mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-27 11:19:37 +00:00
![Andrii Nakryiko](/assets/img/avatar_default.png)
Ubuntu reports incorrect kernel version through uname(), which on older kernels leads to kprobe BPF programs failing to load due to the version check mismatch. Accommodate Ubuntu's quirks with LINUX_VERSION_CODE by using Ubuntu-specific /proc/version_code to fetch major/minor/patch versions to form LINUX_VERSION_CODE. While at it, consolide libbpf's kernel version detection code between libbpf.c and libbpf_probes.c. [0] Closes: https://github.com/libbpf/libbpf/issues/421 Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20211222231003.2334940-1-andrii@kernel.org
477 lines
12 KiB
C
477 lines
12 KiB
C
// 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 | O_CLOEXEC);
|
|
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 probe_prog_load(enum bpf_prog_type prog_type,
|
|
const struct bpf_insn *insns, size_t insns_cnt,
|
|
char *log_buf, size_t log_buf_sz,
|
|
__u32 ifindex)
|
|
{
|
|
LIBBPF_OPTS(bpf_prog_load_opts, opts,
|
|
.log_buf = log_buf,
|
|
.log_size = log_buf_sz,
|
|
.log_level = log_buf ? 1 : 0,
|
|
.prog_ifindex = ifindex,
|
|
);
|
|
int fd, err, exp_err = 0;
|
|
const char *exp_msg = NULL;
|
|
char buf[4096];
|
|
|
|
switch (prog_type) {
|
|
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
|
|
opts.expected_attach_type = BPF_CGROUP_INET4_CONNECT;
|
|
break;
|
|
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
|
|
opts.expected_attach_type = BPF_CGROUP_GETSOCKOPT;
|
|
break;
|
|
case BPF_PROG_TYPE_SK_LOOKUP:
|
|
opts.expected_attach_type = BPF_SK_LOOKUP;
|
|
break;
|
|
case BPF_PROG_TYPE_KPROBE:
|
|
opts.kern_version = get_kernel_version();
|
|
break;
|
|
case BPF_PROG_TYPE_LIRC_MODE2:
|
|
opts.expected_attach_type = BPF_LIRC_MODE2;
|
|
break;
|
|
case BPF_PROG_TYPE_TRACING:
|
|
case BPF_PROG_TYPE_LSM:
|
|
opts.log_buf = buf;
|
|
opts.log_size = sizeof(buf);
|
|
opts.log_level = 1;
|
|
if (prog_type == BPF_PROG_TYPE_TRACING)
|
|
opts.expected_attach_type = BPF_TRACE_FENTRY;
|
|
else
|
|
opts.expected_attach_type = BPF_MODIFY_RETURN;
|
|
opts.attach_btf_id = 1;
|
|
|
|
exp_err = -EINVAL;
|
|
exp_msg = "attach_btf_id 1 is not a function";
|
|
break;
|
|
case BPF_PROG_TYPE_EXT:
|
|
opts.log_buf = buf;
|
|
opts.log_size = sizeof(buf);
|
|
opts.log_level = 1;
|
|
opts.attach_btf_id = 1;
|
|
|
|
exp_err = -EINVAL;
|
|
exp_msg = "Cannot replace kernel functions";
|
|
break;
|
|
case BPF_PROG_TYPE_SYSCALL:
|
|
opts.prog_flags = BPF_F_SLEEPABLE;
|
|
break;
|
|
case BPF_PROG_TYPE_STRUCT_OPS:
|
|
exp_err = -524; /* -ENOTSUPP */
|
|
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_SK_REUSEPORT:
|
|
case BPF_PROG_TYPE_FLOW_DISSECTOR:
|
|
case BPF_PROG_TYPE_CGROUP_SYSCTL:
|
|
break;
|
|
default:
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts);
|
|
err = -errno;
|
|
if (fd >= 0)
|
|
close(fd);
|
|
if (exp_err) {
|
|
if (fd >= 0 || err != exp_err)
