mirror/libbpf
1
0
Fork 0
mirror of https://github.com/netdata/libbpf.git synced 2026-03-20 08:19:07 +08:00
Code Issues Packages Projects Releases Wiki Activity

Revert BPF token-related functionality

Browse Source 
This patch includes the following revert (one  conflicting BPF FS
patch and three token patch sets, represented by merge commits):
  - revert 0f5d5454c723 "Merge branch 'bpf-fs-mount-options-parsing-follow-ups'";
  - revert 750e785796bb "bpf: Support uid and gid when mounting bpffs";
  - revert 733763285acf "Merge branch 'bpf-token-support-in-libbpf-s-bpf-object'";
  - revert c35919dcce28 "Merge branch 'bpf-token-and-bpf-fs-based-delegation'".

Link: https://lore.kernel.org/bpf/CAHk-=wg7JuFYwGy=GOMbRCtOL+jwSQsdUaBsRWkDVYbxipbM5A@mail.gmail.com
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
This commit is contained in:
Andrii Nakryiko
2023-12-19 07:37:35 -08:00
committed by Andrii Nakryiko
parent 43e7309228
commit c65b319c04
12 changed files with 477 additions and 782 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
include/uapi/linux/bpf.h
View File

@@ -847,36 +847,6 @@ union bpf_iter_link_info {
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*
* BPF_TOKEN_CREATE
* Description
* Create BPF token with embedded information about what
* BPF-related functionality it allows:
* - a set of allowed bpf() syscall commands;
* - a set of allowed BPF map types to be created with
* BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed;
* - a set of allowed BPF program types and BPF program attach
* types to be loaded with BPF_PROG_LOAD command, if
* BPF_PROG_LOAD itself is allowed.
*
* BPF token is created (derived) from an instance of BPF FS,
* assuming it has necessary delegation mount options specified.
* This BPF token can be passed as an extra parameter to various
* bpf() syscall commands to grant BPF subsystem functionality to
* unprivileged processes.
*
* When created, BPF token is "associated" with the owning
* user namespace of BPF FS instance (super block) that it was
* derived from, and subsequent BPF operations performed with
* BPF token would be performing capabilities checks (i.e.,
* CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within
* that user namespace. Without BPF token, such capabilities
* have to be granted in init user namespace, making bpf()
* syscall incompatible with user namespace, for the most part.
*
* Return
* A new file descriptor (a nonnegative integer), or -1 if an
* error occurred (in which case, *errno* is set appropriately).
*
* NOTES
* eBPF objects (maps and programs) can be shared between processes.
*
@@ -931,8 +901,6 @@ enum bpf_cmd {
BPF_ITER_CREATE,
BPF_LINK_DETACH,
BPF_PROG_BIND_MAP,
BPF_TOKEN_CREATE,
__MAX_BPF_CMD,
};
enum bpf_map_type {
@@ -983,7 +951,6 @@ enum bpf_map_type {
BPF_MAP_TYPE_BLOOM_FILTER,
BPF_MAP_TYPE_USER_RINGBUF,
BPF_MAP_TYPE_CGRP_STORAGE,
__MAX_BPF_MAP_TYPE
};
/* Note that tracing related programs such as
@@ -1028,7 +995,6 @@ enum bpf_prog_type {
BPF_PROG_TYPE_SK_LOOKUP,
BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
BPF_PROG_TYPE_NETFILTER,
__MAX_BPF_PROG_TYPE
};
enum bpf_attach_type {
@@ -1437,7 +1403,6 @@ union bpf_attr {
* to using 5 hash functions).
*/
__u64 map_extra;
__u32 map_token_fd;
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -1507,7 +1472,6 @@ union bpf_attr {
* truncated), or smaller (if log buffer wasn't filled completely).
*/
__u32 log_true_size;
__u32 prog_token_fd;
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -1620,7 +1584,6 @@ union bpf_attr {
* truncated), or smaller (if log buffer wasn't filled completely).
*/
__u32 btf_log_true_size;
__u32 btf_token_fd;
};
struct {
@@ -1751,11 +1714,6 @@ union bpf_attr {
__u32 flags; /* extra flags */
} prog_bind_map;
struct { /* struct used by BPF_TOKEN_CREATE command */
__u32 flags;
__u32 bpffs_fd;
} token_create;
} __attribute__((aligned(8)));
/* The description below is an attempt at providing documentation to eBPF

