2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-15 16:53:54 +08:00
linux-next/tools/bpf/bpftool/prog.c
David S. Miller 2bbc078f81 Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says:

====================
pull-request: bpf-next 2019-12-27

The following pull-request contains BPF updates for your *net-next* tree.

We've added 127 non-merge commits during the last 17 day(s) which contain
a total of 110 files changed, 6901 insertions(+), 2721 deletions(-).

There are three merge conflicts. Conflicts and resolution looks as follows:

1) Merge conflict in net/bpf/test_run.c:

There was a tree-wide cleanup c593642c8b ("treewide: Use sizeof_field() macro")
which gets in the way with b590cb5f80 ("bpf: Switch to offsetofend in
BPF_PROG_TEST_RUN"):

  <<<<<<< HEAD
          if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) +
                             sizeof_field(struct __sk_buff, priority),
  =======
          if (!range_is_zero(__skb, offsetofend(struct __sk_buff, priority),
  >>>>>>> 7c8dce4b16

There are a few occasions that look similar to this. Always take the chunk with
offsetofend(). Note that there is one where the fields differ in here:

  <<<<<<< HEAD
          if (!range_is_zero(__skb, offsetof(struct __sk_buff, tstamp) +
                             sizeof_field(struct __sk_buff, tstamp),
  =======
          if (!range_is_zero(__skb, offsetofend(struct __sk_buff, gso_segs),
  >>>>>>> 7c8dce4b16

Just take the one with offsetofend() /and/ gso_segs. Latter is correct due to
850a88cc40 ("bpf: Expose __sk_buff wire_len/gso_segs to BPF_PROG_TEST_RUN").

2) Merge conflict in arch/riscv/net/bpf_jit_comp.c:

(I'm keeping Bjorn in Cc here for a double-check in case I got it wrong.)

  <<<<<<< HEAD
          if (is_13b_check(off, insn))
                  return -1;
          emit(rv_blt(tcc, RV_REG_ZERO, off >> 1), ctx);
  =======
          emit_branch(BPF_JSLT, RV_REG_T1, RV_REG_ZERO, off, ctx);
  >>>>>>> 7c8dce4b16

Result should look like:

          emit_branch(BPF_JSLT, tcc, RV_REG_ZERO, off, ctx);

3) Merge conflict in arch/riscv/include/asm/pgtable.h:

  <<<<<<< HEAD
  =======
  #define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
  #define VMALLOC_END      (PAGE_OFFSET - 1)
  #define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)

  #define BPF_JIT_REGION_SIZE     (SZ_128M)
  #define BPF_JIT_REGION_START    (PAGE_OFFSET - BPF_JIT_REGION_SIZE)
  #define BPF_JIT_REGION_END      (VMALLOC_END)

  /*
   * Roughly size the vmemmap space to be large enough to fit enough
   * struct pages to map half the virtual address space. Then
   * position vmemmap directly below the VMALLOC region.
   */
  #define VMEMMAP_SHIFT \
          (CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)
  #define VMEMMAP_SIZE    BIT(VMEMMAP_SHIFT)
  #define VMEMMAP_END     (VMALLOC_START - 1)
  #define VMEMMAP_START   (VMALLOC_START - VMEMMAP_SIZE)

  #define vmemmap         ((struct page *)VMEMMAP_START)

  >>>>>>> 7c8dce4b16

Only take the BPF_* defines from there and move them higher up in the
same file. Remove the rest from the chunk. The VMALLOC_* etc defines
got moved via 01f52e16b8 ("riscv: define vmemmap before pfn_to_page
calls"). Result:

  [...]
  #define __S101  PAGE_READ_EXEC
  #define __S110  PAGE_SHARED_EXEC
  #define __S111  PAGE_SHARED_EXEC

  #define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
  #define VMALLOC_END      (PAGE_OFFSET - 1)
  #define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)

  #define BPF_JIT_REGION_SIZE     (SZ_128M)
  #define BPF_JIT_REGION_START    (PAGE_OFFSET - BPF_JIT_REGION_SIZE)
  #define BPF_JIT_REGION_END      (VMALLOC_END)

  /*
   * Roughly size the vmemmap space to be large enough to fit enough
   * struct pages to map half the virtual address space. Then
   * position vmemmap directly below the VMALLOC region.
   */
  #define VMEMMAP_SHIFT \
          (CONFIG_VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)
  #define VMEMMAP_SIZE    BIT(VMEMMAP_SHIFT)
  #define VMEMMAP_END     (VMALLOC_START - 1)
  #define VMEMMAP_START   (VMALLOC_START - VMEMMAP_SIZE)

  [...]

Let me know if there are any other issues.

Anyway, the main changes are:

1) Extend bpftool to produce a struct (aka "skeleton") tailored and specific
   to a provided BPF object file. This provides an alternative, simplified API
   compared to standard libbpf interaction. Also, add libbpf extern variable
   resolution for .kconfig section to import Kconfig data, from Andrii Nakryiko.

2) Add BPF dispatcher for XDP which is a mechanism to avoid indirect calls by
   generating a branch funnel as discussed back in bpfconf'19 at LSF/MM. Also,
   add various BPF riscv JIT improvements, from Björn Töpel.

3) Extend bpftool to allow matching BPF programs and maps by name,
   from Paul Chaignon.

4) Support for replacing cgroup BPF programs attached with BPF_F_ALLOW_MULTI
   flag for allowing updates without service interruption, from Andrey Ignatov.

5) Cleanup and simplification of ring access functions for AF_XDP with a
   bonus of 0-5% performance improvement, from Magnus Karlsson.

6) Enable BPF JITs for x86-64 and arm64 by default. Also, final version of
   audit support for BPF, from Daniel Borkmann and latter with Jiri Olsa.

7) Move and extend test_select_reuseport into BPF program tests under
   BPF selftests, from Jakub Sitnicki.

8) Various BPF sample improvements for xdpsock for customizing parameters
   to set up and benchmark AF_XDP, from Jay Jayatheerthan.

9) Improve libbpf to provide a ulimit hint on permission denied errors.
   Also change XDP sample programs to attach in driver mode by default,
   from Toke Høiland-Jørgensen.

