2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2025-01-08 21:53:54 +08:00
linux-next/tools/lib/bpf/bpf.c
Alexei Starovoitov f75a697e09 libbpf: Auto-detect btf_id of BTF-based raw_tracepoints
It's a responsiblity of bpf program author to annotate the program
with SEC("tp_btf/name") where "name" is a valid raw tracepoint.
The libbpf will try to find "name" in vmlinux BTF and error out
in case vmlinux BTF is not available or "name" is not found.
If "name" is indeed a valid raw tracepoint then in-kernel BTF
will have "btf_trace_##name" typedef that points to function
prototype of that raw tracepoint. BTF description captures
exact argument the kernel C code is passing into raw tracepoint.
The kernel verifier will check the types while loading bpf program.

libbpf keeps BTF type id in expected_attach_type, but since
kernel ignores this attribute for tracing programs copy it
into attach_btf_id attribute before loading.

Later the kernel will use prog->attach_btf_id to select raw tracepoint
during bpf_raw_tracepoint_open syscall command.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20191016032505.2089704-6-ast@kernel.org
2019-10-17 16:44:35 +02:00

709 lines
18 KiB
C

// 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 = 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_RAW_TRACEPOINT)
/* expected_attach_type is ignored for tracing progs */
attr.attach_btf_id = attr.expected_attach_type;
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.kern_version = load_attr->kern_version;
attr.prog_ifindex = load_attr->prog_ifindex;
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;
}