bpf tools: Introduce 'bpf' library and add bpf feature check
This is the first patch of libbpf. The goal of libbpf is to create a
standard way for accessing eBPF object files. This patch creates
'Makefile' and 'Build' for it, allows 'make' to build libbpf.a and
libbpf.so, 'make install' to put them into proper directories.
Most part of Makefile is borrowed from traceevent.
Before building, it checks the existence of libelf in Makefile, and deny
to build if not found. Instead of throwing an error if libelf not found,
the error raises in a phony target "elfdep". This design is to ensure
'make clean' still workable even if libelf is not found.
Because libbpf requires 'kern_version' field set for 'union bpf_attr'
(bpfdep" is used for that dependency), Kernel BPF API is also checked
by intruducing a new feature check 'bpf' into tools/build/feature,
which checks the existence and version of linux/bpf.h. When building
libbpf, it searches that file from include/uapi/linux in kernel source
tree (controlled by FEATURE_CHECK_CFLAGS-bpf). Since it searches kernel
source tree it reside, installing of newest kernel headers is not
required, except we are trying to port these files to an old kernel.
To avoid checking that file when perf building, the newly introduced
'bpf' feature check doesn't added into FEATURE_TESTS and
FEATURE_DISPLAY by default in tools/build/Makefile.feature, but added
into libbpf's specific.
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Bcc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1435716878-189507-4-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-01 10:13:51 +08:00
|
|
|
/*
|
|
|
|
* Common eBPF ELF object loading operations.
|
|
|
|
*
|
|
|
|
* Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
|
|
|
|
* Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
|
|
|
|
* Copyright (C) 2015 Huawei Inc.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <stdlib.h>
|
2015-07-01 10:13:52 +08:00
|
|
|
#include <stdio.h>
|
|
|
|
#include <stdarg.h>
|
2015-07-01 10:14:02 +08:00
|
|
|
#include <inttypes.h>
|
2015-07-01 10:13:52 +08:00
|
|
|
#include <string.h>
|
bpf tools: Introduce 'bpf' library and add bpf feature check
This is the first patch of libbpf. The goal of libbpf is to create a
standard way for accessing eBPF object files. This patch creates
'Makefile' and 'Build' for it, allows 'make' to build libbpf.a and
libbpf.so, 'make install' to put them into proper directories.
Most part of Makefile is borrowed from traceevent.
Before building, it checks the existence of libelf in Makefile, and deny
to build if not found. Instead of throwing an error if libelf not found,
the error raises in a phony target "elfdep". This design is to ensure
'make clean' still workable even if libelf is not found.
Because libbpf requires 'kern_version' field set for 'union bpf_attr'
(bpfdep" is used for that dependency), Kernel BPF API is also checked
by intruducing a new feature check 'bpf' into tools/build/feature,
which checks the existence and version of linux/bpf.h. When building
libbpf, it searches that file from include/uapi/linux in kernel source
tree (controlled by FEATURE_CHECK_CFLAGS-bpf). Since it searches kernel
source tree it reside, installing of newest kernel headers is not
required, except we are trying to port these files to an old kernel.
To avoid checking that file when perf building, the newly introduced
'bpf' feature check doesn't added into FEATURE_TESTS and
FEATURE_DISPLAY by default in tools/build/Makefile.feature, but added
into libbpf's specific.
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Bcc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1435716878-189507-4-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-01 10:13:51 +08:00
|
|
|
#include <unistd.h>
|
2015-07-01 10:13:53 +08:00
|
|
|
#include <fcntl.h>
|
|
|
|
#include <errno.h>
|
bpf tools: Introduce 'bpf' library and add bpf feature check
This is the first patch of libbpf. The goal of libbpf is to create a
standard way for accessing eBPF object files. This patch creates
'Makefile' and 'Build' for it, allows 'make' to build libbpf.a and
libbpf.so, 'make install' to put them into proper directories.
Most part of Makefile is borrowed from traceevent.
Before building, it checks the existence of libelf in Makefile, and deny
to build if not found. Instead of throwing an error if libelf not found,
the error raises in a phony target "elfdep". This design is to ensure
'make clean' still workable even if libelf is not found.
Because libbpf requires 'kern_version' field set for 'union bpf_attr'
(bpfdep" is used for that dependency), Kernel BPF API is also checked
by intruducing a new feature check 'bpf' into tools/build/feature,
which checks the existence and version of linux/bpf.h. When building
libbpf, it searches that file from include/uapi/linux in kernel source
tree (controlled by FEATURE_CHECK_CFLAGS-bpf). Since it searches kernel
source tree it reside, installing of newest kernel headers is not
required, except we are trying to port these files to an old kernel.
To avoid checking that file when perf building, the newly introduced
'bpf' feature check doesn't added into FEATURE_TESTS and
FEATURE_DISPLAY by default in tools/build/Makefile.feature, but added
into libbpf's specific.
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Bcc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1435716878-189507-4-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-01 10:13:51 +08:00
|
|
|
#include <asm/unistd.h>
|
2015-07-01 10:13:57 +08:00
|
|
|
#include <linux/kernel.h>
|
bpf tools: Introduce 'bpf' library and add bpf feature check
This is the first patch of libbpf. The goal of libbpf is to create a
standard way for accessing eBPF object files. This patch creates
'Makefile' and 'Build' for it, allows 'make' to build libbpf.a and
libbpf.so, 'make install' to put them into proper directories.
Most part of Makefile is borrowed from traceevent.
Before building, it checks the existence of libelf in Makefile, and deny
to build if not found. Instead of throwing an error if libelf not found,
the error raises in a phony target "elfdep". This design is to ensure
'make clean' still workable even if libelf is not found.
Because libbpf requires 'kern_version' field set for 'union bpf_attr'
(bpfdep" is used for that dependency), Kernel BPF API is also checked
by intruducing a new feature check 'bpf' into tools/build/feature,
which checks the existence and version of linux/bpf.h. When building
libbpf, it searches that file from include/uapi/linux in kernel source
tree (controlled by FEATURE_CHECK_CFLAGS-bpf). Since it searches kernel
source tree it reside, installing of newest kernel headers is not
required, except we are trying to port these files to an old kernel.
To avoid checking that file when perf building, the newly introduced
'bpf' feature check doesn't added into FEATURE_TESTS and
FEATURE_DISPLAY by default in tools/build/Makefile.feature, but added
into libbpf's specific.
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Bcc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1435716878-189507-4-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-01 10:13:51 +08:00
|
|
|
#include <linux/bpf.h>
|
2015-07-01 10:14:10 +08:00
|
|
|
#include <linux/list.h>
|
2015-07-01 10:13:53 +08:00
|
|
|
#include <libelf.h>
|
|
|
|
#include <gelf.h>
|
bpf tools: Introduce 'bpf' library and add bpf feature check
This is the first patch of libbpf. The goal of libbpf is to create a
standard way for accessing eBPF object files. This patch creates
'Makefile' and 'Build' for it, allows 'make' to build libbpf.a and
libbpf.so, 'make install' to put them into proper directories.
Most part of Makefile is borrowed from traceevent.
Before building, it checks the existence of libelf in Makefile, and deny
to build if not found. Instead of throwing an error if libelf not found,
the error raises in a phony target "elfdep". This design is to ensure
'make clean' still workable even if libelf is not found.