|
|
return 0;
|
|
if (exp_msg && !strstr(buf, exp_msg))
|
|
return 0;
|
|
return 1;
|
|
}
|
|
return fd >= 0 ? 1 : 0;
|
|
}
|
|
|
|
int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts)
|
|
{
|
|
struct bpf_insn insns[] = {
|
|
BPF_MOV64_IMM(BPF_REG_0, 0),
|
|
BPF_EXIT_INSN()
|
|
};
|
|
const size_t insn_cnt = ARRAY_SIZE(insns);
|
|
int ret;
|
|
|
|
if (opts)
|
|
return libbpf_err(-EINVAL);
|
|
|
|
ret = probe_prog_load(prog_type, insns, insn_cnt, NULL, 0, 0);
|
|
return libbpf_err(ret);
|
|
}
|
|
|
|
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()
|
|
};
|
|
|
|
/* prefer libbpf_probe_bpf_prog_type() unless offload is requested */
|
|
if (ifindex == 0)
|
|
return libbpf_probe_bpf_prog_type(prog_type, NULL) == 1;
|
|
|
|
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_prog_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_btf_load(raw_btf, btf_len, NULL);
|
|
|
|
free(raw_btf);
|
|
return btf_fd;
|
|
}
|
|
|
|
static int load_local_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));
|
|
}
|
|
|
|
static int probe_map_create(enum bpf_map_type map_type, __u32 ifindex)
|
|
{
|
|
LIBBPF_OPTS(bpf_map_create_opts, opts);
|
|
int key_size, value_size, max_entries;
|
|
__u32 btf_key_type_id = 0, btf_value_type_id = 0;
|
|
int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err;
|
|
|
|
opts.map_ifindex = ifindex;
|
|
|
|
key_size = sizeof(__u32);
|
|
value_size = sizeof(__u32);
|
|
max_entries = 1;
|
|
|
|
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);
|
|
opts.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:
|
|
case BPF_MAP_TYPE_INODE_STORAGE:
|
|
case BPF_MAP_TYPE_TASK_STORAGE:
|
|
btf_key_type_id = 1;
|
|
btf_value_type_id = 3;
|
|
value_size = 8;
|
|
max_entries = 0;
|
|
opts.map_flags = BPF_F_NO_PREALLOC;
|
|
btf_fd = load_local_storage_btf();
|
|
if (btf_fd < 0)
|
|
return btf_fd;
|
|
break;
|
|
case BPF_MAP_TYPE_RINGBUF:
|
|
key_size = 0;
|
|
value_size = 0;
|
|
max_entries = 4096;
|
|
break;
|
|
case BPF_MAP_TYPE_STRUCT_OPS:
|
|
/* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */
|
|
opts.btf_vmlinux_value_type_id = 1;
|
|
exp_err = -524; /* -ENOTSUPP */
|
|
break;
|
|
case BPF_MAP_TYPE_BLOOM_FILTER:
|
|
key_size = 0;
|
|
max_entries = 1;
|
|
break;
|
|
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:
|
|
break;
|
|
case BPF_MAP_TYPE_UNSPEC:
|
|
default:
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
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)
|
|
goto cleanup;
|
|
|
|
fd_inner = bpf_map_create(BPF_MAP_TYPE_HASH, NULL,
|
|
sizeof(__u32), sizeof(__u32), 1, NULL);
|
|
if (fd_inner < 0)
|
|
goto cleanup;
|
|
|
|
opts.inner_map_fd = fd_inner;
|
|
}
|
|
|
|
if (btf_fd >= 0) {
|
|
opts.btf_fd = btf_fd;
|
|
opts.btf_key_type_id = btf_key_type_id;
|
|
opts.btf_value_type_id = btf_value_type_id;
|
|
}
|
|
|
|
fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts);
|
|
err = -errno;
|
|
|
|
cleanup:
|
|
if (fd >= 0)