10) Extend BPF test infrastructure to allow changing skb mark from tc BPF
    programs, from Nikita V. Shirokov.

11) Optimize prologue code sequence in BPF arm32 JIT, from Russell King.

12) Fix xdp_redirect_cpu BPF sample to manually attach to tracepoints after
    libbpf conversion, from Jesper Dangaard Brouer.

13) Minor misc improvements from various others.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2019-12-27 14:20:10 -08:00

1609 lines
35 KiB
C

// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
/* Copyright (C) 2017-2018 Netronome Systems, Inc. */
#define _GNU_SOURCE
#include <errno.h>
#include <fcntl.h>
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>
#include <unistd.h>
#include <net/if.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <linux/err.h>
#include <linux/sizes.h>
#include <bpf.h>
#include <btf.h>
#include <libbpf.h>
#include "cfg.h"
#include "main.h"
#include "xlated_dumper.h"
enum dump_mode {
DUMP_JITED,
DUMP_XLATED,
};
static const char * const attach_type_strings[] = {
[BPF_SK_SKB_STREAM_PARSER] = "stream_parser",
[BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict",
[BPF_SK_MSG_VERDICT] = "msg_verdict",
[BPF_FLOW_DISSECTOR] = "flow_dissector",
[__MAX_BPF_ATTACH_TYPE] = NULL,
};
static enum bpf_attach_type parse_attach_type(const char *str)
{
enum bpf_attach_type type;
for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) {
if (attach_type_strings[type] &&
is_prefix(str, attach_type_strings[type]))
return type;
}
return __MAX_BPF_ATTACH_TYPE;
}
static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
{
struct timespec real_time_ts, boot_time_ts;
time_t wallclock_secs;
struct tm load_tm;
buf[--size] = '\0';
if (clock_gettime(CLOCK_REALTIME, &real_time_ts) ||
clock_gettime(CLOCK_BOOTTIME, &boot_time_ts)) {
perror("Can't read clocks");
snprintf(buf, size, "%llu", nsecs / 1000000000);
return;
}
wallclock_secs = (real_time_ts.tv_sec - boot_time_ts.tv_sec) +
(real_time_ts.tv_nsec - boot_time_ts.tv_nsec + nsecs) /
1000000000;
if (!localtime_r(&wallclock_secs, &load_tm)) {
snprintf(buf, size, "%llu", nsecs / 1000000000);
return;
}
if (json_output)
strftime(buf, size, "%s", &load_tm);
else
strftime(buf, size, "%FT%T%z", &load_tm);
}
static int prog_fd_by_nametag(void *nametag, int **fds, bool tag)
{
unsigned int id = 0;
int fd, nb_fds = 0;
void *tmp;
int err;
while (true) {
struct bpf_prog_info info = {};
__u32 len = sizeof(info);
err = bpf_prog_get_next_id(id, &id);
if (err) {
if (errno != ENOENT) {
p_err("%s", strerror(errno));
goto err_close_fds;
}
return nb_fds;
}
fd = bpf_prog_get_fd_by_id(id);
if (fd < 0) {
p_err("can't get prog by id (%u): %s",
id, strerror(errno));
goto err_close_fds;
}
err = bpf_obj_get_info_by_fd(fd, &info, &len);
if (err) {
p_err("can't get prog info (%u): %s",
id, strerror(errno));
goto err_close_fd;
}
if ((tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) ||
(!tag && strncmp(nametag, info.name, BPF_OBJ_NAME_LEN))) {
close(fd);
continue;
}
if (nb_fds > 0) {
tmp = realloc(*fds, (nb_fds + 1) * sizeof(int));
if (!tmp) {
p_err("failed to realloc");
goto err_close_fd;
}
*fds = tmp;
}
(*fds)[nb_fds++] = fd;
}
err_close_fd:
close(fd);
err_close_fds:
while (--nb_fds >= 0)
close((*fds)[nb_fds]);
return -1;
}
static int prog_parse_fds(int *argc, char ***argv, int **fds)
{
if (is_prefix(**argv, "id")) {
unsigned int id;
char *endptr;
NEXT_ARGP();
id = strtoul(**argv, &endptr, 0);
if (*endptr) {
p_err("can't parse %s as ID", **argv);
return -1;
}
NEXT_ARGP();
(*fds)[0] = bpf_prog_get_fd_by_id(id);
if ((*fds)[0] < 0) {
p_err("get by id (%u): %s", id, strerror(errno));
return -1;
}
return 1;
} else if (is_prefix(**argv, "tag")) {
unsigned char tag[BPF_TAG_SIZE];
NEXT_ARGP();
if (sscanf(**argv, BPF_TAG_FMT, tag, tag + 1, tag + 2,
tag + 3, tag + 4, tag + 5, tag + 6, tag + 7)
!= BPF_TAG_SIZE) {
p_err("can't parse tag");
return -1;
}
NEXT_ARGP();
return prog_fd_by_nametag(tag, fds, true);
} else if (is_prefix(**argv, "name")) {
char *name;
NEXT_ARGP();
name = **argv;
if (strlen(name) > BPF_OBJ_NAME_LEN - 1) {
p_err("can't parse name");
return -1;
}
NEXT_ARGP();
return prog_fd_by_nametag(name, fds, false);
} else if (is_prefix(**argv, "pinned")) {
char *path;
NEXT_ARGP();
path = **argv;
NEXT_ARGP();
(*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG);
if ((*fds)[0] < 0)
return -1;
return 1;
}
p_err("expected 'id', 'tag', 'name' or 'pinned', got: '%s'?", **argv);
return -1;
}
int prog_parse_fd(int *argc, char ***argv)
{
int *fds = NULL;
int nb_fds, fd;
fds = malloc(sizeof(int));
if (!fds) {
p_err("mem alloc failed");
return -1;
}
nb_fds = prog_parse_fds(argc, argv, &fds);
if (nb_fds != 1) {
if (nb_fds > 1) {
p_err("several programs match this handle");