Because libbpf requires 'kern_version' field set for 'union bpf_attr'
(bpfdep" is used for that dependency), Kernel BPF API is also checked
by intruducing a new feature check 'bpf' into tools/build/feature,
which checks the existence and version of linux/bpf.h. When building
libbpf, it searches that file from include/uapi/linux in kernel source
tree (controlled by FEATURE_CHECK_CFLAGS-bpf). Since it searches kernel
source tree it reside, installing of newest kernel headers is not
required, except we are trying to port these files to an old kernel.
To avoid checking that file when perf building, the newly introduced
'bpf' feature check doesn't added into FEATURE_TESTS and
FEATURE_DISPLAY by default in tools/build/Makefile.feature, but added
into libbpf's specific.
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Bcc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1435716878-189507-4-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-01 10:13:51 +08:00
|
|
|
|
|
|
|
#include "libbpf.h"
|
2015-07-01 10:14:04 +08:00
|
|
|
#include "bpf.h"
|
2015-07-01 10:13:52 +08:00
|
|
|
|
|
|
|
#define __printf(a, b) __attribute__((format(printf, a, b)))
|
|
|
|
|
|
|
|
__printf(1, 2)
|
|
|
|
static int __base_pr(const char *format, ...)
|
|
|
|
{
|
|
|
|
va_list args;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
va_start(args, format);
|
|
|
|
err = vfprintf(stderr, format, args);
|
|
|
|
va_end(args);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static __printf(1, 2) libbpf_print_fn_t __pr_warning = __base_pr;
|
|
|
|
static __printf(1, 2) libbpf_print_fn_t __pr_info = __base_pr;
|
|
|
|
static __printf(1, 2) libbpf_print_fn_t __pr_debug;
|
|
|
|
|
|
|
|
#define __pr(func, fmt, ...) \
|
|
|
|
do { \
|
|
|
|
if ((func)) \
|
|
|
|
(func)("libbpf: " fmt, ##__VA_ARGS__); \
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
#define pr_warning(fmt, ...) __pr(__pr_warning, fmt, ##__VA_ARGS__)
|
|
|
|
#define pr_info(fmt, ...) __pr(__pr_info, fmt, ##__VA_ARGS__)
|
|
|
|
#define pr_debug(fmt, ...) __pr(__pr_debug, fmt, ##__VA_ARGS__)
|
|
|
|
|
|
|
|
void libbpf_set_print(libbpf_print_fn_t warn,
|
|
|
|
libbpf_print_fn_t info,
|
|
|
|
libbpf_print_fn_t debug)
|
|
|
|
{
|
|
|
|
__pr_warning = warn;
|
|
|
|
__pr_info = info;
|
|
|
|
__pr_debug = debug;
|
|
|
|
}
|
2015-07-01 10:13:53 +08:00
|
|
|
|
2015-11-06 21:49:37 +08:00
|
|
|
#define STRERR_BUFSIZE 128
|
|
|
|
|
|
|
|
#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START)
|
|
|
|
#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c)
|
|
|
|
#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
|
|
|
|
|
|
|
|
static const char *libbpf_strerror_table[NR_ERRNO] = {
|
|
|
|
[ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf",
|
|
|
|
[ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid",
|
|
|
|
[ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost",
|
|
|
|
[ERRCODE_OFFSET(ENDIAN)] = "Endian missmatch",
|
|
|
|
[ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf",
|
|
|
|
[ERRCODE_OFFSET(RELOC)] = "Relocation failed",
|
|
|
|
[ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading",
|
|
|
|
[ERRCODE_OFFSET(PROG2BIG)] = "Program too big",
|
|
|
|
[ERRCODE_OFFSET(KVER)] = "Incorrect kernel version",
|
|
|
|
};
|
|
|
|
|
|
|
|
int libbpf_strerror(int err, char *buf, size_t size)
|
|
|
|
{
|
|
|
|
if (!buf || !size)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
err = err > 0 ? err : -err;
|
|
|
|
|
|
|
|
if (err < __LIBBPF_ERRNO__START) {
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
ret = strerror_r(err, buf, size);
|
|
|
|
buf[size - 1] = '\0';
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (err < __LIBBPF_ERRNO__END) {
|
|
|
|
const char *msg;
|
|
|
|
|
|
|
|
msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
|
|
|
|
snprintf(buf, size, "%s", msg);
|
|
|
|
buf[size - 1] = '\0';
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
snprintf(buf, size, "Unknown libbpf error %d", err);
|
|
|
|
buf[size - 1] = '\0';
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
#define CHECK_ERR(action, err, out) do { \
|
|
|
|
err = action; \
|
|
|
|
if (err) \
|
|
|
|
goto out; \
|
|
|
|
} while(0)
|
|
|
|
|
|
|
|
|
2015-07-01 10:13:53 +08:00
|
|
|
/* Copied from tools/perf/util/util.h */
|
|
|
|
#ifndef zfree
|
|
|
|
# define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef zclose
|
|
|
|
# define zclose(fd) ({ \
|
|
|
|
int ___err = 0; \
|
|
|
|
if ((fd) >= 0) \
|
|
|
|
___err = close((fd)); \
|
|
|
|
fd = -1; \
|
|
|
|
___err; })
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifdef HAVE_LIBELF_MMAP_SUPPORT
|
|
|
|
# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ_MMAP
|
|
|
|
#else
|
|
|
|
# define LIBBPF_ELF_C_READ_MMAP ELF_C_READ
|
|
|
|
#endif
|
|
|
|
|
2015-07-01 10:14:00 +08:00
|
|
|
/*
|
|
|
|
* bpf_prog should be a better name but it has been used in
|
|
|
|
* linux/filter.h.
|
|
|
|
*/
|
|
|
|
struct bpf_program {
|
|
|
|
/* Index in elf obj file, for relocation use. */
|
|
|
|
int idx;
|
|
|
|
char *section_name;
|
|
|
|
struct bpf_insn *insns;
|
|
|
|
size_t insns_cnt;
|
2015-07-01 10:14:02 +08:00
|
|
|
|
|
|
|
struct {
|
|
|
|
int insn_idx;
|
|
|
|
int map_idx;
|
|
|
|
} *reloc_desc;
|
|
|
|
int nr_reloc;
|
2015-07-01 10:14:07 +08:00
|
|
|
|
2015-11-16 20:10:09 +08:00
|
|
|
struct {
|
|
|
|
int nr;
|
|
|
|
int *fds;
|
|
|
|
} instances;
|
|
|
|
bpf_program_prep_t preprocessor;
|
2015-07-01 10:14:08 +08:00
|
|
|
|
|
|
|
struct bpf_object *obj;
|
|
|
|
void *priv;
|
|
|
|
bpf_program_clear_priv_t clear_priv;
|
2015-07-01 10:14:00 +08:00
|
|
|
};
|
|
|
|
|
2015-11-27 16:47:35 +08:00
|
|
|
struct bpf_map {
|
|
|
|
int fd;
|
2015-11-27 16:47:36 +08:00
|
|
|
char *name;
|
2015-11-27 16:47:35 +08:00
|
|
|
struct bpf_map_def def;
|
|
|
|
void *priv;
|
|
|
|
bpf_map_clear_priv_t clear_priv;
|
|
|
|
};
|
|
|
|
|
2015-07-01 10:14:10 +08:00
|
|
|
static LIST_HEAD(bpf_objects_list);
|
|
|
|
|
2015-07-01 10:13:53 +08:00
|
|
|
struct bpf_object {
|
2015-07-01 10:13:57 +08:00
|
|
|
char license[64];
|
|
|
|
u32 kern_version;
|
2015-07-01 10:13:58 +08:00
|
|
|
|
2015-07-01 10:14:00 +08:00
|
|
|
struct bpf_program *programs;
|
|
|
|
size_t nr_programs;
|
2015-11-27 16:47:35 +08:00
|
|
|
struct bpf_map *maps;
|
|
|
|
size_t nr_maps;
|
|
|
|
|
2015-07-01 10:14:04 +08:00
|
|
|
bool loaded;
|
2015-07-01 10:14:00 +08:00
|
|
|
|
2015-07-01 10:13:53 +08:00
|
|
|
/*
|
|
|
|
* Information when doing elf related work. Only valid if fd
|
|
|
|
* is valid.