37
src/bpf.c
View File

@@ -103,7 +103,7 @@ int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts)
* [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/
* [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper")
*/
int probe_memcg_account(int token_fd)
int probe_memcg_account(void)
{
const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
struct bpf_insn insns[] = {
@@ -120,7 +120,6 @@ int probe_memcg_account(int token_fd)
attr.insns = ptr_to_u64(insns);
attr.insn_cnt = insn_cnt;
attr.license = ptr_to_u64("GPL");
attr.prog_token_fd = token_fd;
prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz);
if (prog_fd >= 0) {
@@ -147,7 +146,7 @@ int bump_rlimit_memlock(void)
struct rlimit rlim;
/* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */
if (memlock_bumped || feat_supported(NULL, FEAT_MEMCG_ACCOUNT))
if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT))
return 0;
memlock_bumped = true;
@@ -170,7 +169,7 @@ int bpf_map_create(enum bpf_map_type map_type,
__u32 max_entries,
const struct bpf_map_create_opts *opts)
{
const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd);
const size_t attr_sz = offsetofend(union bpf_attr, map_extra);
union bpf_attr attr;
int fd;
@@ -182,7 +181,7 @@ int bpf_map_create(enum bpf_map_type map_type,
return libbpf_err(-EINVAL);
attr.map_type = map_type;
if (map_name && feat_supported(NULL, FEAT_PROG_NAME))
if (map_name && kernel_supports(NULL, FEAT_PROG_NAME))
libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
attr.key_size = key_size;
attr.value_size = value_size;
@@ -199,8 +198,6 @@ int bpf_map_create(enum bpf_map_type map_type,
attr.numa_node = OPTS_GET(opts, numa_node, 0);
attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0);
attr.map_token_fd = OPTS_GET(opts, token_fd, 0);
fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz);
return libbpf_err_errno(fd);
}
@@ -235,7 +232,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
const struct bpf_insn *insns, size_t insn_cnt,
struct bpf_prog_load_opts *opts)
{
const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd);
const size_t attr_sz = offsetofend(union bpf_attr, log_true_size);
void *finfo = NULL, *linfo = NULL;
const char *func_info, *line_info;
__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
@@ -264,9 +261,8 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
attr.prog_flags = OPTS_GET(opts, prog_flags, 0);
attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0);
attr.kern_version = OPTS_GET(opts, kern_version, 0);
attr.prog_token_fd = OPTS_GET(opts, token_fd, 0);
if (prog_name && feat_supported(NULL, FEAT_PROG_NAME))
if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME))
libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
attr.license = ptr_to_u64(license);
@@ -1186,7 +1182,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts)
{
const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd);
const size_t attr_sz = offsetofend(union bpf_attr, btf_log_true_size);
union bpf_attr attr;
char *log_buf;
size_t log_size;
@@ -1211,8 +1207,6 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts
attr.btf = ptr_to_u64(btf_data);
attr.btf_size = btf_size;
attr.btf_token_fd = OPTS_GET(opts, token_fd, 0);
/* log_level == 0 and log_buf != NULL means "try loading without
* log_buf, but retry with log_buf and log_level=1 on error", which is
* consistent across low-level and high-level BTF and program loading
@@ -1293,20 +1287,3 @@ int bpf_prog_bind_map(int prog_fd, int map_fd,
ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz);
return libbpf_err_errno(ret);
}
int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts)
{
const size_t attr_sz = offsetofend(union bpf_attr, token_create);
union bpf_attr attr;
int fd;
if (!OPTS_VALID(opts, bpf_token_create_opts))
return libbpf_err(-EINVAL);
memset(&attr, 0, attr_sz);
attr.token_create.bpffs_fd = bpffs_fd;
attr.token_create.flags = OPTS_GET(opts, flags, 0);
fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz);
return libbpf_err_errno(fd);
}

35
src/bpf.h
View File

@@ -51,11 +51,8 @@ struct bpf_map_create_opts {
__u32 numa_node;
__u32 map_ifindex;
__u32 token_fd;
size_t :0;
};
#define bpf_map_create_opts__last_field token_fd
#define bpf_map_create_opts__last_field map_ifindex
LIBBPF_API int bpf_map_create(enum bpf_map_type map_type,
const char *map_name,
@@ -105,10 +102,9 @@ struct bpf_prog_load_opts {
* If kernel doesn't support this feature, log_size is left unchanged.
*/
__u32 log_true_size;
__u32 token_fd;
size_t :0;
};
#define bpf_prog_load_opts__last_field token_fd
#define bpf_prog_load_opts__last_field log_true_size
LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type,
const char *prog_name, const char *license,
@@ -134,10 +130,9 @@ struct bpf_btf_load_opts {
* If kernel doesn't support this feature, log_size is left unchanged.
*/
__u32 log_true_size;
__u32 token_fd;
size_t :0;
};
#define bpf_btf_load_opts__last_field token_fd
#define bpf_btf_load_opts__last_field log_true_size
LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size,
struct bpf_btf_load_opts *opts);
@@ -645,30 +640,6 @@ struct bpf_test_run_opts {
LIBBPF_API int bpf_prog_test_run_opts(int prog_fd,
struct bpf_test_run_opts *opts);
struct bpf_token_create_opts {
size_t sz; /* size of this struct for forward/backward compatibility */
__u32 flags;
size_t :0;
};
#define bpf_token_create_opts__last_field flags
/**
* @brief **bpf_token_create()** creates a new instance of BPF token derived
* from specified BPF FS mount point.
*
* BPF token created with this API can be passed to bpf() syscall for
* commands like BPF_PROG_LOAD, BPF_MAP_CREATE, etc.
*
* @param bpffs_fd FD for BPF FS instance from which to derive a BPF token
* instance.
* @param opts optional BPF token creation options, can be NULL
*
* @return BPF token FD > 0, on success; negative error code, otherwise (errno
* is also set to the error code)
*/
LIBBPF_API int bpf_token_create(int bpffs_fd,
struct bpf_token_create_opts *opts);
#ifdef __cplusplus
} /* extern "C" */
#endif