while (nb_fds--)
close(fds[nb_fds]);
}
fd = -1;
goto exit_free;
}
fd = fds[0];
exit_free:
free(fds);
return fd;
}
static void show_prog_maps(int fd, u32 num_maps)
{
struct bpf_prog_info info = {};
__u32 len = sizeof(info);
__u32 map_ids[num_maps];
unsigned int i;
int err;
info.nr_map_ids = num_maps;
info.map_ids = ptr_to_u64(map_ids);
err = bpf_obj_get_info_by_fd(fd, &info, &len);
if (err || !info.nr_map_ids)
return;
if (json_output) {
jsonw_name(json_wtr, "map_ids");
jsonw_start_array(json_wtr);
for (i = 0; i < info.nr_map_ids; i++)
jsonw_uint(json_wtr, map_ids[i]);
jsonw_end_array(json_wtr);
} else {
printf(" map_ids ");
for (i = 0; i < info.nr_map_ids; i++)
printf("%u%s", map_ids[i],
i == info.nr_map_ids - 1 ? "" : ",");
}
}
static void print_prog_header_json(struct bpf_prog_info *info)
{
jsonw_uint_field(json_wtr, "id", info->id);
if (info->type < ARRAY_SIZE(prog_type_name))
jsonw_string_field(json_wtr, "type",
prog_type_name[info->type]);
else
jsonw_uint_field(json_wtr, "type", info->type);
if (*info->name)
jsonw_string_field(json_wtr, "name", info->name);
jsonw_name(json_wtr, "tag");
jsonw_printf(json_wtr, "\"" BPF_TAG_FMT "\"",
info->tag[0], info->tag[1], info->tag[2], info->tag[3],
info->tag[4], info->tag[5], info->tag[6], info->tag[7]);
jsonw_bool_field(json_wtr, "gpl_compatible", info->gpl_compatible);
if (info->run_time_ns) {
jsonw_uint_field(json_wtr, "run_time_ns", info->run_time_ns);
jsonw_uint_field(json_wtr, "run_cnt", info->run_cnt);
}
}
static void print_prog_json(struct bpf_prog_info *info, int fd)
{
char *memlock;
jsonw_start_object(json_wtr);
print_prog_header_json(info);
print_dev_json(info->ifindex, info->netns_dev, info->netns_ino);
if (info->load_time) {
char buf[32];
print_boot_time(info->load_time, buf, sizeof(buf));
/* Piggy back on load_time, since 0 uid is a valid one */
jsonw_name(json_wtr, "loaded_at");
jsonw_printf(json_wtr, "%s", buf);
jsonw_uint_field(json_wtr, "uid", info->created_by_uid);
}
jsonw_uint_field(json_wtr, "bytes_xlated", info->xlated_prog_len);
if (info->jited_prog_len) {
jsonw_bool_field(json_wtr, "jited", true);
jsonw_uint_field(json_wtr, "bytes_jited", info->jited_prog_len);
} else {
jsonw_bool_field(json_wtr, "jited", false);
}
memlock = get_fdinfo(fd, "memlock");
if (memlock)
jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock));
free(memlock);
if (info->nr_map_ids)
show_prog_maps(fd, info->nr_map_ids);
if (info->btf_id)
jsonw_int_field(json_wtr, "btf_id", info->btf_id);
if (!hash_empty(prog_table.table)) {
struct pinned_obj *obj;
jsonw_name(json_wtr, "pinned");
jsonw_start_array(json_wtr);
hash_for_each_possible(prog_table.table, obj, hash, info->id) {
if (obj->id == info->id)
jsonw_string(json_wtr, obj->path);
}
jsonw_end_array(json_wtr);
}
jsonw_end_object(json_wtr);
}
static void print_prog_header_plain(struct bpf_prog_info *info)
{
printf("%u: ", info->id);
if (info->type < ARRAY_SIZE(prog_type_name))
printf("%s ", prog_type_name[info->type]);
else
printf("type %u ", info->type);
if (*info->name)
printf("name %s ", info->name);
printf("tag ");
fprint_hex(stdout, info->tag, BPF_TAG_SIZE, "");
print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino);
printf("%s", info->gpl_compatible ? " gpl" : "");
if (info->run_time_ns)
printf(" run_time_ns %lld run_cnt %lld",
info->run_time_ns, info->run_cnt);
printf("\n");
}
static void print_prog_plain(struct bpf_prog_info *info, int fd)
{
char *memlock;
print_prog_header_plain(info);
if (info->load_time) {
char buf[32];
print_boot_time(info->load_time, buf, sizeof(buf));
/* Piggy back on load_time, since 0 uid is a valid one */
printf("\tloaded_at %s uid %u\n", buf, info->created_by_uid);
}
printf("\txlated %uB", info->xlated_prog_len);
if (info->jited_prog_len)
printf(" jited %uB", info->jited_prog_len);
else
printf(" not jited");
memlock = get_fdinfo(fd, "memlock");
if (memlock)
printf(" memlock %sB", memlock);
free(memlock);
if (info->nr_map_ids)
show_prog_maps(fd, info->nr_map_ids);
if (!hash_empty(prog_table.table)) {
struct pinned_obj *obj;
hash_for_each_possible(prog_table.table, obj, hash, info->id) {
if (obj->id == info->id)
printf("\n\tpinned %s", obj->path);
}
}
if (info->btf_id)
printf("\n\tbtf_id %d", info->btf_id);
printf("\n");
}
static int show_prog(int fd)
{
struct bpf_prog_info info = {};
__u32 len = sizeof(info);
int err;
err = bpf_obj_get_info_by_fd(fd, &info, &len);
if (err) {
p_err("can't get prog info: %s", strerror(errno));
return -1;
}
if (json_output)
print_prog_json(&info, fd);
else
print_prog_plain(&info, fd);
return 0;
}
static int do_show_subset(int argc, char **argv)
{
int *fds = NULL;
int nb_fds, i;
int err = -1;
fds = malloc(sizeof(int));
if (!fds) {