|
|
|
|
*/
|
|
|
|
struct {
|
|
|
|
int fd;
|
2015-07-01 10:13:54 +08:00
|
|
|
void *obj_buf;
|
|
|
|
size_t obj_buf_sz;
|
2015-07-01 10:13:53 +08:00
|
|
|
Elf *elf;
|
|
|
|
GElf_Ehdr ehdr;
|
bpf tools: Collect symbol table from SHT_SYMTAB section
This patch collects symbols section. This section is useful when linking
BPF maps.
What 'bpf_map_xxx()' functions actually require are map's file
descriptors (and the internal verifier converts fds into pointers to
'struct bpf_map'), which we don't know when compiling. Therefore, we
should make compiler generate a 'ldr_64 r1, <imm>' instruction, and
fill the 'imm' field with the actual file descriptor when loading in
libbpf.
BPF programs should be written in this way:
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(unsigned long),
.value_size = sizeof(unsigned long),
.max_entries = 1000000,
};
SEC("my_func=sys_write")
int my_func(void *ctx)
{
...
bpf_map_update_elem(&my_map, &key, &value, BPF_ANY);
...
}
Compiler should convert '&my_map' into a 'ldr_64, r1, <imm>'
instruction, where imm should be the address of 'my_map'. According to
the address, libbpf knows which map it actually referenced, and then
fills the imm field with the 'fd' of that map created by it.
However, since we never really 'link' the object file, the imm field is
only a record in relocation section. Therefore libbpf should do the
relocation:
1. In relocation section (type == SHT_REL), positions of each such
'ldr_64' instruction are recorded with a reference of an entry in
symbol table (SHT_SYMTAB);
2. From records in symbol table we can find the indics of map
variables.
Libbpf first record SHT_SYMTAB and positions of each instruction which
required bu such operation. Then create file descriptor. Finally, after
map creation complete, replace the imm field.
This is the first patch of BPF map related stuff. It records SHT_SYMTAB
into object's efile field for further use.
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1435716878-189507-12-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-01 10:13:59 +08:00
|
|
|
Elf_Data *symbols;
|
2015-12-08 10:25:30 +08:00
|
|
|
size_t strtabidx;
|
2015-07-01 10:14:01 +08:00
|
|
|
struct {
|
|
|
|
GElf_Shdr shdr;
|
|
|
|
Elf_Data *data;
|
|
|
|
} *reloc;
|
|
|
|
int nr_reloc;
|
2015-07-01 10:13:53 +08:00
|
|
|
} efile;
|
2015-07-01 10:14:10 +08:00
|
|
|
/*
|
|
|
|
* All loaded bpf_object is linked in a list, which is
|
|
|
|
* hidden to caller. bpf_objects__<func> handlers deal with
|
|
|
|
* all objects.
|
|
|
|
*/
|
|
|
|
struct list_head list;
|
2015-07-01 10:13:53 +08:00
|
|
|
char path[];
|
|
|
|
};
|
|
|
|
#define obj_elf_valid(o) ((o)->efile.elf)
|
|
|
|
|
2015-07-01 10:14:07 +08:00
|
|
|
static void bpf_program__unload(struct bpf_program *prog)
|
|
|
|
{
|
2015-11-16 20:10:09 +08:00
|
|
|
int i;
|
|
|
|
|
2015-07-01 10:14:07 +08:00
|
|
|
if (!prog)
|
|
|
|
return;
|
|
|
|
|
2015-11-16 20:10:09 +08:00
|
|
|
/*
|
|
|
|
* If the object is opened but the program was never loaded,
|
|
|
|
* it is possible that prog->instances.nr == -1.
|
|
|
|
*/
|
|
|
|
if (prog->instances.nr > 0) {
|
|
|
|
for (i = 0; i < prog->instances.nr; i++)
|
|
|
|
zclose(prog->instances.fds[i]);
|
|
|
|
} else if (prog->instances.nr != -1) {
|
|
|
|
pr_warning("Internal error: instances.nr is %d\n",
|
|
|
|
prog->instances.nr);
|
|
|
|
}
|
|
|
|
|
|
|
|
prog->instances.nr = -1;
|
|
|
|
zfree(&prog->instances.fds);
|
2015-07-01 10:14:07 +08:00
|
|
|
}
|
|
|
|
|
2015-07-01 10:14:00 +08:00
|
|
|
static void bpf_program__exit(struct bpf_program *prog)
|
|
|
|
{
|
|
|
|
if (!prog)
|
|
|
|
return;
|
|
|
|
|
2015-07-01 10:14:08 +08:00
|
|
|
if (prog->clear_priv)
|
|
|
|
prog->clear_priv(prog, prog->priv);
|
|
|
|
|
|
|
|
prog->priv = NULL;
|
|
|
|
prog->clear_priv = NULL;
|
|
|
|
|
2015-07-01 10:14:07 +08:00
|
|
|
bpf_program__unload(prog);
|
2015-07-01 10:14:00 +08:00
|
|
|
zfree(&prog->section_name);
|
|
|
|
zfree(&prog->insns);
|
2015-07-01 10:14:02 +08:00
|
|
|
zfree(&prog->reloc_desc);
|
|
|
|
|
|
|
|
prog->nr_reloc = 0;
|
2015-07-01 10:14:00 +08:00
|
|
|
prog->insns_cnt = 0;
|
|
|
|
prog->idx = -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
bpf_program__init(void *data, size_t size, char *name, int idx,
|
|
|
|
struct bpf_program *prog)
|
|
|
|
{
|
|
|
|
if (size < sizeof(struct bpf_insn)) {
|
|
|
|
pr_warning("corrupted section '%s'\n", name);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
bzero(prog, sizeof(*prog));
|
|
|
|
|
|
|
|
prog->section_name = strdup(name);
|
|
|
|
if (!prog->section_name) {
|
|
|
|
pr_warning("failed to alloc name for prog %s\n",
|
|
|
|
name);
|
|
|
|
goto errout;
|
|
|
|
}
|
|
|
|
|
|
|
|
prog->insns = malloc(size);
|
|
|
|
if (!prog->insns) {
|
|
|
|
pr_warning("failed to alloc insns for %s\n", name);
|
|
|
|
goto errout;
|
|
|
|
}
|
|
|
|
prog->insns_cnt = size / sizeof(struct bpf_insn);
|
|
|
|
memcpy(prog->insns, data,
|
|
|
|
prog->insns_cnt * sizeof(struct bpf_insn));
|
|
|
|
prog->idx = idx;
|
2015-11-16 20:10:09 +08:00
|
|
|
prog->instances.fds = NULL;
|
|
|
|
prog->instances.nr = -1;
|
2015-07-01 10:14:00 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
errout:
|
|
|
|
bpf_program__exit(prog);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
|
|
|
|
char *name, int idx)
|
|
|
|
{
|
|
|
|
struct bpf_program prog, *progs;
|
|
|
|
int nr_progs, err;
|
|
|
|
|
|
|
|
err = bpf_program__init(data, size, name, idx, &prog);
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
|
|
|
|
progs = obj->programs;
|
|
|
|
nr_progs = obj->nr_programs;
|
|
|
|
|
|
|
|
progs = realloc(progs, sizeof(progs[0]) * (nr_progs + 1));
|
|
|
|
if (!progs) {
|
|
|
|
/*
|
|
|
|
* In this case the original obj->programs
|
|
|
|
* is still valid, so don't need special treat for
|
|
|
|
* bpf_close_object().