7
src/btf.c
View File

@@ -1317,9 +1317,7 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf)
static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian);
int btf_load_into_kernel(struct btf *btf,
char *log_buf, size_t log_sz, __u32 log_level,
int token_fd)
int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level)
{
LIBBPF_OPTS(bpf_btf_load_opts, opts);
__u32 buf_sz = 0, raw_size;
@@ -1369,7 +1367,6 @@ retry_load:
opts.log_level = log_level;
}
opts.token_fd = token_fd;
btf->fd = bpf_btf_load(raw_data, raw_size, &opts);
if (btf->fd < 0) {
/* time to turn on verbose mode and try again */
@@ -1397,7 +1394,7 @@ done:
int btf__load_into_kernel(struct btf *btf)
{
return btf_load_into_kernel(btf, NULL, 0, 0, 0);
return btf_load_into_kernel(btf, NULL, 0, 0);
}
int btf__fd(const struct btf *btf)

2
src/elf.c
View File

@@ -11,6 +11,8 @@
#include "libbpf_internal.h"
#include "str_error.h"
#define STRERR_BUFSIZE 128
/* A SHT_GNU_versym section holds 16-bit words. This bit is set if
* the symbol is hidden and can only be seen when referenced using an
* explicit version number. This is a GNU extension.

478
src/features.c
View File

@@ -1,478 +0,0 @@
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
#include <linux/kernel.h>
#include <linux/filter.h>
#include "bpf.h"
#include "libbpf.h"
#include "libbpf_common.h"
#include "libbpf_internal.h"
#include "str_error.h"
static inline __u64 ptr_to_u64(const void *ptr)
{
return (__u64)(unsigned long)ptr;
}
static int probe_fd(int fd)
{
if (fd >= 0)
close(fd);
return fd >= 0;
}
static int probe_kern_prog_name(int token_fd)
{
const size_t attr_sz = offsetofend(union bpf_attr, prog_name);
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
union bpf_attr attr;
int ret;
memset(&attr, 0, attr_sz);
attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
attr.license = ptr_to_u64("GPL");
attr.insns = ptr_to_u64(insns);
attr.insn_cnt = (__u32)ARRAY_SIZE(insns);
attr.prog_token_fd = token_fd;
libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name));
/* make sure loading with name works */
ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS);
return probe_fd(ret);
}
static int probe_kern_global_data(int token_fd)
{
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(),
};
LIBBPF_OPTS(bpf_map_create_opts, map_opts, .token_fd = token_fd);
LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, .token_fd = token_fd);
int ret, map, insn_cnt = ARRAY_SIZE(insns);
map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, &map_opts);
if (map < 0) {
ret = -errno;
cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
__func__, cp, -ret);
return ret;
}
insns[0].imm = map;
ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
close(map);
return probe_fd(ret);
}
static int probe_kern_btf(int token_fd)
{
static const char strs[] = "\0int";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_btf_func(int token_fd)
{
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),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_btf_func_global(int token_fd)
{
static const char strs[] = "\0int\0x\0a";
/* static 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 BTF_FUNC_GLOBAL */ /* [3] */
BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_btf_datasec(int token_fd)
{
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),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_btf_float(int token_fd)
{
static const char strs[] = "\0float";
__u32 types[] = {
/* float */
BTF_TYPE_FLOAT_ENC(1, 4),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_btf_decl_tag(int token_fd)
{
static const char strs[] = "\0tag";
__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,
/* attr */
BTF_TYPE_DECL_TAG_ENC(1, 2, -1),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_btf_type_tag(int token_fd)
{
static const char strs[] = "\0tag";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* attr */
BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */
/* ptr */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
static int probe_kern_array_mmap(int token_fd)
{
LIBBPF_OPTS(bpf_map_create_opts, opts,
.map_flags = BPF_F_MMAPABLE,
.token_fd = token_fd,
);
int fd;
fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts);
return probe_fd(fd);
}
static int probe_kern_exp_attach_type(int token_fd)
{
LIBBPF_OPTS(bpf_prog_load_opts, opts,
.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
.token_fd = token_fd,
);
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
int fd, insn_cnt = ARRAY_SIZE(insns);
/* use any valid combination of program type and (optional)
* non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS)
* to see if kernel supports expected_attach_type field for
* BPF_PROG_LOAD command
*/
fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts);
return probe_fd(fd);
}
static int probe_kern_probe_read_kernel(int token_fd)
{
LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd);
struct bpf_insn insns[] = {
BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */
BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */
BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
};
int fd, insn_cnt = ARRAY_SIZE(insns);
fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
return probe_fd(fd);
}
static int probe_prog_bind_map(int token_fd)
{
char *cp, errmsg[STRERR_BUFSIZE];
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
LIBBPF_OPTS(bpf_map_create_opts, map_opts, .token_fd = token_fd);
LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, .token_fd = token_fd);
int ret, map, prog, insn_cnt = ARRAY_SIZE(insns);
map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, &map_opts);
if (map < 0) {
ret = -errno;
cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
__func__, cp, -ret);
return ret;
}
prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
if (prog < 0) {
close(map);
return 0;
}
ret = bpf_prog_bind_map(prog, map, NULL);
close(map);
close(prog);
return ret >= 0;
}
static int probe_module_btf(int token_fd)
{
static const char strs[] = "\0int";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
};
struct bpf_btf_info info;
__u32 len = sizeof(info);
char name[16];
int fd, err;
fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), token_fd);
if (fd < 0)
return 0; /* BTF not supported at all */
memset(&info, 0, sizeof(info));
info.name = ptr_to_u64(name);
info.name_len = sizeof(name);
/* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer;
* kernel's module BTF support coincides with support for
* name/name_len fields in struct bpf_btf_info.
*/
err = bpf_btf_get_info_by_fd(fd, &info, &len);
close(fd);
return !err;
}
static int probe_perf_link(int token_fd)
{
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd);
int prog_fd, link_fd, err;
prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL",
insns, ARRAY_SIZE(insns), &opts);
if (prog_fd < 0)
return -errno;
/* use invalid perf_event FD to get EBADF, if link is supported;
* otherwise EINVAL should be returned
*/
link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL);
err = -errno; /* close() can clobber errno */
if (link_fd >= 0)
close(link_fd);
close(prog_fd);
return link_fd < 0 && err == -EBADF;
}
static int probe_uprobe_multi_link(int token_fd)
{
LIBBPF_OPTS(bpf_prog_load_opts, load_opts,
.expected_attach_type = BPF_TRACE_UPROBE_MULTI,
.token_fd = token_fd,
);
LIBBPF_OPTS(bpf_link_create_opts, link_opts);
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
int prog_fd, link_fd, err;
unsigned long offset = 0;
prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL",
insns, ARRAY_SIZE(insns), &load_opts);
if (prog_fd < 0)
return -errno;
/* Creating uprobe in '/' binary should fail with -EBADF. */
link_opts.uprobe_multi.path = "/";
link_opts.uprobe_multi.offsets = &offset;
link_opts.uprobe_multi.cnt = 1;
link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
err = -errno; /* close() can clobber errno */
if (link_fd >= 0)
close(link_fd);
close(prog_fd);
return link_fd < 0 && err == -EBADF;
}
static int probe_kern_bpf_cookie(int token_fd)
{
struct bpf_insn insns[] = {
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie),
BPF_EXIT_INSN(),
};
LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd);
int ret, insn_cnt = ARRAY_SIZE(insns);
ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
return probe_fd(ret);
}
static int probe_kern_btf_enum64(int token_fd)
{
static const char strs[] = "\0enum64";
__u32 types[] = {
BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), token_fd));
}
typedef int (*feature_probe_fn)(int /* token_fd */);
static struct kern_feature_cache feature_cache;
static struct kern_feature_desc {
const char *desc;
feature_probe_fn probe;
} feature_probes[__FEAT_CNT] = {
[FEAT_PROG_NAME] = {
"BPF program name", probe_kern_prog_name,
},
[FEAT_GLOBAL_DATA] = {
"global variables", probe_kern_global_data,
},
[FEAT_BTF] = {
"minimal BTF", probe_kern_btf,
},
[FEAT_BTF_FUNC] = {
"BTF functions", probe_kern_btf_func,
},
[FEAT_BTF_GLOBAL_FUNC] = {
"BTF global function", probe_kern_btf_func_global,
},
[FEAT_BTF_DATASEC] = {
"BTF data section and variable", probe_kern_btf_datasec,
},
[FEAT_ARRAY_MMAP] = {
"ARRAY map mmap()", probe_kern_array_mmap,
},
[FEAT_EXP_ATTACH_TYPE] = {
"BPF_PROG_LOAD expected_attach_type attribute",
probe_kern_exp_attach_type,
},
[FEAT_PROBE_READ_KERN] = {
"bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel,
},
[FEAT_PROG_BIND_MAP] = {
"BPF_PROG_BIND_MAP support", probe_prog_bind_map,
},
[FEAT_MODULE_BTF] = {
"module BTF support", probe_module_btf,
},
[FEAT_BTF_FLOAT] = {
"BTF_KIND_FLOAT support", probe_kern_btf_float,
},
[FEAT_PERF_LINK] = {
"BPF perf link support", probe_perf_link,
},
[FEAT_BTF_DECL_TAG] = {
"BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag,
},
[FEAT_BTF_TYPE_TAG] = {
"BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag,
},
[FEAT_MEMCG_ACCOUNT] = {
"memcg-based memory accounting", probe_memcg_account,
},
[FEAT_BPF_COOKIE] = {
"BPF cookie support", probe_kern_bpf_cookie,
},
[FEAT_BTF_ENUM64] = {
"BTF_KIND_ENUM64 support", probe_kern_btf_enum64,
},
[FEAT_SYSCALL_WRAPPER] = {
"Kernel using syscall wrapper", probe_kern_syscall_wrapper,
},
[FEAT_UPROBE_MULTI_LINK] = {
"BPF multi-uprobe link support", probe_uprobe_multi_link,
},
};
bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id)
{
struct kern_feature_desc *feat = &feature_probes[feat_id];
int ret;
/* assume global feature cache, unless custom one is provided */
if (!cache)
cache = &feature_cache;
if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) {
ret = feat->probe(cache->token_fd);
if (ret > 0) {
WRITE_ONCE(cache->res[feat_id], FEAT_SUPPORTED);
} else if (ret == 0) {
WRITE_ONCE(cache->res[feat_id], FEAT_MISSING);
} else {
pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret);
WRITE_ONCE(cache->res[feat_id], FEAT_MISSING);
}
}
return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED;
}