p_err("mem alloc failed");
return -1;
}
nb_fds = prog_parse_fds(&argc, &argv, &fds);
if (nb_fds < 1)
goto exit_free;
if (json_output && nb_fds > 1)
jsonw_start_array(json_wtr); /* root array */
for (i = 0; i < nb_fds; i++) {
err = show_prog(fds[i]);
if (err) {
for (; i < nb_fds; i++)
close(fds[i]);
break;
}
close(fds[i]);
}
if (json_output && nb_fds > 1)
jsonw_end_array(json_wtr); /* root array */
exit_free:
free(fds);
return err;
}
static int do_show(int argc, char **argv)
{
__u32 id = 0;
int err;
int fd;
if (show_pinned)
build_pinned_obj_table(&prog_table, BPF_OBJ_PROG);
if (argc == 2)
return do_show_subset(argc, argv);
if (argc)
return BAD_ARG();
if (json_output)
jsonw_start_array(json_wtr);
while (true) {
err = bpf_prog_get_next_id(id, &id);
if (err) {
if (errno == ENOENT) {
err = 0;
break;
}
p_err("can't get next program: %s%s", strerror(errno),
errno == EINVAL ? " -- kernel too old?" : "");
err = -1;
break;
}
fd = bpf_prog_get_fd_by_id(id);
if (fd < 0) {
if (errno == ENOENT)
continue;
p_err("can't get prog by id (%u): %s",
id, strerror(errno));
err = -1;
break;
}
err = show_prog(fd);
close(fd);
if (err)
break;
}
if (json_output)
jsonw_end_array(json_wtr);
return err;
}
static int
prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
char *filepath, bool opcodes, bool visual, bool linum)
{
struct bpf_prog_linfo *prog_linfo = NULL;
const char *disasm_opt = NULL;
struct dump_data dd = {};
void *func_info = NULL;
struct btf *btf = NULL;
char func_sig[1024];
unsigned char *buf;
__u32 member_len;
ssize_t n;
int fd;
if (mode == DUMP_JITED) {
if (info->jited_prog_len == 0 || !info->jited_prog_insns) {
p_info("no instructions returned");
return -1;
}
buf = (unsigned char *)(info->jited_prog_insns);
member_len = info->jited_prog_len;
} else { /* DUMP_XLATED */
if (info->xlated_prog_len == 0) {
p_err("error retrieving insn dump: kernel.kptr_restrict set?");
return -1;
}
buf = (unsigned char *)info->xlated_prog_insns;
member_len = info->xlated_prog_len;
}
if (info->btf_id && btf__get_from_id(info->btf_id, &btf)) {
p_err("failed to get btf");
return -1;
}
func_info = (void *)info->func_info;
if (info->nr_line_info) {
prog_linfo = bpf_prog_linfo__new(info);
if (!prog_linfo)
p_info("error in processing bpf_line_info. continue without it.");
}
if (filepath) {
fd = open(filepath, O_WRONLY | O_CREAT | O_TRUNC, 0600);
if (fd < 0) {
p_err("can't open file %s: %s", filepath,
strerror(errno));
return -1;
}
n = write(fd, buf, member_len);
close(fd);
if (n != member_len) {
p_err("error writing output file: %s",
n < 0 ? strerror(errno) : "short write");
return -1;
}
if (json_output)
jsonw_null(json_wtr);
} else if (mode == DUMP_JITED) {
const char *name = NULL;
if (info->ifindex) {
name = ifindex_to_bfd_params(info->ifindex,
info->netns_dev,
info->netns_ino,
&disasm_opt);
if (!name)
return -1;
}
if (info->nr_jited_func_lens && info->jited_func_lens) {
struct kernel_sym *sym = NULL;
struct bpf_func_info *record;
char sym_name[SYM_MAX_NAME];
unsigned char *img = buf;
__u64 *ksyms = NULL;
__u32 *lens;
__u32 i;
if (info->nr_jited_ksyms) {
kernel_syms_load(&dd);
ksyms = (__u64 *) info->jited_ksyms;
}
if (json_output)
jsonw_start_array(json_wtr);
lens = (__u32 *) info->jited_func_lens;
for (i = 0; i < info->nr_jited_func_lens; i++) {
if (ksyms) {
sym = kernel_syms_search(&dd, ksyms[i]);
if (sym)
sprintf(sym_name, "%s", sym->name);
else
sprintf(sym_name, "0x%016llx", ksyms[i]);
} else {
strcpy(sym_name, "unknown");
}
if (func_info) {
record = func_info + i * info->func_info_rec_size;
btf_dumper_type_only(btf, record->type_id,
func_sig,
sizeof(func_sig));
}
if (json_output) {
jsonw_start_object(json_wtr);
if (func_info && func_sig[0] != '\0') {
jsonw_name(json_wtr, "proto");
jsonw_string(json_wtr, func_sig);
}
jsonw_name(json_wtr, "name");
jsonw_string(json_wtr, sym_name);
jsonw_name(json_wtr, "insns");
} else {
if (func_info && func_sig[0] != '\0')
printf("%s:\n", func_sig);
printf("%s:\n", sym_name);
}
disasm_print_insn(img, lens[i], opcodes,
name, disasm_opt, btf,
prog_linfo, ksyms[i], i,
linum);
img += lens[i];
if (json_output)
jsonw_end_object(json_wtr);
else
printf("\n");
}
if (json_output)
jsonw_end_array(json_wtr);
} else {
disasm_print_insn(buf, member_len, opcodes, name,
disasm_opt, btf, NULL, 0, 0, false);
}
} else if (visual) {
if (json_output)
jsonw_null(json_wtr);
else
dump_xlated_cfg(buf, member_len);
} else {
kernel_syms_load(&dd);
dd.nr_jited_ksyms = info->nr_jited_ksyms;
dd.jited_ksyms = (__u64 *) info->jited_ksyms;
dd.btf = btf;
dd.func_info = func_info;
dd.finfo_rec_size = info->func_info_rec_size;
dd.prog_linfo = prog_linfo;
if (json_output)
dump_xlated_json(&dd, buf, member_len, opcodes,
linum);
else
dump_xlated_plain(&dd, buf, member_len, opcodes,