|
|
close(fd);
|
|
if (fd_inner >= 0)
|
|
close(fd_inner);
|
|
if (btf_fd >= 0)
|
|
close(btf_fd);
|
|
|
|
if (exp_err)
|
|
return fd < 0 && err == exp_err ? 1 : 0;
|
|
else
|
|
return fd >= 0 ? 1 : 0;
|
|
}
|
|
|
|
int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts)
|
|
{
|
|
int ret;
|
|
|
|
if (opts)
|
|
return libbpf_err(-EINVAL);
|
|
|
|
ret = probe_map_create(map_type, 0);
|
|
return libbpf_err(ret);
|
|
}
|
|
|
|
bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
|
|
{
|
|
return probe_map_create(map_type, ifindex) == 1;
|
|
}
|
|
|
|
int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helper_id,
|
|
const void *opts)
|
|
{
|
|
struct bpf_insn insns[] = {
|
|
BPF_EMIT_CALL((__u32)helper_id),
|
|
BPF_EXIT_INSN(),
|
|
};
|
|
const size_t insn_cnt = ARRAY_SIZE(insns);
|
|
char buf[4096];
|
|
int ret;
|
|
|
|
if (opts)
|
|
return libbpf_err(-EINVAL);
|
|
|
|
/* we can't successfully load all prog types to check for BPF helper
|
|
* support, so bail out with -EOPNOTSUPP error
|
|
*/
|
|
switch (prog_type) {
|
|
case BPF_PROG_TYPE_TRACING:
|
|
case BPF_PROG_TYPE_EXT:
|
|
case BPF_PROG_TYPE_LSM:
|
|
case BPF_PROG_TYPE_STRUCT_OPS:
|
|
return -EOPNOTSUPP;
|
|
default:
|
|
break;
|
|
}
|
|
|
|
buf[0] = '\0';
|
|
ret = probe_prog_load(prog_type, insns, insn_cnt, buf, sizeof(buf), 0);
|
|
if (ret < 0)
|
|
return libbpf_err(ret);
|
|
|
|
/* If BPF verifier doesn't recognize BPF helper ID (enum bpf_func_id)
|
|
* at all, it will emit something like "invalid func unknown#181".
|
|
* If BPF verifier recognizes BPF helper but it's not supported for
|
|
* given BPF program type, it will emit "unknown func bpf_sys_bpf#166".
|
|
* In both cases, provided combination of BPF program type and BPF
|
|
* helper is not supported by the kernel.
|
|
* In all other cases, probe_prog_load() above will either succeed (e.g.,
|
|
* because BPF helper happens to accept no input arguments or it
|
|
* accepts one input argument and initial PTR_TO_CTX is fine for
|
|
* that), or we'll get some more specific BPF verifier error about
|
|
* some unsatisfied conditions.
|
|
*/
|
|
if (ret == 0 && (strstr(buf, "invalid func ") || strstr(buf, "unknown func ")))
|
|
return 0;
|
|
return 1; /* assume supported */
|
|
}
|
|
|
|
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_prog_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;
|
|
}
|
|
|
|
/*
|
|
* Probe for availability of kernel commit (5.3):
|
|
*
|
|
* c04c0d2b968a ("bpf: increase complexity limit and maximum program size")
|
|
*/
|
|
bool bpf_probe_large_insn_limit(__u32 ifindex)
|
|
{
|
|
struct bpf_insn insns[BPF_MAXINSNS + 1];
|
|
int i;
|
|
|
|
for (i = 0; i < BPF_MAXINSNS; i++)
|
|
insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1);
|
|
insns[BPF_MAXINSNS] = BPF_EXIT_INSN();
|
|
|
|
errno = 0;
|
|
probe_prog_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0,
|
|
ifindex);
|
|
|
|
return errno != E2BIG && errno != EINVAL;
|
|
}
|