */ + IFLA_VF_TRUST, /* Trust VF */ + IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */ + IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */ + IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */ + IFLA_VF_BROADCAST, /* VF broadcast */ + __IFLA_VF_MAX, +}; + +#define IFLA_VF_MAX (__IFLA_VF_MAX - 1) + +struct ifla_vf_mac { + __u32 vf; + __u8 mac[32]; /* MAX_ADDR_LEN */ +}; + +struct ifla_vf_broadcast { + __u8 broadcast[32]; +}; + +struct ifla_vf_vlan { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; +}; + +enum { + IFLA_VF_VLAN_INFO_UNSPEC, + IFLA_VF_VLAN_INFO, /* VLAN ID, QoS and VLAN protocol */ + __IFLA_VF_VLAN_INFO_MAX, +}; + +#define IFLA_VF_VLAN_INFO_MAX (__IFLA_VF_VLAN_INFO_MAX - 1) +#define MAX_VLAN_LIST_LEN 1 + +struct ifla_vf_vlan_info { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; + __be16 vlan_proto; /* VLAN protocol either 802.1Q or 802.1ad */ +}; + +struct ifla_vf_tx_rate { + __u32 vf; + __u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */ +}; + +struct ifla_vf_rate { + __u32 vf; + __u32 min_tx_rate; /* Min Bandwidth in Mbps */ + __u32 max_tx_rate; /* Max Bandwidth in Mbps */ +}; + +struct ifla_vf_spoofchk { + __u32 vf; + __u32 setting; +}; + +struct ifla_vf_guid { + __u32 vf; + __u64 guid; +}; + +enum { + IFLA_VF_LINK_STATE_AUTO, /* link state of the uplink */ + IFLA_VF_LINK_STATE_ENABLE, /* link always up */ + IFLA_VF_LINK_STATE_DISABLE, /* link always down */ + __IFLA_VF_LINK_STATE_MAX, +}; + +struct ifla_vf_link_state { + __u32 vf; + __u32 link_state; +}; + +struct ifla_vf_rss_query_en { + __u32 vf; + __u32 setting; +}; + +enum { + IFLA_VF_STATS_RX_PACKETS, + IFLA_VF_STATS_TX_PACKETS, + IFLA_VF_STATS_RX_BYTES, + IFLA_VF_STATS_TX_BYTES, + IFLA_VF_STATS_BROADCAST, + IFLA_VF_STATS_MULTICAST, + IFLA_VF_STATS_PAD, + IFLA_VF_STATS_RX_DROPPED, + IFLA_VF_STATS_TX_DROPPED, + __IFLA_VF_STATS_MAX, +}; + +#define IFLA_VF_STATS_MAX (__IFLA_VF_STATS_MAX - 1) + +struct ifla_vf_trust { + __u32 vf; + __u32 setting; +}; + +/* VF ports management section + * + * Nested layout of set/get msg is: + * + * [IFLA_NUM_VF] + * [IFLA_VF_PORTS] + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * ... + * [IFLA_PORT_SELF] + * [IFLA_PORT_*], ... + */ + +enum { + IFLA_VF_PORT_UNSPEC, + IFLA_VF_PORT, /* nest */ + __IFLA_VF_PORT_MAX, +}; + +#define IFLA_VF_PORT_MAX (__IFLA_VF_PORT_MAX - 1) + +enum { + IFLA_PORT_UNSPEC, + IFLA_PORT_VF, /* __u32 */ + IFLA_PORT_PROFILE, /* string */ + IFLA_PORT_VSI_TYPE, /* 802.1Qbg (pre-)standard VDP */ + IFLA_PORT_INSTANCE_UUID, /* binary UUID */ + IFLA_PORT_HOST_UUID, /* binary UUID */ + IFLA_PORT_REQUEST, /* __u8 */ + IFLA_PORT_RESPONSE, /* __u16, output only */ + __IFLA_PORT_MAX, +}; + +#define IFLA_PORT_MAX (__IFLA_PORT_MAX - 1) + +#define PORT_PROFILE_MAX 40 +#define PORT_UUID_MAX 16 +#define PORT_SELF_VF -1 + +enum { + PORT_REQUEST_PREASSOCIATE = 0, + PORT_REQUEST_PREASSOCIATE_RR, + PORT_REQUEST_ASSOCIATE, + PORT_REQUEST_DISASSOCIATE, +}; + +enum { + PORT_VDP_RESPONSE_SUCCESS = 0, + PORT_VDP_RESPONSE_INVALID_FORMAT, + PORT_VDP_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_VDP_RESPONSE_UNUSED_VTID, + PORT_VDP_RESPONSE_VTID_VIOLATION, + PORT_VDP_RESPONSE_VTID_VERSION_VIOALTION, + PORT_VDP_RESPONSE_OUT_OF_SYNC, + /* 