linum);
kernel_syms_destroy(&dd);
}
return 0;
}
static int do_dump(int argc, char **argv)
{
struct bpf_prog_info_linear *info_linear;
char *filepath = NULL;
bool opcodes = false;
bool visual = false;
enum dump_mode mode;
bool linum = false;
int *fds = NULL;
int nb_fds, i = 0;
int err = -1;
__u64 arrays;
if (is_prefix(*argv, "jited")) {
if (disasm_init())
return -1;
mode = DUMP_JITED;
} else if (is_prefix(*argv, "xlated")) {
mode = DUMP_XLATED;
} else {
p_err("expected 'xlated' or 'jited', got: %s", *argv);
return -1;
}
NEXT_ARG();
if (argc < 2)
usage();
fds = malloc(sizeof(int));
if (!fds) {
p_err("mem alloc failed");
return -1;
}
nb_fds = prog_parse_fds(&argc, &argv, &fds);
if (nb_fds < 1)
goto exit_free;
if (is_prefix(*argv, "file")) {
NEXT_ARG();
if (!argc) {
p_err("expected file path");
goto exit_close;
}
if (nb_fds > 1) {
p_err("several programs matched");
goto exit_close;
}
filepath = *argv;
NEXT_ARG();
} else if (is_prefix(*argv, "opcodes")) {
opcodes = true;
NEXT_ARG();
} else if (is_prefix(*argv, "visual")) {
if (nb_fds > 1) {
p_err("several programs matched");
goto exit_close;
}
visual = true;
NEXT_ARG();
} else if (is_prefix(*argv, "linum")) {
linum = true;
NEXT_ARG();
}
if (argc) {
usage();
goto exit_close;
}
if (mode == DUMP_JITED)
arrays = 1UL << BPF_PROG_INFO_JITED_INSNS;
else
arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS;
arrays |= 1UL << BPF_PROG_INFO_JITED_KSYMS;
arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS;
arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO;
arrays |= 1UL << BPF_PROG_INFO_LINE_INFO;
arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO;
if (json_output && nb_fds > 1)
jsonw_start_array(json_wtr); /* root array */
for (i = 0; i < nb_fds; i++) {
info_linear = bpf_program__get_prog_info_linear(fds[i], arrays);
if (IS_ERR_OR_NULL(info_linear)) {
p_err("can't get prog info: %s", strerror(errno));
break;
}
if (json_output && nb_fds > 1) {
jsonw_start_object(json_wtr); /* prog object */
print_prog_header_json(&info_linear->info);
jsonw_name(json_wtr, "insns");
} else if (nb_fds > 1) {
print_prog_header_plain(&info_linear->info);
}
err = prog_dump(&info_linear->info, mode, filepath, opcodes,
visual, linum);
if (json_output && nb_fds > 1)
jsonw_end_object(json_wtr); /* prog object */
else if (i != nb_fds - 1 && nb_fds > 1)
printf("\n");
free(info_linear);
if (err)
break;
close(fds[i]);
}
if (json_output && nb_fds > 1)
jsonw_end_array(json_wtr); /* root array */
exit_close:
for (; i < nb_fds; i++)
close(fds[i]);
exit_free:
free(fds);
return err;
}
static int do_pin(int argc, char **argv)
{
int err;
err = do_pin_any(argc, argv, bpf_prog_get_fd_by_id);
if (!err && json_output)
jsonw_null(json_wtr);
return err;
}
struct map_replace {
int idx;
int fd;
char *name;
};
static int map_replace_compar(const void *p1, const void *p2)
{
const struct map_replace *a = p1, *b = p2;
return a->idx - b->idx;
}
static int parse_attach_detach_args(int argc, char **argv, int *progfd,
enum bpf_attach_type *attach_type,
int *mapfd)
{
if (!REQ_ARGS(3))
return -EINVAL;
*progfd = prog_parse_fd(&argc, &argv);
if (*progfd < 0)
return *progfd;
*attach_type = parse_attach_type(*argv);
if (*attach_type == __MAX_BPF_ATTACH_TYPE) {
p_err("invalid attach/detach type");
return -EINVAL;
}
if (*attach_type == BPF_FLOW_DISSECTOR) {
*mapfd = -1;
return 0;
}
NEXT_ARG();
if (!REQ_ARGS(2))
return -EINVAL;
*mapfd = map_parse_fd(&argc, &argv);
if (*mapfd < 0)
return *mapfd;
return 0;
}
static int do_attach(int argc, char **argv)
{
enum bpf_attach_type attach_type;
int err, progfd;
int mapfd;
err = parse_attach_detach_args(argc, argv,
&progfd, &attach_type, &mapfd);
if (err)
return err;
err = bpf_prog_attach(progfd, mapfd, attach_type, 0);
if (err) {
p_err("failed prog attach to map");
return -EINVAL;
}
if (json_output)
jsonw_null(json_wtr);
return 0;
}
static int do_detach(int argc, char **argv)
{
enum bpf_attach_type attach_type;
int err, progfd;
int mapfd;
err = parse_attach_detach_args(argc, argv,
&progfd, &attach_type, &mapfd);
if (err)
return err;
err = bpf_prog_detach2(progfd, mapfd, attach_type);
if (err) {
p_err("failed prog detach from map");
return -EINVAL;
}
if (json_output)
jsonw_null(json_wtr);
return 0;
}
static int check_single_stdin(char *file_data_in, char *file_ctx_in)
{
if (file_data_in && file_ctx_in &&
!strcmp(file_data_in, "-") && !strcmp(file_ctx_in, "-")) {
p_err("cannot use standard input for both data_in and ctx_in");
return -1;
}
return 0;
}
static int get_run_data(const char *fname, void **data_ptr, unsigned int *size)
{
size_t block_size = 256;
size_t buf_size = block_size;
size_t nb_read = 0;
void *tmp;
FILE *f;
if (!fname) {
*data_ptr = NULL;
*size = 0;