|
|
|
|
*/
|
|
|
|
pr_warning("failed to alloc a new program '%s'\n",
|
|
|
|
name);
|
|
|
|
bpf_program__exit(&prog);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
pr_debug("found program %s\n", prog.section_name);
|
|
|
|
obj->programs = progs;
|
|
|
|
obj->nr_programs = nr_progs + 1;
|
2015-07-01 10:14:08 +08:00
|
|
|
prog.obj = obj;
|
2015-07-01 10:14:00 +08:00
|
|
|
progs[nr_progs] = prog;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-07-01 10:13:54 +08:00
|
|
|
static struct bpf_object *bpf_object__new(const char *path,
|
|
|
|
void *obj_buf,
|
|
|
|
size_t obj_buf_sz)
|
2015-07-01 10:13:53 +08:00
|
|
|
{
|
|
|
|
struct bpf_object *obj;
|
|
|
|
|
|
|
|
obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
|
|
|
|
if (!obj) {
|
|
|
|
pr_warning("alloc memory failed for %s\n", path);
|
2015-11-06 21:49:37 +08:00
|
|
|
return ERR_PTR(-ENOMEM);
|
2015-07-01 10:13:53 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
strcpy(obj->path, path);
|
|
|
|
obj->efile.fd = -1;
|
2015-07-01 10:13:54 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Caller of this function should also calls
|
|
|
|
* bpf_object__elf_finish() after data collection to return
|
|
|
|
* obj_buf to user. If not, we should duplicate the buffer to
|
|
|
|
* avoid user freeing them before elf finish.
|
|
|
|
*/
|
|
|
|
obj->efile.obj_buf = obj_buf;
|
|
|
|
obj->efile.obj_buf_sz = obj_buf_sz;
|
|
|
|
|
2015-07-01 10:14:04 +08:00
|
|
|
obj->loaded = false;
|
2015-07-01 10:14:10 +08:00
|
|
|
|
|
|
|
INIT_LIST_HEAD(&obj->list);
|
|
|
|
list_add(&obj->list, &bpf_objects_list);
|
2015-07-01 10:13:53 +08:00
|
|
|
return obj;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void bpf_object__elf_finish(struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
if (!obj_elf_valid(obj))
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (obj->efile.elf) {
|
|
|
|
elf_end(obj->efile.elf);
|
|
|
|
obj->efile.elf = NULL;
|
|
|
|
}
|
bpf tools: Collect symbol table from SHT_SYMTAB section
This patch collects symbols section. This section is useful when linking
BPF maps.
What 'bpf_map_xxx()' functions actually require are map's file
descriptors (and the internal verifier converts fds into pointers to
'struct bpf_map'), which we don't know when compiling. Therefore, we
should make compiler generate a 'ldr_64 r1, <imm>' instruction, and
fill the 'imm' field with the actual file descriptor when loading in
libbpf.
BPF programs should be written in this way:
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(unsigned long),
.value_size = sizeof(unsigned long),
.max_entries = 1000000,
};
SEC("my_func=sys_write")
int my_func(void *ctx)
{
...
bpf_map_update_elem(&my_map, &key, &value, BPF_ANY);
...
}
Compiler should convert '&my_map' into a 'ldr_64, r1, <imm>'
instruction, where imm should be the address of 'my_map'. According to
the address, libbpf knows which map it actually referenced, and then
fills the imm field with the 'fd' of that map created by it.
However, since we never really 'link' the object file, the imm field is
only a record in relocation section. Therefore libbpf should do the
relocation:
1. In relocation section (type == SHT_REL), positions of each such
'ldr_64' instruction are recorded with a reference of an entry in
symbol table (SHT_SYMTAB);
2. From records in symbol table we can find the indics of map
variables.
Libbpf first record SHT_SYMTAB and positions of each instruction which
required bu such operation. Then create file descriptor. Finally, after
map creation complete, replace the imm field.
This is the first patch of BPF map related stuff. It records SHT_SYMTAB
into object's efile field for further use.
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1435716878-189507-12-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-01 10:13:59 +08:00
|
|
|
obj->efile.symbols = NULL;
|
2015-07-01 10:14:01 +08:00
|
|
|
|
|
|
|
zfree(&obj->efile.reloc);
|
|
|
|
obj->efile.nr_reloc = 0;
|
2015-07-01 10:13:53 +08:00
|
|
|
zclose(obj->efile.fd);
|
2015-07-01 10:13:54 +08:00
|
|
|
obj->efile.obj_buf = NULL;
|
|
|
|
obj->efile.obj_buf_sz = 0;
|
2015-07-01 10:13:53 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int bpf_object__elf_init(struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
int err = 0;
|
|
|
|
GElf_Ehdr *ep;
|
|
|
|
|
|
|
|
if (obj_elf_valid(obj)) {
|
|
|
|
pr_warning("elf init: internal error\n");
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__LIBELF;
|
2015-07-01 10:13:53 +08:00
|
|
|
}
|
|
|
|
|
2015-07-01 10:13:54 +08:00
|
|
|
if (obj->efile.obj_buf_sz > 0) {
|
|
|
|
/*
|
|
|
|
* obj_buf should have been validated by
|
|
|
|
* bpf_object__open_buffer().