0x08-0xFF reserved for future VDP use */ + PORT_PROFILE_RESPONSE_SUCCESS = 0x100, + PORT_PROFILE_RESPONSE_INPROGRESS, + PORT_PROFILE_RESPONSE_INVALID, + PORT_PROFILE_RESPONSE_BADSTATE, + PORT_PROFILE_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_PROFILE_RESPONSE_ERROR, +}; + +struct ifla_port_vsi { + __u8 vsi_mgr_id; + __u8 vsi_type_id[3]; + __u8 vsi_type_version; + __u8 pad[3]; +}; + + +/* IPoIB section */ + +enum { + IFLA_IPOIB_UNSPEC, + IFLA_IPOIB_PKEY, + IFLA_IPOIB_MODE, + IFLA_IPOIB_UMCAST, + __IFLA_IPOIB_MAX +}; + +enum { + IPOIB_MODE_DATAGRAM = 0, /* using unreliable datagram QPs */ + IPOIB_MODE_CONNECTED = 1, /* using connected QPs */ +}; + +#define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) + + +/* HSR section */ + +enum { + IFLA_HSR_UNSPEC, + IFLA_HSR_SLAVE1, + IFLA_HSR_SLAVE2, + IFLA_HSR_MULTICAST_SPEC, /* Last byte of supervision addr */ + IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ + IFLA_HSR_SEQ_NR, + IFLA_HSR_VERSION, /* HSR version */ + __IFLA_HSR_MAX, +}; + +#define IFLA_HSR_MAX (__IFLA_HSR_MAX - 1) + +/* STATS section */ + +struct if_stats_msg { + __u8 family; + __u8 pad1; + __u16 pad2; + __u32 ifindex; + __u32 filter_mask; +}; + +/* A stats attribute can be netdev specific or a global stat. + * For netdev stats, lets use the prefix IFLA_STATS_LINK_* + */ +enum { + IFLA_STATS_UNSPEC, /* also used as 64bit pad attribute */ + IFLA_STATS_LINK_64, + IFLA_STATS_LINK_XSTATS, + IFLA_STATS_LINK_XSTATS_SLAVE, + IFLA_STATS_LINK_OFFLOAD_XSTATS, + IFLA_STATS_AF_SPEC, + __IFLA_STATS_MAX, +}; + +#define IFLA_STATS_MAX (__IFLA_STATS_MAX - 1) + +#define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1)) + +/* These are embedded into IFLA_STATS_LINK_XSTATS: + * [IFLA_STATS_LINK_XSTATS] + * -> [LINK_XSTATS_TYPE_xxx] + * -> [rtnl link type specific attributes] + */ +enum { + LINK_XSTATS_TYPE_UNSPEC, + LINK_XSTATS_TYPE_BRIDGE, + LINK_XSTATS_TYPE_BOND, + __LINK_XSTATS_TYPE_MAX +}; +#define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1) + +/* These are stats embedded into IFLA_STATS_LINK_OFFLOAD_XSTATS */ +enum { + IFLA_OFFLOAD_XSTATS_UNSPEC, + IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */ + __IFLA_OFFLOAD_XSTATS_MAX +}; +#define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1) + +/* XDP section */ + +#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0) +#define XDP_FLAGS_SKB_MODE (1U << 1) +#define XDP_FLAGS_DRV_MODE (1U << 2) +#define XDP_FLAGS_HW_MODE (1U << 3) +#define XDP_FLAGS_MODES (XDP_FLAGS_SKB_MODE | \ + XDP_FLAGS_DRV_MODE | \ + XDP_FLAGS_HW_MODE) +#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \ + XDP_FLAGS_MODES) + +/* These are stored into IFLA_XDP_ATTACHED on dump. */ +enum { + XDP_ATTACHED_NONE = 0, + XDP_ATTACHED_DRV, + XDP_ATTACHED_SKB, + XDP_ATTACHED_HW, + XDP_ATTACHED_MULTI, +}; + +enum { + IFLA_XDP_UNSPEC, + IFLA_XDP_FD, + IFLA_XDP_ATTACHED, + IFLA_XDP_FLAGS, + IFLA_XDP_PROG_ID, + IFLA_XDP_DRV_PROG_ID, + IFLA_XDP_SKB_PROG_ID, + IFLA_XDP_HW_PROG_ID, + __IFLA_XDP_MAX, +}; + +#define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1) + +enum { + IFLA_EVENT_NONE, + IFLA_EVENT_REBOOT, /* internal reset / reboot */ + IFLA_EVENT_FEATURES, /* change in offload features */ + IFLA_EVENT_BONDING_FAILOVER, /* change in active slave */ + IFLA_EVENT_NOTIFY_PEERS, /* re-sent grat. arp/ndisc */ + IFLA_EVENT_IGMP_RESEND, /* re-sent IGMP JOIN */ + IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */ +}; + +/* tun section */ + +enum { + IFLA_TUN_UNSPEC, + IFLA_TUN_OWNER, + IFLA_TUN_GROUP, + IFLA_TUN_TYPE, + IFLA_TUN_PI, + IFLA_TUN_VNET_HDR, + IFLA_TUN_PERSIST, + IFLA_TUN_MULTI_QUEUE, + IFLA_TUN_NUM_QUEUES, + IFLA_TUN_NUM_DISABLED_QUEUES, + __IFLA_TUN_MAX, +}; + +#define IFLA_TUN_MAX (__IFLA_TUN_MAX - 1) + +/* rmnet section */ + +#define RMNET_FLAGS_INGRESS_DEAGGREGATION (1U << 0) +#define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1) +#define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2) +#define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3) + +enum { + IFLA_RMNET_UNSPEC, + IFLA_RMNET_MUX_ID, + IFLA_RMNET_FLAGS, + __IFLA_RMNET_MAX, +}; + +#define IFLA_RMNET_MAX (__IFLA_RMNET_MAX - 1) + +struct ifla_rmnet_flags { + __u32 flags; + __u32 mask; +}; + +#endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/src/contrib/libbpf/include/uapi/linux/if_xdp.h b/src/contrib/libbpf/include/uapi/linux/if_xdp.h new file mode 100644 index 0000000..be328c5 --- /dev/null +++ b/src/contrib/libbpf/include/uapi/linux/if_xdp.h @@ -0,0 +1,108 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * if_xdp: XDP socket user-space interface + * Copyright(c) 2018 Intel Corporation. + * + * Author(s): Björn Töpel <bjorn.topel@intel.com> + * Magnus Karlsson <magnus.karlsson@intel.com> + */ + +#ifndef _LINUX_IF_XDP_H +#define _LINUX_IF_XDP_H + +#include <linux/types.h> + +/* Options for the sxdp_flags field */ +#define XDP_SHARED_UMEM (1 << 0) +#define XDP_COPY (1 << 1) /* Force copy-mode */ +#define XDP_ZEROCOPY (1 << 2) /* Force zero-copy mode */ +/* If this option is set, the driver might go sleep and in that case + * the XDP_RING_NEED_WAKEUP flag in the fill and/or Tx rings will be + * set. If it is set, the application need to explicitly wake up the + * driver with a poll() (Rx and Tx) or sendto() (Tx only). If you are + * running the driver and the application on the same core, you should + * use this option so that the kernel will yield to the user space + * application. + */ +#define XDP_USE_NEED_WAKEUP (1 << 3) + +/* Flags for xsk_umem_config flags */ +#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0) + +struct sockaddr_xdp { + __u16 sxdp_family; + __u16 sxdp_flags; + __u32 sxdp_ifindex; + __u32 sxdp_queue_id; + __u32 sxdp_shared_umem_fd; +}; + +/* XDP_RING flags */ +#define XDP_RING_NEED_WAKEUP (1 << 0) + +struct xdp_ring_offset { + __u64 producer; + __u64 consumer; + __u64 desc; + __u64 flags; +}; + +struct xdp_mmap_offsets { + struct xdp_ring_offset rx; + struct xdp_ring_offset tx; + struct xdp_ring_offset fr; /* Fill */ + struct xdp_ring_offset cr; /* Completion */ +}; + +/* XDP socket options */ +#define XDP_MMAP_OFFSETS 