return 0;
}
if (!strcmp(fname, "-"))
f = stdin;
else
f = fopen(fname, "r");
if (!f) {
p_err("failed to open %s: %s", fname, strerror(errno));
return -1;
}
*data_ptr = malloc(block_size);
if (!*data_ptr) {
p_err("failed to allocate memory for data_in/ctx_in: %s",
strerror(errno));
goto err_fclose;
}
while ((nb_read += fread(*data_ptr + nb_read, 1, block_size, f))) {
if (feof(f))
break;
if (ferror(f)) {
p_err("failed to read data_in/ctx_in from %s: %s",
fname, strerror(errno));
goto err_free;
}
if (nb_read > buf_size - block_size) {
if (buf_size == UINT32_MAX) {
p_err("data_in/ctx_in is too long (max: %d)",
UINT32_MAX);
goto err_free;
}
/* No space for fread()-ing next chunk; realloc() */
buf_size *= 2;
tmp = realloc(*data_ptr, buf_size);
if (!tmp) {
p_err("failed to reallocate data_in/ctx_in: %s",
strerror(errno));
goto err_free;
}
*data_ptr = tmp;
}
}
if (f != stdin)
fclose(f);
*size = nb_read;
return 0;
err_free:
free(*data_ptr);
*data_ptr = NULL;
err_fclose:
if (f != stdin)
fclose(f);
return -1;
}
static void hex_print(void *data, unsigned int size, FILE *f)
{
size_t i, j;
char c;
for (i = 0; i < size; i += 16) {
/* Row offset */
fprintf(f, "%07zx\t", i);
/* Hexadecimal values */
for (j = i; j < i + 16 && j < size; j++)
fprintf(f, "%02x%s", *(uint8_t *)(data + j),
j % 2 ? " " : "");
for (; j < i + 16; j++)
fprintf(f, " %s", j % 2 ? " " : "");
/* ASCII values (if relevant), '.' otherwise */
fprintf(f, "| ");
for (j = i; j < i + 16 && j < size; j++) {
c = *(char *)(data + j);
if (c < ' ' || c > '~')
c = '.';
fprintf(f, "%c%s", c, j == i + 7 ? " " : "");
}
fprintf(f, "\n");
}
}
static int
print_run_output(void *data, unsigned int size, const char *fname,
const char *json_key)
{
size_t nb_written;
FILE *f;
if (!fname)
return 0;
if (!strcmp(fname, "-")) {
f = stdout;
if (json_output) {
jsonw_name(json_wtr, json_key);
print_data_json(data, size);
} else {
hex_print(data, size, f);
}
return 0;
}
f = fopen(fname, "w");
if (!f) {
p_err("failed to open %s: %s", fname, strerror(errno));
return -1;
}
nb_written = fwrite(data, 1, size, f);
fclose(f);
if (nb_written != size) {
p_err("failed to write output data/ctx: %s", strerror(errno));
return -1;
}
return 0;
}
static int alloc_run_data(void **data_ptr, unsigned int size_out)
{
*data_ptr = calloc(size_out, 1);
if (!*data_ptr) {
p_err("failed to allocate memory for output data/ctx: %s",
strerror(errno));
return -1;
}
return 0;
}
static int do_run(int argc, char **argv)
{
char *data_fname_in = NULL, *data_fname_out = NULL;
char *ctx_fname_in = NULL, *ctx_fname_out = NULL;
struct bpf_prog_test_run_attr test_attr = {0};
const unsigned int default_size = SZ_32K;
void *data_in = NULL, *data_out = NULL;
void *ctx_in = NULL, *ctx_out = NULL;
unsigned int repeat = 1;
int fd, err;
if (!REQ_ARGS(4))
return -1;
fd = prog_parse_fd(&argc, &argv);
if (fd < 0)
return -1;
while (argc) {
if (detect_common_prefix(*argv, "data_in", "data_out",
"data_size_out", NULL))
return -1;
if (detect_common_prefix(*argv, "ctx_in", "ctx_out",
"ctx_size_out", NULL))
return -1;
if (is_prefix(*argv, "data_in")) {
NEXT_ARG();
if (!REQ_ARGS(1))
return -1;
data_fname_in = GET_ARG();
if (check_single_stdin(data_fname_in, ctx_fname_in))
return -1;
} else if (is_prefix(*argv, "data_out")) {
NEXT_ARG();
if (!REQ_ARGS(1))
return -1;
data_fname_out = GET_ARG();
} else if (is_prefix(*argv, "data_size_out")) {
char *endptr;
NEXT_ARG();
if (!REQ_ARGS(1))
return -1;
test_attr.data_size_out = strtoul(*argv, &endptr, 0);
if (*endptr) {
p_err("can't parse %s as output data size",
*argv);
return -1;
}
NEXT_ARG();
} else if (is_prefix(*argv, "ctx_in")) {
NEXT_ARG();
if (!REQ_ARGS(1))
return -1;
ctx_fname_in = GET_ARG();
if (check_single_stdin(data_fname_in, ctx_fname_in))
return -1;
} else if (is_prefix(*argv, "ctx_out")) {
NEXT_ARG();
if (!REQ_ARGS(1))
return -1;
ctx_fname_out = GET_ARG();
} else if (is_prefix(*argv, "ctx_size_out")) {
char *endptr;
NEXT_ARG();
if (!REQ_ARGS(1))
return -1;
test_attr.ctx_size_out = strtoul(*argv, &endptr, 0);
if (*endptr) {
p_err("can't parse %s as output context size",
*argv);
return -1;
}
NEXT_ARG();
} else if (is_prefix(*argv, "repeat")) {
char *endptr;
NEXT_ARG();
if (!REQ_ARGS(1))
return -1;
repeat = strtoul(*argv, &endptr, 0);
if (*endptr) {
p_err("can't parse %s as repeat number",
*argv);
return -1;
}
NEXT_ARG();
} else {
p_err("expected no more arguments, 'data_in', 'data_out', 'data_size_out', 'ctx_in', 'ctx_out', 'ctx_size_out' or 'repeat', got: '%s'?",
*argv);
return -1;
}
}
err = get_run_data(data_fname_in, &data_in, &test_attr.data_size_in);
if (err)
return -1;
if (data_in) {
if (!test_attr.data_size_out)
test_attr.data_size_out = default_size;
err = alloc_run_data(&data_out, test_attr.data_size_out);