573
src/libbpf.c
View File

@@ -59,8 +59,6 @@
#define BPF_FS_MAGIC 0xcafe4a11
#endif
#define BPF_FS_DEFAULT_PATH "/sys/fs/bpf"
#define BPF_INSN_SZ (sizeof(struct bpf_insn))
/* vsprintf() in __base_pr() uses nonliteral format string. It may break
@@ -695,10 +693,6 @@ struct bpf_object {
struct usdt_manager *usdt_man;
struct kern_feature_cache *feat_cache;
char *token_path;
int token_fd;
char path[];
};
@@ -2198,7 +2192,7 @@ static int build_map_pin_path(struct bpf_map *map, const char *path)
int err;
if (!path)
path = BPF_FS_DEFAULT_PATH;
path = "/sys/fs/bpf";
err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map));
if (err)
@@ -3285,7 +3279,7 @@ skip_exception_cb:
} else {
/* currently BPF_BTF_LOAD only supports log_level 1 */
err = btf_load_into_kernel(kern_btf, obj->log_buf, obj->log_size,
obj->log_level ? 1 : 0, obj->token_fd);
obj->log_level ? 1 : 0);
}
if (sanitize) {
if (!err) {
@@ -4608,63 +4602,6 @@ int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries)
return 0;
}
static int bpf_object_prepare_token(struct bpf_object *obj)
{
const char *bpffs_path;
int bpffs_fd = -1, token_fd, err;
bool mandatory;
enum libbpf_print_level level;
/* token is already set up */
if (obj->token_fd > 0)
return 0;
/* token is explicitly prevented */
if (obj->token_fd < 0) {
pr_debug("object '%s': token is prevented, skipping...\n", obj->name);
/* reset to zero to avoid extra checks during map_create and prog_load steps */
obj->token_fd = 0;
return 0;
}
mandatory = obj->token_path != NULL;
level = mandatory ? LIBBPF_WARN : LIBBPF_DEBUG;
bpffs_path = obj->token_path ?: BPF_FS_DEFAULT_PATH;
bpffs_fd = open(bpffs_path, O_DIRECTORY, O_RDWR);
if (bpffs_fd < 0) {
err = -errno;
__pr(level, "object '%s': failed (%d) to open BPF FS mount at '%s'%s\n",
obj->name, err, bpffs_path,
mandatory ? "" : ", skipping optional step...");
return mandatory ? err : 0;
}
token_fd = bpf_token_create(bpffs_fd, 0);
close(bpffs_fd);
if (token_fd < 0) {
if (!mandatory && token_fd == -ENOENT) {
pr_debug("object '%s': BPF FS at '%s' doesn't have BPF token delegation set up, skipping...\n",
obj->name, bpffs_path);
return 0;
}
__pr(level, "object '%s': failed (%d) to create BPF token from '%s'%s\n",
obj->name, token_fd, bpffs_path,
mandatory ? "" : ", skipping optional step...");
return mandatory ? token_fd : 0;
}
obj->feat_cache = calloc(1, sizeof(*obj->feat_cache));
if (!obj->feat_cache) {
close(token_fd);
return -ENOMEM;
}
obj->token_fd = token_fd;
obj->feat_cache->token_fd = token_fd;
return 0;
}
static int
bpf_object__probe_loading(struct bpf_object *obj)
{
@@ -4674,7 +4611,6 @@ bpf_object__probe_loading(struct bpf_object *obj)
BPF_EXIT_INSN(),
};
int ret, insn_cnt = ARRAY_SIZE(insns);
LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = obj->token_fd);
if (obj->gen_loader)
return 0;
@@ -4684,9 +4620,9 @@ bpf_object__probe_loading(struct bpf_object *obj)
pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret);
/* make sure basic loading works */
ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &opts);
ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL);
if (ret < 0)
ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL);
if (ret < 0) {
ret = errno;
cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
@@ -4701,18 +4637,462 @@ bpf_object__probe_loading(struct bpf_object *obj)
return 0;
}
static int probe_fd(int fd)
{
if (fd >= 0)
close(fd);
return fd >= 0;
}
static int probe_kern_prog_name(void)
{
const size_t attr_sz = offsetofend(union bpf_attr, prog_name);
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
union bpf_attr attr;
int ret;
memset(&attr, 0, attr_sz);
attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
attr.license = ptr_to_u64("GPL");
attr.insns = ptr_to_u64(insns);
attr.insn_cnt = (__u32)ARRAY_SIZE(insns);
libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name));
/* make sure loading with name works */
ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS);
return probe_fd(ret);
}
static int probe_kern_global_data(void)
{
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, insn_cnt = ARRAY_SIZE(insns);
map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL);
if (map < 0) {
ret = -errno;
cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
__func__, cp, -ret);
return ret;
}
insns[0].imm = map;
ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL);
close(map);
return probe_fd(ret);
}
static int probe_kern_btf(void)
{
static const char strs[] = "\0int";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_btf_func(void)
{
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),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_btf_func_global(void)
{
static const char strs[] = "\0int\0x\0a";
/* static 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 BTF_FUNC_GLOBAL */ /* [3] */
BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_btf_datasec(void)
{
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),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_btf_float(void)
{
static const char strs[] = "\0float";
__u32 types[] = {
/* float */
BTF_TYPE_FLOAT_ENC(1, 4),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_btf_decl_tag(void)
{
static const char strs[] = "\0tag";
__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,
/* attr */