1 +#define XDP_RX_RING 2 +#define XDP_TX_RING 3 +#define XDP_UMEM_REG 4 +#define XDP_UMEM_FILL_RING 5 +#define XDP_UMEM_COMPLETION_RING 6 +#define XDP_STATISTICS 7 +#define XDP_OPTIONS 8 + +struct xdp_umem_reg { + __u64 addr; /* Start of packet data area */ + __u64 len; /* Length of packet data area */ + __u32 chunk_size; + __u32 headroom; + __u32 flags; +}; + +struct xdp_statistics { + __u64 rx_dropped; /* Dropped for reasons other than invalid desc */ + __u64 rx_invalid_descs; /* Dropped due to invalid descriptor */ + __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ +}; + +struct xdp_options { + __u32 flags; +}; + +/* Flags for the flags field of struct xdp_options */ +#define XDP_OPTIONS_ZEROCOPY (1 << 0) + +/* Pgoff for mmaping the rings */ +#define XDP_PGOFF_RX_RING 0 +#define XDP_PGOFF_TX_RING 0x80000000 +#define XDP_UMEM_PGOFF_FILL_RING 0x100000000ULL +#define XDP_UMEM_PGOFF_COMPLETION_RING 0x180000000ULL + +/* Masks for unaligned chunks mode */ +#define XSK_UNALIGNED_BUF_OFFSET_SHIFT 48 +#define XSK_UNALIGNED_BUF_ADDR_MASK \ + ((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1) + +/* Rx/Tx descriptor */ +struct xdp_desc { + __u64 addr; + __u32 len; + __u32 options; +}; + +/* UMEM descriptor is __u64 */ + +#endif /* _LINUX_IF_XDP_H */ diff --git a/src/contrib/libbpf/include/uapi/linux/netlink.h b/src/contrib/libbpf/include/uapi/linux/netlink.h new file mode 100644 index 0000000..0a4d733 --- /dev/null +++ b/src/contrib/libbpf/include/uapi/linux/netlink.h @@ -0,0 +1,252 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_NETLINK_H +#define _UAPI__LINUX_NETLINK_H + +#include <linux/kernel.h> +#include <linux/socket.h> /* for __kernel_sa_family_t */ +#include <linux/types.h> + +#define NETLINK_ROUTE 0 /* Routing/device hook */ +#define NETLINK_UNUSED 1 /* Unused number */ +#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */ +#define NETLINK_FIREWALL 3 /* Unused number, formerly ip_queue */ +#define NETLINK_SOCK_DIAG 4 /* socket monitoring */ +#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */ +#define NETLINK_XFRM 6 /* ipsec */ +#define NETLINK_SELINUX 7 /* SELinux event notifications */ +#define NETLINK_ISCSI 8 /* Open-iSCSI */ +#define NETLINK_AUDIT 9 /* auditing */ +#define NETLINK_FIB_LOOKUP 10 +#define NETLINK_CONNECTOR 11 +#define NETLINK_NETFILTER 12 /* netfilter subsystem */ +#define NETLINK_IP6_FW 13 +#define NETLINK_DNRTMSG 14 /* DECnet routing messages */ +#define NETLINK_KOBJECT_UEVENT 15 /* Kernel messages to userspace */ +#define NETLINK_GENERIC 16 +/* leave room for NETLINK_DM (DM Events) */ +#define NETLINK_SCSITRANSPORT 18 /* SCSI Transports */ +#define NETLINK_ECRYPTFS 19 +#define NETLINK_RDMA 20 +#define NETLINK_CRYPTO 21 /* Crypto layer */ +#define NETLINK_SMC 22 /* SMC monitoring */ + +#define NETLINK_INET_DIAG NETLINK_SOCK_DIAG + +#define MAX_LINKS 32 + +struct sockaddr_nl { + __kernel_sa_family_t nl_family; /* AF_NETLINK */ + unsigned short nl_pad; /* zero */ + __u32 nl_pid; /* port ID */ + __u32 nl_groups; /* multicast groups mask */ +}; + +struct nlmsghdr { + __u32 nlmsg_len; /* Length of message including header */ + __u16 nlmsg_type; /* Message content */ + __u16 nlmsg_flags; /* Additional flags */ + __u32 nlmsg_seq; /* Sequence number */ + __u32 nlmsg_pid; /* Sending process port ID */ +}; + +/* Flags values */ + +#define NLM_F_REQUEST 0x01 /* It is request message. */ +#define NLM_F_MULTI 0x02 /* Multipart message, terminated by NLMSG_DONE */ +#define NLM_F_ACK 0x04 /* Reply with ack, with zero or error code */ +#define NLM_F_ECHO 0x08 /* Echo this request */ +#define NLM_F_DUMP_INTR 0x10 /* Dump was inconsistent due to sequence change */ +#define NLM_F_DUMP_FILTERED 0x20 /* Dump was filtered as requested */ + +/* Modifiers to GET request */ +#define NLM_F_ROOT 0x100 /* specify tree root */ +#define NLM_F_MATCH 0x200 /* return all matching */ +#define NLM_F_ATOMIC 0x400 /* atomic GET */ +#define NLM_F_DUMP (NLM_F_ROOT|NLM_F_MATCH) + +/* Modifiers to NEW request */ +#define NLM_F_REPLACE 0x100 /* Override existing */ +#define NLM_F_EXCL 0x200 /* Do not touch, if it exists */ +#define NLM_F_CREATE 0x400 /* Create, if it does not exist */ +#define NLM_F_APPEND 0x800 /* Add to end of list */ + +/* Modifiers to DELETE request */ +#define NLM_F_NONREC 0x100 /* Do not delete recursively */ + +/* Flags for ACK message */ +#define NLM_F_CAPPED 0x100 /* request was capped */ +#define NLM_F_ACK_TLVS 0x200 /* extended ACK TVLs were included */ + +/* + 4.4BSD ADD NLM_F_CREATE|NLM_F_EXCL + 4.4BSD CHANGE NLM_F_REPLACE + + True CHANGE NLM_F_CREATE|NLM_F_REPLACE + Append NLM_F_CREATE + Check NLM_F_EXCL + */ + +#define NLMSG_ALIGNTO 4U +#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) ) +#define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr))) +#define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN) +#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len)) +#define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0))) +#define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \ + (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len))) +#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \ + (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \ + (nlh)->nlmsg_len <= (len)) +#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len))) + +#define NLMSG_NOOP 0x1 /* Nothing. */ +#define NLMSG_ERROR 0x2 /* Error */ +#define NLMSG_DONE 0x3 /* End of a dump */ +#define NLMSG_OVERRUN 0x4 /* Data lost */ + +#define NLMSG_MIN_TYPE 0x10 /* < 0x10: reserved control messages */ + +struct nlmsgerr { + int error; + struct nlmsghdr msg; + /* + * followed by the message contents unless NETLINK_CAP_ACK was set + * or the ACK indicates success (error == 0) + * message length is aligned with NLMSG_ALIGN() + */ + /* + * followed by TLVs defined in enum nlmsgerr_attrs + * if NETLINK_EXT_ACK was set + */ +}; + +/** + * enum nlmsgerr_attrs - nlmsgerr attributes + * @NLMSGERR_ATTR_UNUSED: unused + * @NLMSGERR_ATTR_MSG: error message string (string) + * @NLMSGERR_ATTR_OFFS: offset of the invalid attribute in the original + * message, counting from the beginning of the header (u32) + * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to + * be used - in the success case - to identify a created + * object or operation or similar (binary) + * @__NLMSGERR_ATTR_MAX: number of attributes + * @NLMSGERR_ATTR_MAX: highest attribute number + */ +enum nlmsgerr_attrs { + NLMSGERR_ATTR_UNUSED, + NLMSGERR_ATTR_MSG, + NLMSGERR_ATTR_OFFS, + NLMSGERR_ATTR_COOKIE, + + __NLMSGERR_ATTR_MAX, + NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1 +}; + +#define NETLINK_ADD_MEMBERSHIP 1 +#define NETLINK_DROP_MEMBERSHIP 2 +#define NETLINK_PKTINFO 3 +#define NETLINK_BROADCAST_ERROR 4 +#define NETLINK_NO_ENOBUFS 5 +#ifndef __KERNEL__ +#define NETLINK_RX_RING 6 +#define NETLINK_TX_RING 7 +#endif +#define NETLINK_LISTEN_ALL_NSID 8 +#define NETLINK_LIST_MEMBERSHIPS 9 +#define NETLINK_CAP_ACK 10 +#define NETLINK_EXT_ACK 11 +#define NETLINK_GET_STRICT_CHK 12 + +struct nl_pktinfo { + __u32 group; +}; + +struct nl_mmap_req { + unsigned int nm_block_size; + unsigned int nm_block_nr; + unsigned int nm_frame_size; + unsigned int nm_frame_nr; +}; + +struct nl_mmap_hdr { + unsigned int nm_status; + unsigned int nm_len; + __u32 nm_group; + /* credentials */ + __u32 nm_pid; + __u32 nm_uid; + __u32 nm_gid; +}; + +#ifndef __KERNEL__ +enum nl_mmap_status { + NL_MMAP_STATUS_UNUSED, + NL_MMAP_STATUS_RESERVED, + NL_MMAP_STATUS_VALID, + NL_MMAP_STATUS_COPY, + NL_MMAP_STATUS_SKIP, +}; + +#define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO +#define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT) +#define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr)) +#endif + +#define NET_MAJOR 36 /* Major 36 is reserved for networking */ + +enum { + NETLINK_UNCONNECTED = 0, + NETLINK_CONNECTED, +}; + +/* + * <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)--> + * +---------------------+- - -+- - - - - - - - - -+- - -+ + * | Header | Pad | Payload | Pad | + * | (struct nlattr) | ing | | ing | + * +---------------------+- - -+- - - - - - - - - -+- - -+ + * <-------------- nlattr->nla_len --------------> + */ + +struct nlattr { + __u16 nla_len; + __u16 nla_type; +}; + +/* + * nla_type (16 bits) + * +---+---+-------------------------------+ + * | N | O | Attribute Type | + * +---+---+-------------------------------+ + * N := Carries nested attributes + * O := Payload stored in network byte order + * + * Note: The N and O flag are mutually exclusive. + */ +#define NLA_F_NESTED (1 << 15) +#define NLA_F_NET_BYTEORDER (1 << 14) +#define NLA_TYPE_MASK ~(NLA_F_NESTED | NLA_F_NET_BYTEORDER) + +#define NLA_ALIGNTO 4 +#define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1)) +#define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr))) + +/* Generic 32 bitflags attribute content sent to the kernel. + * + * The value is a bitmap that defines the values being set + * The selector is a bitmask that defines which value is legit + * + * Examples: + * value = 0x0, and selector = 0x1 + * implies we are selecting bit 1 and we want to set its value to 0. + * + * value = 0x2, and selector = 0x2 + * implies we are selecting bit 2 and we want to set its value to 1. + * + */ +struct nla_bitfield32 { + __u32 value; + __u32 selector; +}; + +#endif /* _UAPI__LINUX_NETLINK_H */ |