if (err)
goto free_data_in;
}
err = get_run_data(ctx_fname_in, &ctx_in, &test_attr.ctx_size_in);
if (err)
goto free_data_out;
if (ctx_in) {
if (!test_attr.ctx_size_out)
test_attr.ctx_size_out = default_size;
err = alloc_run_data(&ctx_out, test_attr.ctx_size_out);
if (err)
goto free_ctx_in;
}
test_attr.prog_fd = fd;
test_attr.repeat = repeat;
test_attr.data_in = data_in;
test_attr.data_out = data_out;
test_attr.ctx_in = ctx_in;
test_attr.ctx_out = ctx_out;
err = bpf_prog_test_run_xattr(&test_attr);
if (err) {
p_err("failed to run program: %s", strerror(errno));
goto free_ctx_out;
}
err = 0;
if (json_output)
jsonw_start_object(json_wtr); /* root */
/* Do not exit on errors occurring when printing output data/context,
* we still want to print return value and duration for program run.
*/
if (test_attr.data_size_out)
err += print_run_output(test_attr.data_out,
test_attr.data_size_out,
data_fname_out, "data_out");
if (test_attr.ctx_size_out)
err += print_run_output(test_attr.ctx_out,
test_attr.ctx_size_out,
ctx_fname_out, "ctx_out");
if (json_output) {
jsonw_uint_field(json_wtr, "retval", test_attr.retval);
jsonw_uint_field(json_wtr, "duration", test_attr.duration);
jsonw_end_object(json_wtr); /* root */
} else {
fprintf(stdout, "Return value: %u, duration%s: %uns\n",
test_attr.retval,
repeat > 1 ? " (average)" : "", test_attr.duration);
}
free_ctx_out:
free(ctx_out);
free_ctx_in:
free(ctx_in);
free_data_out:
free(data_out);
free_data_in:
free(data_in);
return err;
}
static int load_with_options(int argc, char **argv, bool first_prog_only)
{
enum bpf_prog_type common_prog_type = BPF_PROG_TYPE_UNSPEC;
DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts,
.relaxed_maps = relaxed_maps,
);
struct bpf_object_load_attr load_attr = { 0 };
enum bpf_attach_type expected_attach_type;
struct map_replace *map_replace = NULL;
struct bpf_program *prog = NULL, *pos;
unsigned int old_map_fds = 0;
const char *pinmaps = NULL;
struct bpf_object *obj;
struct bpf_map *map;
const char *pinfile;
unsigned int i, j;
__u32 ifindex = 0;
const char *file;
int idx, err;
if (!REQ_ARGS(2))
return -1;
file = GET_ARG();
pinfile = GET_ARG();
while (argc) {
if (is_prefix(*argv, "type")) {
char *type;
NEXT_ARG();
if (common_prog_type != BPF_PROG_TYPE_UNSPEC) {
p_err("program type already specified");
goto err_free_reuse_maps;
}
if (!REQ_ARGS(1))
goto err_free_reuse_maps;
/* Put a '/' at the end of type to appease libbpf */
type = malloc(strlen(*argv) + 2);
if (!type) {
p_err("mem alloc failed");
goto err_free_reuse_maps;
}
*type = 0;
strcat(type, *argv);
strcat(type, "/");
err = libbpf_prog_type_by_name(type, &common_prog_type,
&expected_attach_type);
free(type);
if (err < 0)
goto err_free_reuse_maps;
NEXT_ARG();
} else if (is_prefix(*argv, "map")) {
void *new_map_replace;
char *endptr, *name;
int fd;
NEXT_ARG();
if (!REQ_ARGS(4))
goto err_free_reuse_maps;
if (is_prefix(*argv, "idx")) {
NEXT_ARG();
idx = strtoul(*argv, &endptr, 0);
if (*endptr) {
p_err("can't parse %s as IDX", *argv);
goto err_free_reuse_maps;
}
name = NULL;
} else if (is_prefix(*argv, "name")) {
NEXT_ARG();
name = *argv;
idx = -1;
} else {
p_err("expected 'idx' or 'name', got: '%s'?",
*argv);
goto err_free_reuse_maps;
}
NEXT_ARG();
fd = map_parse_fd(&argc, &argv);
if (fd < 0)
goto err_free_reuse_maps;
new_map_replace = reallocarray(map_replace,
old_map_fds + 1,
sizeof(*map_replace));
if (!new_map_replace) {
p_err("mem alloc failed");
goto err_free_reuse_maps;
}
map_replace = new_map_replace;
map_replace[old_map_fds].idx = idx;
map_replace[old_map_fds].name = name;
map_replace[old_map_fds].fd = fd;
old_map_fds++;
} else if (is_prefix(*argv, "dev")) {
NEXT_ARG();
if (ifindex) {
p_err("offload device already specified");
goto err_free_reuse_maps;
}
if (!REQ_ARGS(1))
goto err_free_reuse_maps;
ifindex = if_nametoindex(*argv);
if (!ifindex) {
p_err("unrecognized netdevice '%s': %s",
*argv, strerror(errno));
goto err_free_reuse_maps;
}
NEXT_ARG();
} else if (is_prefix(*argv, "pinmaps")) {
NEXT_ARG();
if (!REQ_ARGS(1))
goto err_free_reuse_maps;
pinmaps = GET_ARG();
} else {
p_err("expected no more arguments, 'type', 'map' or 'dev', got: '%s'?",
*argv);
goto err_free_reuse_maps;
}
}
set_max_rlimit();
obj = bpf_object__open_file(file, &open_opts);
if (IS_ERR_OR_NULL(obj)) {
p_err("failed to open object file");
goto err_free_reuse_maps;
}
bpf_object__for_each_program(pos, obj) {
enum bpf_prog_type prog_type = common_prog_type;
if (prog_type == BPF_PROG_TYPE_UNSPEC) {
const char *sec_name = bpf_program__title(pos, false);
err = libbpf_prog_type_by_name(sec_name, &prog_type,
&expected_attach_type);
if (err < 0)
goto err_close_obj;
}
bpf_program__set_ifindex(pos, ifindex);