BTF_TYPE_DECL_TAG_ENC(1, 2, -1),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_btf_type_tag(void)
{
static const char strs[] = "\0tag";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
/* attr */
BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */
/* ptr */
BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_array_mmap(void)
{
LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE);
int fd;
fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts);
return probe_fd(fd);
}
static int probe_kern_exp_attach_type(void)
{
LIBBPF_OPTS(bpf_prog_load_opts, opts, .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE);
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
int fd, insn_cnt = ARRAY_SIZE(insns);
/* use any valid combination of program type and (optional)
* non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS)
* to see if kernel supports expected_attach_type field for
* BPF_PROG_LOAD command
*/
fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts);
return probe_fd(fd);
}
static int probe_kern_probe_read_kernel(void)
{
struct bpf_insn insns[] = {
BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */
BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */
BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */
BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel),
BPF_EXIT_INSN(),
};
int fd, insn_cnt = ARRAY_SIZE(insns);
fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL);
return probe_fd(fd);
}
static int probe_prog_bind_map(void)
{
char *cp, errmsg[STRERR_BUFSIZE];
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
int ret, map, prog, insn_cnt = ARRAY_SIZE(insns);
map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, NULL);
if (map < 0) {
ret = -errno;
cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n",
__func__, cp, -ret);
return ret;
}
prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL);
if (prog < 0) {
close(map);
return 0;
}
ret = bpf_prog_bind_map(prog, map, NULL);
close(map);
close(prog);
return ret >= 0;
}
static int probe_module_btf(void)
{
static const char strs[] = "\0int";
__u32 types[] = {
/* int */
BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),
};
struct bpf_btf_info info;
__u32 len = sizeof(info);
char name[16];
int fd, err;
fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs));
if (fd < 0)
return 0; /* BTF not supported at all */
memset(&info, 0, sizeof(info));
info.name = ptr_to_u64(name);
info.name_len = sizeof(name);
/* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer;
* kernel's module BTF support coincides with support for
* name/name_len fields in struct bpf_btf_info.
*/
err = bpf_btf_get_info_by_fd(fd, &info, &len);
close(fd);
return !err;
}
static int probe_perf_link(void)
{
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
int prog_fd, link_fd, err;
prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL",
insns, ARRAY_SIZE(insns), NULL);
if (prog_fd < 0)
return -errno;
/* use invalid perf_event FD to get EBADF, if link is supported;
* otherwise EINVAL should be returned
*/
link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL);
err = -errno; /* close() can clobber errno */
if (link_fd >= 0)
close(link_fd);
close(prog_fd);
return link_fd < 0 && err == -EBADF;
}
static int probe_uprobe_multi_link(void)
{
LIBBPF_OPTS(bpf_prog_load_opts, load_opts,
.expected_attach_type = BPF_TRACE_UPROBE_MULTI,
);
LIBBPF_OPTS(bpf_link_create_opts, link_opts);
struct bpf_insn insns[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
};
int prog_fd, link_fd, err;
unsigned long offset = 0;
prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL",
insns, ARRAY_SIZE(insns), &load_opts);
if (prog_fd < 0)
return -errno;
/* Creating uprobe in '/' binary should fail with -EBADF. */
link_opts.uprobe_multi.path = "/";
link_opts.uprobe_multi.offsets = &offset;
link_opts.uprobe_multi.cnt = 1;
link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
err = -errno; /* close() can clobber errno */
if (link_fd >= 0)
close(link_fd);
close(prog_fd);
return link_fd < 0 && err == -EBADF;
}
static int probe_kern_bpf_cookie(void)
{
struct bpf_insn insns[] = {
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie),
BPF_EXIT_INSN(),
};
int ret, insn_cnt = ARRAY_SIZE(insns);
ret = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL);
return probe_fd(ret);
}
static int probe_kern_btf_enum64(void)
{
static const char strs[] = "\0enum64";
__u32 types[] = {
BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8),
};
return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs)));
}
static int probe_kern_syscall_wrapper(void);
enum kern_feature_result {
FEAT_UNKNOWN = 0,
FEAT_SUPPORTED = 1,
FEAT_MISSING = 2,
};
typedef int (*feature_probe_fn)(void);
static struct kern_feature_desc {
const char *desc;
feature_probe_fn probe;
enum kern_feature_result res;
} feature_probes[__FEAT_CNT] = {
[FEAT_PROG_NAME] = {
"BPF program name", probe_kern_prog_name,
},
[FEAT_GLOBAL_DATA] = {
"global variables", probe_kern_global_data,
},
[FEAT_BTF] = {
"minimal BTF", probe_kern_btf,
},
[FEAT_BTF_FUNC] = {
"BTF functions", probe_kern_btf_func,
},
[FEAT_BTF_GLOBAL_FUNC] = {
"BTF global function", probe_kern_btf_func_global,
},
[FEAT_BTF_DATASEC] = {
"BTF data section and variable", probe_kern_btf_datasec,
},
[FEAT_ARRAY_MMAP] = {
"ARRAY map mmap()", probe_kern_array_mmap,
},
[FEAT_EXP_ATTACH_TYPE] = {