|
|
|
|
*/
|
|
|
|
obj->efile.elf = elf_memory(obj->efile.obj_buf,
|
|
|
|
obj->efile.obj_buf_sz);
|
|
|
|
} else {
|
|
|
|
obj->efile.fd = open(obj->path, O_RDONLY);
|
|
|
|
if (obj->efile.fd < 0) {
|
|
|
|
pr_warning("failed to open %s: %s\n", obj->path,
|
|
|
|
strerror(errno));
|
|
|
|
return -errno;
|
|
|
|
}
|
|
|
|
|
|
|
|
obj->efile.elf = elf_begin(obj->efile.fd,
|
|
|
|
LIBBPF_ELF_C_READ_MMAP,
|
|
|
|
NULL);
|
2015-07-01 10:13:53 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (!obj->efile.elf) {
|
|
|
|
pr_warning("failed to open %s as ELF file\n",
|
|
|
|
obj->path);
|
2015-11-06 21:49:37 +08:00
|
|
|
err = -LIBBPF_ERRNO__LIBELF;
|
2015-07-01 10:13:53 +08:00
|
|
|
goto errout;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
|
|
|
|
pr_warning("failed to get EHDR from %s\n",
|
|
|
|
obj->path);
|
2015-11-06 21:49:37 +08:00
|
|
|
err = -LIBBPF_ERRNO__FORMAT;
|
2015-07-01 10:13:53 +08:00
|
|
|
goto errout;
|
|
|
|
}
|
|
|
|
ep = &obj->efile.ehdr;
|
|
|
|
|
|
|
|
if ((ep->e_type != ET_REL) || (ep->e_machine != 0)) {
|
|
|
|
pr_warning("%s is not an eBPF object file\n",
|
|
|
|
obj->path);
|
2015-11-06 21:49:37 +08:00
|
|
|
err = -LIBBPF_ERRNO__FORMAT;
|
2015-07-01 10:13:53 +08:00
|
|
|
goto errout;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
errout:
|
|
|
|
bpf_object__elf_finish(obj);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2015-07-01 10:13:55 +08:00
|
|
|
static int
|
|
|
|
bpf_object__check_endianness(struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
static unsigned int const endian = 1;
|
|
|
|
|
|
|
|
switch (obj->efile.ehdr.e_ident[EI_DATA]) {
|
|
|
|
case ELFDATA2LSB:
|
|
|
|
/* We are big endian, BPF obj is little endian. */
|
|
|
|
if (*(unsigned char const *)&endian != 1)
|
|
|
|
goto mismatch;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case ELFDATA2MSB:
|
|
|
|
/* We are little endian, BPF obj is big endian. */
|
|
|
|
if (*(unsigned char const *)&endian != 0)
|
|
|
|
goto mismatch;
|
|
|
|
break;
|
|
|
|
default:
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__ENDIAN;
|
2015-07-01 10:13:55 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
mismatch:
|
|
|
|
pr_warning("Error: endianness mismatch.\n");
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__ENDIAN;
|
2015-07-01 10:13:55 +08:00
|
|
|
}
|
|
|
|
|
2015-07-01 10:13:57 +08:00
|
|
|
static int
|
|
|
|
bpf_object__init_license(struct bpf_object *obj,
|
|
|
|
void *data, size_t size)
|
|
|
|
{
|
|
|
|
memcpy(obj->license, data,
|
|
|
|
min(size, sizeof(obj->license) - 1));
|
|
|
|
pr_debug("license of %s is %s\n", obj->path, obj->license);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
bpf_object__init_kversion(struct bpf_object *obj,
|
|
|
|
void *data, size_t size)
|
|
|
|
{
|
|
|
|
u32 kver;
|
|
|
|
|
|
|
|
if (size != sizeof(kver)) {
|
|
|
|
pr_warning("invalid kver section in %s\n", obj->path);
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__FORMAT;
|
2015-07-01 10:13:57 +08:00
|
|
|
}
|
|
|
|
memcpy(&kver, data, sizeof(kver));
|
|
|
|
obj->kern_version = kver;
|
|
|
|
pr_debug("kernel version of %s is %x\n", obj->path,
|
|
|
|
obj->kern_version);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-07-01 10:13:58 +08:00
|
|
|
static int
|
|
|
|
bpf_object__init_maps(struct bpf_object *obj, void *data,
|
|
|
|
size_t size)
|
|
|
|
{
|
2015-11-27 16:47:35 +08:00
|
|
|
size_t nr_maps;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
nr_maps = size / sizeof(struct bpf_map_def);
|
|
|
|
if (!data || !nr_maps) {
|
2015-07-01 10:13:58 +08:00
|
|
|
pr_debug("%s doesn't need map definition\n",
|
|
|
|
obj->path);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-11-27 16:47:35 +08:00
|
|
|
pr_debug("maps in %s: %zd bytes\n", obj->path, size);
|
|
|
|
|
|
|
|
obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
|
|
|
|
if (!obj->maps) {
|
|
|
|
pr_warning("alloc maps for object failed\n");
|
2015-07-01 10:13:58 +08:00
|
|
|
return -ENOMEM;
|
|
|
|
}
|
2015-11-27 16:47:35 +08:00
|
|
|
obj->nr_maps = nr_maps;
|
|
|
|
|
|
|
|
for (i = 0; i < nr_maps; i++) {
|
|
|
|
struct bpf_map_def *def = &obj->maps[i].def;
|
2015-07-01 10:13:58 +08:00
|
|
|
|
2015-11-27 16:47:35 +08:00
|
|
|
/*
|
|
|
|
* fill all fd with -1 so won't close incorrect
|
|
|
|
* fd (fd=0 is stdin) when failure (zclose won't close
|
|
|
|
* negative fd)).
|
|
|
|
*/
|
|
|
|
obj->maps[i].fd = -1;
|
|
|
|
|
|
|
|
/* Save map definition into obj->maps */
|
|
|
|
*def = ((struct bpf_map_def *)data)[i];
|
|
|
|
}
|
2015-07-01 10:13:58 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-12-08 10:25:29 +08:00
|
|
|
static int
|
2015-11-27 16:47:36 +08:00
|
|
|
bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
Elf_Data *symbols = obj->efile.symbols;
|
|
|
|
|
|
|
|
if (!symbols || maps_shndx < 0)
|
2015-12-08 10:25:29 +08:00
|
|
|
return -EINVAL;
|
2015-11-27 16:47:36 +08:00
|
|
|
|
|
|
|
for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
|
|
|
|
GElf_Sym sym;
|
|
|
|
size_t map_idx;
|
|
|
|
const char *map_name;
|
|
|
|
|
|
|
|
if (!gelf_getsym(symbols, i, &sym))
|
|
|
|
continue;
|
|
|
|
if (sym.st_shndx != maps_shndx)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
map_name = elf_strptr(obj->efile.elf,
|
2015-12-08 10:25:30 +08:00
|
|
|
obj->efile.strtabidx,
|
2015-11-27 16:47:36 +08:00
|
|
|
sym.st_name);
|
|
|
|
map_idx = sym.st_value / sizeof(struct bpf_map_def);
|
|
|
|
if (map_idx >= obj->nr_maps) {
|
|
|
|
pr_warning("index of map \"%s\" is buggy: %zu > %zu\n",
|
|
|
|
map_name, map_idx, obj->nr_maps);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
obj->maps[map_idx].name = strdup(map_name);
|
2015-12-08 10:25:29 +08:00
|
|
|
if (!obj->maps[map_idx].name) {
|
|
|
|
pr_warning("failed to alloc map name\n");
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
2015-11-27 16:47:36 +08:00
|
|
|
pr_debug("map %zu is \"%s\"\n", map_idx,
|
|
|
|
obj->maps[map_idx].name);
|
|
|
|
}
|
2015-12-08 10:25:29 +08:00
|
|
|
return 0;
|
2015-11-27 16:47:36 +08:00
|
|
|
}
|
|
|
|
|
2015-07-01 10:13:56 +08:00
|
|
|
static int bpf_object__elf_collect(struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
Elf *elf = obj->efile.elf;
|
|
|
|
GElf_Ehdr *ep = &obj->efile.ehdr;
|
|
|
|
Elf_Scn *scn = NULL;
|
2015-11-27 16:47:36 +08:00
|
|
|
int idx = 0, err = 0, maps_shndx = -1;
|
2015-07-01 10:13:56 +08:00
|
|
|
|
|
|
|
/* Elf is corrupted/truncated, avoid calling elf_strptr. */
|
|
|
|
if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
|
|
|
|
pr_warning("failed to get e_shstrndx from %s\n",
|
|
|
|
obj->path);
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__FORMAT;
|
2015-07-01 10:13:56 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
while ((scn = elf_nextscn(elf, scn)) != NULL) {
|
|
|
|
char *name;
|
|
|
|
GElf_Shdr sh;
|
|
|
|
Elf_Data *data;
|
|
|
|
|
|
|
|
idx++;
|
|