bpf_program__set_type(pos, prog_type);
bpf_program__set_expected_attach_type(pos, expected_attach_type);
}
qsort(map_replace, old_map_fds, sizeof(*map_replace),
map_replace_compar);
/* After the sort maps by name will be first on the list, because they
* have idx == -1. Resolve them.
*/
j = 0;
while (j < old_map_fds && map_replace[j].name) {
i = 0;
bpf_object__for_each_map(map, obj) {
if (!strcmp(bpf_map__name(map), map_replace[j].name)) {
map_replace[j].idx = i;
break;
}
i++;
}
if (map_replace[j].idx == -1) {
p_err("unable to find map '%s'", map_replace[j].name);
goto err_close_obj;
}
j++;
}
/* Resort if any names were resolved */
if (j)
qsort(map_replace, old_map_fds, sizeof(*map_replace),
map_replace_compar);
/* Set ifindex and name reuse */
j = 0;
idx = 0;
bpf_object__for_each_map(map, obj) {
if (!bpf_map__is_offload_neutral(map))
bpf_map__set_ifindex(map, ifindex);
if (j < old_map_fds && idx == map_replace[j].idx) {
err = bpf_map__reuse_fd(map, map_replace[j++].fd);
if (err) {
p_err("unable to set up map reuse: %d", err);
goto err_close_obj;
}
/* Next reuse wants to apply to the same map */
if (j < old_map_fds && map_replace[j].idx == idx) {
p_err("replacement for map idx %d specified more than once",
idx);
goto err_close_obj;
}
}
idx++;
}
if (j < old_map_fds) {
p_err("map idx '%d' not used", map_replace[j].idx);
goto err_close_obj;
}
load_attr.obj = obj;
if (verifier_logs)
/* log_level1 + log_level2 + stats, but not stable UAPI */
load_attr.log_level = 1 + 2 + 4;
err = bpf_object__load_xattr(&load_attr);
if (err) {
p_err("failed to load object file");
goto err_close_obj;
}
err = mount_bpffs_for_pin(pinfile);
if (err)
goto err_close_obj;
if (first_prog_only) {
prog = bpf_program__next(NULL, obj);
if (!prog) {
p_err("object file doesn't contain any bpf program");
goto err_close_obj;
}
err = bpf_obj_pin(bpf_program__fd(prog), pinfile);
if (err) {
p_err("failed to pin program %s",
bpf_program__title(prog, false));
goto err_close_obj;
}
} else {
err = bpf_object__pin_programs(obj, pinfile);
if (err) {
p_err("failed to pin all programs");
goto err_close_obj;
}
}
if (pinmaps) {
err = bpf_object__pin_maps(obj, pinmaps);
if (err) {
p_err("failed to pin all maps");
goto err_unpin;
}
}
if (json_output)
jsonw_null(json_wtr);
bpf_object__close(obj);
for (i = 0; i < old_map_fds; i++)
close(map_replace[i].fd);
free(map_replace);
return 0;
err_unpin:
if (first_prog_only)
unlink(pinfile);
else
bpf_object__unpin_programs(obj, pinfile);
err_close_obj:
bpf_object__close(obj);
err_free_reuse_maps:
for (i = 0; i < old_map_fds; i++)
close(map_replace[i].fd);
free(map_replace);
return -1;
}
static int do_load(int argc, char **argv)
{
return load_with_options(argc, argv, true);
}
static int do_loadall(int argc, char **argv)
{
return load_with_options(argc, argv, false);
}
static int do_help(int argc, char **argv)
{
if (json_output) {
jsonw_null(json_wtr);
return 0;
}
fprintf(stderr,
"Usage: %s %s { show | list } [PROG]\n"
" %s %s dump xlated PROG [{ file FILE | opcodes | visual | linum }]\n"
" %s %s dump jited PROG [{ file FILE | opcodes | linum }]\n"
" %s %s pin PROG FILE\n"
" %s %s { load | loadall } OBJ PATH \\\n"
" [type TYPE] [dev NAME] \\\n"
" [map { idx IDX | name NAME } MAP]\\\n"
" [pinmaps MAP_DIR]\n"
" %s %s attach PROG ATTACH_TYPE [MAP]\n"
" %s %s detach PROG ATTACH_TYPE [MAP]\n"
" %s %s run PROG \\\n"
" data_in FILE \\\n"
" [data_out FILE [data_size_out L]] \\\n"
" [ctx_in FILE [ctx_out FILE [ctx_size_out M]]] \\\n"
" [repeat N]\n"
" %s %s tracelog\n"
" %s %s help\n"
"\n"
" " HELP_SPEC_MAP "\n"
" " HELP_SPEC_PROGRAM "\n"
" TYPE := { socket | kprobe | kretprobe | classifier | action |\n"
" tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n"
" cgroup/sock | cgroup/dev | lwt_in | lwt_out | lwt_xmit |\n"
" lwt_seg6local | sockops | sk_skb | sk_msg | lirc_mode2 |\n"
" sk_reuseport | flow_dissector | cgroup/sysctl |\n"
" cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
" cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
" cgroup/sendmsg4 | cgroup/sendmsg6 | cgroup/recvmsg4 |\n"
" cgroup/recvmsg6 | cgroup/getsockopt |\n"
" cgroup/setsockopt }\n"
" ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n"
" flow_dissector }\n"
" " HELP_SPEC_OPTIONS "\n"
"",
bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
bin_name, argv[-2]);
return 0;
}
static const struct cmd cmds[] = {
{ "show", do_show },
{ "list", do_show },
{ "help", do_help },
{ "dump", do_dump },
{ "pin", do_pin },
{ "load", do_load },
{ "loadall", do_loadall },
{ "attach", do_attach },
{ "detach", do_detach },
{ "tracelog", do_tracelog },
{ "run", do_run },
{ 0 }
};
int do_prog(int argc, char **argv)
{
return cmd_select(cmds, argc, argv, do_help);
}