"BPF_PROG_LOAD expected_attach_type attribute",
probe_kern_exp_attach_type,
},
[FEAT_PROBE_READ_KERN] = {
"bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel,
},
[FEAT_PROG_BIND_MAP] = {
"BPF_PROG_BIND_MAP support", probe_prog_bind_map,
},
[FEAT_MODULE_BTF] = {
"module BTF support", probe_module_btf,
},
[FEAT_BTF_FLOAT] = {
"BTF_KIND_FLOAT support", probe_kern_btf_float,
},
[FEAT_PERF_LINK] = {
"BPF perf link support", probe_perf_link,
},
[FEAT_BTF_DECL_TAG] = {
"BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag,
},
[FEAT_BTF_TYPE_TAG] = {
"BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag,
},
[FEAT_MEMCG_ACCOUNT] = {
"memcg-based memory accounting", probe_memcg_account,
},
[FEAT_BPF_COOKIE] = {
"BPF cookie support", probe_kern_bpf_cookie,
},
[FEAT_BTF_ENUM64] = {
"BTF_KIND_ENUM64 support", probe_kern_btf_enum64,
},
[FEAT_SYSCALL_WRAPPER] = {
"Kernel using syscall wrapper", probe_kern_syscall_wrapper,
},
[FEAT_UPROBE_MULTI_LINK] = {
"BPF multi-uprobe link support", probe_uprobe_multi_link,
},
};
bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
{
struct kern_feature_desc *feat = &feature_probes[feat_id];
int ret;
if (obj && obj->gen_loader)
/* To generate loader program assume the latest kernel
* to avoid doing extra prog_load, map_create syscalls.
*/
return true;
if (obj->token_fd)
return feat_supported(obj->feat_cache, feat_id);
if (READ_ONCE(feat->res) == FEAT_UNKNOWN) {
ret = feat->probe();
if (ret > 0) {
WRITE_ONCE(feat->res, FEAT_SUPPORTED);
} else if (ret == 0) {
WRITE_ONCE(feat->res, FEAT_MISSING);
} else {
pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret);
WRITE_ONCE(feat->res, FEAT_MISSING);
}
}
return feat_supported(NULL, feat_id);
return READ_ONCE(feat->res) == FEAT_SUPPORTED;
}
static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
@@ -4831,7 +5211,6 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
create_attr.map_flags = def->map_flags;
create_attr.numa_node = map->numa_node;
create_attr.map_extra = map->map_extra;
create_attr.token_fd = obj->token_fd;
if (bpf_map__is_struct_ops(map))
create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id;
@@ -6667,7 +7046,6 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
load_attr.attach_btf_id = prog->attach_btf_id;
load_attr.kern_version = kern_version;
load_attr.prog_ifindex = prog->prog_ifindex;
load_attr.token_fd = obj->token_fd;
/* specify func_info/line_info only if kernel supports them */
btf_fd = bpf_object__btf_fd(obj);
@@ -7129,10 +7507,10 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object
static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz,
const struct bpf_object_open_opts *opts)
{
const char *obj_name, *kconfig, *btf_tmp_path, *token_path;
const char *obj_name, *kconfig, *btf_tmp_path;
struct bpf_object *obj;
char tmp_name[64];
int err, token_fd;
int err;
char *log_buf;
size_t log_size;
__u32 log_level;
@@ -7166,28 +7544,6 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
if (log_size && !log_buf)
return ERR_PTR(-EINVAL);
token_path = OPTS_GET(opts, bpf_token_path, NULL);
token_fd = OPTS_GET(opts, bpf_token_fd, -1);
/* non-empty token path can't be combined with invalid token FD */
if (token_path && token_path[0] != '\0' && token_fd < 0)
return ERR_PTR(-EINVAL);
/* empty token path can't be combined with valid token FD */
if (token_path && token_path[0] == '\0' && token_fd > 0)
return ERR_PTR(-EINVAL);
/* if user didn't specify bpf_token_path/bpf_token_fd explicitly,
* check if LIBBPF_BPF_TOKEN_PATH envvar was set and treat it as
* bpf_token_path option
*/
if (token_fd == 0 && !token_path)
token_path = getenv("LIBBPF_BPF_TOKEN_PATH");
/* empty token_path is equivalent to invalid token_fd */
if (token_path && token_path[0] == '\0') {
token_path = NULL;
token_fd = -1;
}
if (token_path && strlen(token_path) >= PATH_MAX)
return ERR_PTR(-ENAMETOOLONG);
obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name);
if (IS_ERR(obj))
return obj;
@@ -7196,19 +7552,6 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
obj->log_size = log_size;
obj->log_level = log_level;
obj->token_fd = token_fd <= 0 ? token_fd : dup_good_fd(token_fd);
if (token_fd > 0 && obj->token_fd < 0) {
err = -errno;
goto out;
}
if (token_path) {
obj->token_path = strdup(token_path);
if (!obj->token_path) {
err = -ENOMEM;
goto out;
}
}
btf_tmp_path = OPTS_GET(opts, btf_custom_path, NULL);
if (btf_tmp_path) {
if (strlen(btf_tmp_path) >= PATH_MAX) {
@@ -7719,8 +8062,7 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
if (obj->gen_loader)
bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps);
err = bpf_object_prepare_token(obj);
err = err ? : bpf_object__probe_loading(obj);
err = bpf_object__probe_loading(obj);
err = err ? : bpf_object__load_vmlinux_btf(obj, false);
err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
err = err ? : bpf_object__sanitize_and_load_btf(obj);
@@ -8257,11 +8599,6 @@ void bpf_object__close(struct bpf_object *obj)
}
zfree(&obj->programs);
zfree(&obj->feat_cache);
zfree(&obj->token_path);
if (obj->token_fd > 0)
close(obj->token_fd);
free(obj);
}
@@ -10275,7 +10612,7 @@ static const char *arch_specific_syscall_pfx(void)
#endif
}
int probe_kern_syscall_wrapper(int token_fd)
static int probe_kern_syscall_wrapper(void)
{
char syscall_name[64];
const char *ksys_pfx;