|
|
if (gelf_getshdr(scn, &sh) != &sh) {
|
|
|
|
pr_warning("failed to get section header from %s\n",
|
|
|
|
obj->path);
|
2015-11-06 21:49:37 +08:00
|
|
|
err = -LIBBPF_ERRNO__FORMAT;
|
2015-07-01 10:13:56 +08:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
|
|
|
|
if (!name) {
|
|
|
|
pr_warning("failed to get section name from %s\n",
|
|
|
|
obj->path);
|
2015-11-06 21:49:37 +08:00
|
|
|
err = -LIBBPF_ERRNO__FORMAT;
|
2015-07-01 10:13:56 +08:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
data = elf_getdata(scn, 0);
|
|
|
|
if (!data) {
|
|
|
|
pr_warning("failed to get section data from %s(%s)\n",
|
|
|
|
name, obj->path);
|
2015-11-06 21:49:37 +08:00
|
|
|
err = -LIBBPF_ERRNO__FORMAT;
|
2015-07-01 10:13:56 +08:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
pr_debug("section %s, size %ld, link %d, flags %lx, type=%d\n",
|
|
|
|
name, (unsigned long)data->d_size,
|
|
|
|
(int)sh.sh_link, (unsigned long)sh.sh_flags,
|
|
|
|
(int)sh.sh_type);
|
2015-07-01 10:13:57 +08:00
|
|
|
|
|
|
|
if (strcmp(name, "license") == 0)
|
|
|
|
err = bpf_object__init_license(obj,
|
|
|
|
data->d_buf,
|
|
|
|
data->d_size);
|
|
|
|
else if (strcmp(name, "version") == 0)
|
|
|
|
err = bpf_object__init_kversion(obj,
|
|
|
|
data->d_buf,
|
|
|
|
data->d_size);
|
2015-11-27 16:47:36 +08:00
|
|
|
else if (strcmp(name, "maps") == 0) {
|
2015-07-01 10:13:58 +08:00
|
|
|
err = bpf_object__init_maps(obj, data->d_buf,
|
|
|
|
data->d_size);
|
2015-11-27 16:47:36 +08:00
|
|
|
maps_shndx = idx;
|
|
|
|
} else if (sh.sh_type == SHT_SYMTAB) {
|
bpf tools: Collect symbol table from SHT_SYMTAB section
This patch collects symbols section. This section is useful when linking
BPF maps.
What 'bpf_map_xxx()' functions actually require are map's file
descriptors (and the internal verifier converts fds into pointers to
'struct bpf_map'), which we don't know when compiling. Therefore, we
should make compiler generate a 'ldr_64 r1, <imm>' instruction, and
fill the 'imm' field with the actual file descriptor when loading in
libbpf.
BPF programs should be written in this way:
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(unsigned long),
.value_size = sizeof(unsigned long),
.max_entries = 1000000,
};
SEC("my_func=sys_write")
int my_func(void *ctx)
{
...
bpf_map_update_elem(&my_map, &key, &value, BPF_ANY);
...
}
Compiler should convert '&my_map' into a 'ldr_64, r1, <imm>'
instruction, where imm should be the address of 'my_map'. According to
the address, libbpf knows which map it actually referenced, and then
fills the imm field with the 'fd' of that map created by it.
However, since we never really 'link' the object file, the imm field is
only a record in relocation section. Therefore libbpf should do the
relocation:
1. In relocation section (type == SHT_REL), positions of each such
'ldr_64' instruction are recorded with a reference of an entry in
symbol table (SHT_SYMTAB);
2. From records in symbol table we can find the indics of map
variables.
Libbpf first record SHT_SYMTAB and positions of each instruction which
required bu such operation. Then create file descriptor. Finally, after
map creation complete, replace the imm field.
This is the first patch of BPF map related stuff. It records SHT_SYMTAB
into object's efile field for further use.
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1435716878-189507-12-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-01 10:13:59 +08:00
|
|
|
if (obj->efile.symbols) {
|
|
|
|
pr_warning("bpf: multiple SYMTAB in %s\n",
|
|
|
|
obj->path);
|
2015-11-06 21:49:37 +08:00
|
|
|
err = -LIBBPF_ERRNO__FORMAT;
|
2015-12-08 10:25:30 +08:00
|
|
|
} else {
|
bpf tools: Collect symbol table from SHT_SYMTAB section
This patch collects symbols section. This section is useful when linking
BPF maps.
What 'bpf_map_xxx()' functions actually require are map's file
descriptors (and the internal verifier converts fds into pointers to
'struct bpf_map'), which we don't know when compiling. Therefore, we
should make compiler generate a 'ldr_64 r1, <imm>' instruction, and
fill the 'imm' field with the actual file descriptor when loading in
libbpf.
BPF programs should be written in this way:
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(unsigned long),
.value_size = sizeof(unsigned long),
.max_entries = 1000000,
};
SEC("my_func=sys_write")
int my_func(void *ctx)
{
...
bpf_map_update_elem(&my_map, &key, &value, BPF_ANY);
...
}
Compiler should convert '&my_map' into a 'ldr_64, r1, <imm>'
instruction, where imm should be the address of 'my_map'. According to
the address, libbpf knows which map it actually referenced, and then
fills the imm field with the 'fd' of that map created by it.
However, since we never really 'link' the object file, the imm field is
only a record in relocation section. Therefore libbpf should do the
relocation:
1. In relocation section (type == SHT_REL), positions of each such
'ldr_64' instruction are recorded with a reference of an entry in
symbol table (SHT_SYMTAB);
2. From records in symbol table we can find the indics of map
variables.
Libbpf first record SHT_SYMTAB and positions of each instruction which
required bu such operation. Then create file descriptor. Finally, after
map creation complete, replace the imm field.
This is the first patch of BPF map related stuff. It records SHT_SYMTAB
into object's efile field for further use.
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1435716878-189507-12-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-01 10:13:59 +08:00
|
|
|
obj->efile.symbols = data;
|
2015-12-08 10:25:30 +08:00
|
|
|
obj->efile.strtabidx = sh.sh_link;
|
|
|
|
}
|
2015-07-01 10:14:00 +08:00
|
|
|
} else if ((sh.sh_type == SHT_PROGBITS) &&
|
|
|
|
(sh.sh_flags & SHF_EXECINSTR) &&
|
|
|
|
(data->d_size > 0)) {
|
|
|
|
err = bpf_object__add_program(obj, data->d_buf,
|
|
|
|
data->d_size, name, idx);
|
|
|
|
if (err) {
|
2015-11-06 21:49:37 +08:00
|
|
|
char errmsg[STRERR_BUFSIZE];
|
|
|
|
|
2015-07-01 10:14:00 +08:00
|
|
|
strerror_r(-err, errmsg, sizeof(errmsg));
|
|
|
|
pr_warning("failed to alloc program %s (%s): %s",
|
|
|
|
name, obj->path, errmsg);
|
|
|
|
}
|
2015-07-01 10:14:01 +08:00
|
|
|
} else if (sh.sh_type == SHT_REL) {
|
|
|
|
void *reloc = obj->efile.reloc;
|
|
|
|
int nr_reloc = obj->efile.nr_reloc + 1;
|
|
|
|
|
|
|
|
reloc = realloc(reloc,
|
|
|
|
sizeof(*obj->efile.reloc) * nr_reloc);
|
|
|
|
if (!reloc) {
|
|
|
|
pr_warning("realloc failed\n");
|
|
|
|
err = -ENOMEM;
|
|
|
|
} else {
|
|
|
|
int n = nr_reloc - 1;
|
|
|
|
|
|
|
|
obj->efile.reloc = reloc;
|
|
|
|
obj->efile.nr_reloc = nr_reloc;
|
|
|
|
|
|
|
|
obj->efile.reloc[n].shdr = sh;
|
|
|
|
obj->efile.reloc[n].data = data;
|
|
|
|
}
|
bpf tools: Collect symbol table from SHT_SYMTAB section
This patch collects symbols section. This section is useful when linking
BPF maps.