37
src/libbpf.h
View File

@@ -177,45 +177,10 @@ struct bpf_object_open_opts {
* logs through its print callback.
*/
__u32 kernel_log_level;
/* FD of a BPF token instantiated by user through bpf_token_create()
* API. BPF object will keep dup()'ed FD internally, so passed token
* FD can be closed after BPF object/skeleton open step.
*
* Setting bpf_token_fd to negative value disables libbpf's automatic
* attempt to create BPF token from default BPF FS mount point
* (/sys/fs/bpf), in case this default behavior is undesirable.
*
* If bpf_token_path and bpf_token_fd are not specified, libbpf will
* consult LIBBPF_BPF_TOKEN_PATH environment variable. If set, it will
* be taken as a value of bpf_token_path option and will force libbpf
* to either create BPF token from provided custom BPF FS path, or
* will disable implicit BPF token creation, if envvar value is an
* empty string.
*
* bpf_token_path and bpf_token_fd are mutually exclusive and only one
* of those options should be set. Either of them overrides
* LIBBPF_BPF_TOKEN_PATH envvar.
*/
int bpf_token_fd;
/* Path to BPF FS mount point to derive BPF token from.
*
* Created BPF token will be used for all bpf() syscall operations
* that accept BPF token (e.g., map creation, BTF and program loads,
* etc) automatically within instantiated BPF object.
*
* Setting bpf_token_path option to empty string disables libbpf's
* automatic attempt to create BPF token from default BPF FS mount
* point (/sys/fs/bpf), in case this default behavior is undesirable.
*
* bpf_token_path and bpf_token_fd are mutually exclusive and only one
* of those options should be set. Either of them overrides
* LIBBPF_BPF_TOKEN_PATH envvar.
*/
const char *bpf_token_path;
size_t :0;
};
#define bpf_object_open_opts__last_field bpf_token_path
#define bpf_object_open_opts__last_field kernel_log_level
/**
* @brief **bpf_object__open()** creates a bpf_object by opening

1
src/libbpf.map
View File

@@ -401,7 +401,6 @@ LIBBPF_1.3.0 {
bpf_program__attach_netkit;
bpf_program__attach_tcx;
bpf_program__attach_uprobe_multi;
bpf_token_create;
ring__avail_data_size;
ring__consume;
ring__consumer_pos;

36
src/libbpf_internal.h
View File

@@ -360,32 +360,15 @@ enum kern_feature_id {
__FEAT_CNT,
};
enum kern_feature_result {
FEAT_UNKNOWN = 0,
FEAT_SUPPORTED = 1,
FEAT_MISSING = 2,
};
struct kern_feature_cache {
enum kern_feature_result res[__FEAT_CNT];
int token_fd;
};
bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id);
int probe_memcg_account(void);
bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
int probe_kern_syscall_wrapper(int token_fd);
int probe_memcg_account(int token_fd);
int bump_rlimit_memlock(void);
int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
const char *str_sec, size_t str_len,
int token_fd);
int btf_load_into_kernel(struct btf *btf,
char *log_buf, size_t log_sz, __u32 log_level,
int token_fd);
const char *str_sec, size_t str_len);
int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level);
struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
@@ -549,17 +532,6 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn)
return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
}
/* Unconditionally dup FD, ensuring it doesn't use [0, 2] range.
* Original FD is not closed or altered in any other way.
* Preserves original FD value, if it's invalid (negative).
*/
static inline int dup_good_fd(int fd)
{
if (fd < 0)
return fd;
return fcntl(fd, F_DUPFD_CLOEXEC, 3);
}
/* if fd is stdin, stdout, or stderr, dup to a fd greater than 2
* Takes ownership of the fd passed in, and closes it if calling
* fcntl(fd, F_DUPFD_CLOEXEC, 3).
@@ -571,7 +543,7 @@ static inline int ensure_good_fd(int fd)
if (fd < 0)
return fd;
if (fd < 3) {
fd = dup_good_fd(fd);
fd = fcntl(fd, F_DUPFD_CLOEXEC, 3);
saved_errno = errno;
close(old_fd);
errno = saved_errno;

8
src/libbpf_probes.c
View File

@@ -219,8 +219,7 @@ int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts)
}
int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
const char *str_sec, size_t str_len,
int token_fd)
const char *str_sec, size_t str_len)
{
struct btf_header hdr = {
.magic = BTF_MAGIC,
@@ -230,7 +229,6 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
.str_off = types_len,
.str_len = str_len,
};
LIBBPF_OPTS(bpf_btf_load_opts, opts, .token_fd = token_fd);
int btf_fd, btf_len;
__u8 *raw_btf;
@@ -243,7 +241,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
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_btf_load(raw_btf, btf_len, &opts);
btf_fd = bpf_btf_load(raw_btf, btf_len, NULL);
free(raw_btf);
return btf_fd;
@@ -273,7 +271,7 @@ static int load_local_storage_btf(void)
};
return libbpf__load_raw_btf((char *)types, sizeof(types),
strs, sizeof(strs), 0);
strs, sizeof(strs));
}
static int probe_map_create(enum bpf_map_type map_type)

3
src/str_error.h
View File

@@ -2,8 +2,5 @@
#ifndef __LIBBPF_STR_ERROR_H
#define __LIBBPF_STR_ERROR_H
#define STRERR_BUFSIZE 128
char *libbpf_strerror_r(int err, char *dst, int len);
#endif /* __LIBBPF_STR_ERROR_H */