What 'bpf_map_xxx()' functions actually require are map's file
descriptors (and the internal verifier converts fds into pointers to
'struct bpf_map'), which we don't know when compiling. Therefore, we
should make compiler generate a 'ldr_64 r1, <imm>' instruction, and
fill the 'imm' field with the actual file descriptor when loading in
libbpf.
BPF programs should be written in this way:
struct bpf_map_def SEC("maps") my_map = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(unsigned long),
.value_size = sizeof(unsigned long),
.max_entries = 1000000,
};
SEC("my_func=sys_write")
int my_func(void *ctx)
{
...
bpf_map_update_elem(&my_map, &key, &value, BPF_ANY);
...
}
Compiler should convert '&my_map' into a 'ldr_64, r1, <imm>'
instruction, where imm should be the address of 'my_map'. According to
the address, libbpf knows which map it actually referenced, and then
fills the imm field with the 'fd' of that map created by it.
However, since we never really 'link' the object file, the imm field is
only a record in relocation section. Therefore libbpf should do the
relocation:
1. In relocation section (type == SHT_REL), positions of each such
'ldr_64' instruction are recorded with a reference of an entry in
symbol table (SHT_SYMTAB);
2. From records in symbol table we can find the indics of map
variables.
Libbpf first record SHT_SYMTAB and positions of each instruction which
required bu such operation. Then create file descriptor. Finally, after
map creation complete, replace the imm field.
This is the first patch of BPF map related stuff. It records SHT_SYMTAB
into object's efile field for further use.
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kaixu Xia <xiakaixu@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1435716878-189507-12-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-01 10:13:59 +08:00
|
|
|
}
|
2015-07-01 10:13:57 +08:00
|
|
|
if (err)
|
|
|
|
goto out;
|
2015-07-01 10:13:56 +08:00
|
|
|
}
|
2015-11-27 16:47:36 +08:00
|
|
|
|
2015-12-08 10:25:30 +08:00
|
|
|
if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
|
|
|
|
pr_warning("Corrupted ELF file: index of strtab invalid\n");
|
|
|
|
return LIBBPF_ERRNO__FORMAT;
|
|
|
|
}
|
2015-11-27 16:47:36 +08:00
|
|
|
if (maps_shndx >= 0)
|
2015-12-08 10:25:29 +08:00
|
|
|
err = bpf_object__init_maps_name(obj, maps_shndx);
|
2015-07-01 10:13:56 +08:00
|
|
|
out:
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2015-07-01 10:14:02 +08:00
|
|
|
static struct bpf_program *
|
|
|
|
bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
|
|
|
|
{
|
|
|
|
struct bpf_program *prog;
|
|
|
|
size_t i;
|
|
|
|
|
|
|
|
for (i = 0; i < obj->nr_programs; i++) {
|
|
|
|
prog = &obj->programs[i];
|
|
|
|
if (prog->idx == idx)
|
|
|
|
return prog;
|
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
bpf_program__collect_reloc(struct bpf_program *prog,
|
|
|
|
size_t nr_maps, GElf_Shdr *shdr,
|
|
|
|
Elf_Data *data, Elf_Data *symbols)
|
|
|
|
{
|
|
|
|
int i, nrels;
|
|
|
|
|
|
|
|
pr_debug("collecting relocating info for: '%s'\n",
|
|
|
|
prog->section_name);
|
|
|
|
nrels = shdr->sh_size / shdr->sh_entsize;
|
|
|
|
|
|
|
|
prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels);
|
|
|
|
if (!prog->reloc_desc) {
|
|
|
|
pr_warning("failed to alloc memory in relocation\n");
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
prog->nr_reloc = nrels;
|
|
|
|
|
|
|
|
for (i = 0; i < nrels; i++) {
|
|
|
|
GElf_Sym sym;
|
|
|
|
GElf_Rel rel;
|
|
|
|
unsigned int insn_idx;
|
|
|
|
struct bpf_insn *insns = prog->insns;
|
|
|
|
size_t map_idx;
|
|
|
|
|
|
|
|
if (!gelf_getrel(data, i, &rel)) {
|
|
|
|
pr_warning("relocation: failed to get %d reloc\n", i);
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__FORMAT;
|
2015-07-01 10:14:02 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
insn_idx = rel.r_offset / sizeof(struct bpf_insn);
|
|
|
|
pr_debug("relocation: insn_idx=%u\n", insn_idx);
|
|
|
|
|
|
|
|
if (!gelf_getsym(symbols,
|
|
|
|
GELF_R_SYM(rel.r_info),
|
|
|
|
&sym)) {
|
|
|
|
pr_warning("relocation: symbol %"PRIx64" not found\n",
|
|
|
|
GELF_R_SYM(rel.r_info));
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__FORMAT;
|
2015-07-01 10:14:02 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) {
|
|
|
|
pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n",
|
|
|
|
insn_idx, insns[insn_idx].code);
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__RELOC;
|
2015-07-01 10:14:02 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
map_idx = sym.st_value / sizeof(struct bpf_map_def);
|
|
|
|
if (map_idx >= nr_maps) {
|
|
|
|
pr_warning("bpf relocation: map_idx %d large than %d\n",
|
|
|
|
(int)map_idx, (int)nr_maps - 1);
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__RELOC;
|
2015-07-01 10:14:02 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
prog->reloc_desc[i].insn_idx = insn_idx;
|
|
|
|
prog->reloc_desc[i].map_idx = map_idx;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-07-01 10:14:04 +08:00
|
|
|
static int
|
|
|
|
bpf_object__create_maps(struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
unsigned int i;
|
|
|
|
|
2015-11-27 16:47:35 +08:00
|
|
|
for (i = 0; i < obj->nr_maps; i++) {
|
|
|
|
struct bpf_map_def *def = &obj->maps[i].def;
|
|
|
|
int *pfd = &obj->maps[i].fd;
|
2015-07-01 10:14:04 +08:00
|
|
|
|
2015-11-27 16:47:35 +08:00
|
|
|
*pfd = bpf_create_map(def->type,
|
|
|
|
def->key_size,
|
|
|
|
def->value_size,
|
|
|
|
def->max_entries);
|
2015-07-01 10:14:04 +08:00
|
|
|
if (*pfd < 0) {
|
|
|
|
size_t j;
|
|
|
|
int err = *pfd;
|
|
|
|
|
|
|
|
pr_warning("failed to create map: %s\n",
|
|
|
|
strerror(errno));
|
|
|
|
for (j = 0; j < i; j++)
|
2015-11-27 16:47:35 +08:00
|
|
|
zclose(obj->maps[j].fd);
|
2015-07-01 10:14:04 +08:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
pr_debug("create map: fd=%d\n", *pfd);
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-07-01 10:14:05 +08:00
|
|
|
static int
|
2015-11-27 16:47:35 +08:00
|
|
|
bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
|
2015-07-01 10:14:05 +08:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (!prog || !prog->reloc_desc)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
for (i = 0; i < prog->nr_reloc; i++) {
|
|
|
|
int insn_idx, map_idx;
|
|
|
|
struct bpf_insn *insns = prog->insns;
|
|
|
|
|
|
|
|
insn_idx = prog->reloc_desc[i].insn_idx;
|
|
|
|
map_idx = prog->reloc_desc[i].map_idx;
|
|
|
|
|
|
|
|
if (insn_idx >= (int)prog->insns_cnt) {
|
|
|
|
pr_warning("relocation out of range: '%s'\n",
|
|
|
|
prog->section_name);
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__RELOC;
|
2015-07-01 10:14:05 +08:00
|
|
|
}
|
|
|
|
insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
|
2015-11-27 16:47:35 +08:00
|
|
|
insns[insn_idx].imm = obj->maps[map_idx].fd;
|
2015-07-01 10:14:05 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
zfree(&prog->reloc_desc);
|
|
|
|
prog->nr_reloc = 0;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int
|
|
|
|
bpf_object__relocate(struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
struct bpf_program *prog;
|
|
|
|
size_t i;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
for (i = 0; i < obj->nr_programs; i++) {
|
|
|
|
prog = &obj->programs[i];
|
|
|
|
|
2015-11-27 16:47:35 +08:00
|
|
|
err = bpf_program__relocate(prog, obj);
|
2015-07-01 10:14:05 +08:00
|
|
|
if (err) {
|
|
|
|
pr_warning("failed to relocate '%s'\n",
|
|
|
|
prog->section_name);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-07-01 10:14:02 +08:00
|
|
|
static int bpf_object__collect_reloc(struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
int i, err;
|
|
|
|
|
|
|
|
if (!obj_elf_valid(obj)) {
|
|
|
|
pr_warning("Internal error: elf object is closed\n");
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__INTERNAL;
|
2015-07-01 10:14:02 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; i < obj->efile.nr_reloc; i++) {
|
|
|
|
GElf_Shdr *shdr = &obj->efile.reloc[i].shdr;
|
|
|
|
Elf_Data *data = obj->efile.reloc[i].data;
|
|
|
|
int idx = shdr->sh_info;
|
|
|
|
struct bpf_program *prog;
|
2015-11-27 16:47:35 +08:00
|
|
|
size_t nr_maps = obj->nr_maps;
|
2015-07-01 10:14:02 +08:00
|
|
|
|
|
|
|
if (shdr->sh_type != SHT_REL) {
|
|
|
|
pr_warning("internal error at %d\n", __LINE__);
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__INTERNAL;
|
2015-07-01 10:14:02 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
prog = bpf_object__find_prog_by_idx(obj, idx);
|
|
|
|
if (!prog) {
|
|
|
|
pr_warning("relocation failed: no %d section\n",
|
|
|
|
idx);
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__RELOC;
|
2015-07-01 10:14:02 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
err = bpf_program__collect_reloc(prog, nr_maps,
|
|
|
|
shdr, data,
|
|
|
|
obj->efile.symbols);
|
|
|
|
if (err)
|
2015-11-06 21:49:37 +08:00
|
|
|
return err;
|
2015-07-01 10:14:02 +08:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-07-01 10:14:07 +08:00
|
|
|
static int
|
|
|
|
load_program(struct bpf_insn *insns, int insns_cnt,
|
|
|
|
char *license, u32 kern_version, int *pfd)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
char *log_buf;
|
|
|
|
|
|
|
|
if (!insns || !insns_cnt)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
log_buf = malloc(BPF_LOG_BUF_SIZE);
|
|
|
|
if (!log_buf)
|
|
|
|
pr_warning("Alloc log buffer for bpf loader error, continue without log\n");
|
|
|
|
|
|
|
|
ret = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
|
|
|
|
insns_cnt, license, kern_version,
|
|
|
|
log_buf, BPF_LOG_BUF_SIZE);
|
|
|
|
|
|
|
|
if (ret >= 0) {
|
|
|
|
*pfd = ret;
|
|
|
|
ret = 0;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2015-11-06 21:49:37 +08:00
|
|
|
ret = -LIBBPF_ERRNO__LOAD;
|
2015-07-01 10:14:07 +08:00
|
|
|
pr_warning("load bpf program failed: %s\n", strerror(errno));
|
|
|
|
|
2015-11-06 21:49:37 +08:00
|
|
|
if (log_buf && log_buf[0] != '\0') {
|
|
|
|
ret = -LIBBPF_ERRNO__VERIFY;
|
2015-07-01 10:14:07 +08:00
|
|
|
pr_warning("-- BEGIN DUMP LOG ---\n");
|
|
|
|
pr_warning("\n%s\n", log_buf);
|
|
|
|
pr_warning("-- END LOG --\n");
|
2015-11-06 21:49:37 +08:00
|
|
|
} else {
|
|
|
|
if (insns_cnt >= BPF_MAXINSNS) {
|
|
|
|
pr_warning("Program too large (%d insns), at most %d insns\n",
|
|
|
|
insns_cnt, BPF_MAXINSNS);
|
|
|
|
ret = -LIBBPF_ERRNO__PROG2BIG;
|
|
|
|
} else if (log_buf) {
|
|
|
|
pr_warning("log buffer is empty\n");
|
|
|
|
ret = -LIBBPF_ERRNO__KVER;
|
|
|
|
}
|
2015-07-01 10:14:07 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
out:
|
|
|
|
free(log_buf);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
bpf_program__load(struct bpf_program *prog,
|
|
|
|
char *license, u32 kern_version)
|
|
|
|
{
|
2015-11-16 20:10:09 +08:00
|
|
|
int err = 0, fd, i;
|
2015-07-01 10:14:07 +08:00
|
|
|
|
2015-11-16 20:10:09 +08:00
|
|
|
if (prog->instances.nr < 0 || !prog->instances.fds) {
|
|
|
|
if (prog->preprocessor) {
|
|
|
|
pr_warning("Internal error: can't load program '%s'\n",
|
|
|
|
prog->section_name);
|
|
|
|
return -LIBBPF_ERRNO__INTERNAL;
|
|
|
|
}
|
2015-07-01 10:14:07 +08:00
|
|
|
|
2015-11-16 20:10:09 +08:00
|
|
|
prog->instances.fds = malloc(sizeof(int));
|
|
|
|
if (!prog->instances.fds) {
|
|
|
|
pr_warning("Not enough memory for BPF fds\n");
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
prog->instances.nr = 1;
|
|
|
|
prog->instances.fds[0] = -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!prog->preprocessor) {
|
|
|
|
if (prog->instances.nr != 1) {
|
|
|
|
pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
|
|
|
|
prog->section_name, prog->instances.nr);
|
|
|
|
}
|
|
|
|
err = load_program(prog->insns, prog->insns_cnt,
|
|
|
|
license, kern_version, &fd);
|
|
|
|
if (!err)
|
|
|
|
prog->instances.fds[0] = fd;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; i < prog->instances.nr; i++) {
|
|
|
|
struct bpf_prog_prep_result result;
|
|
|
|
bpf_program_prep_t preprocessor = prog->preprocessor;
|
|
|
|
|
|
|
|
bzero(&result, sizeof(result));
|
|
|
|
err = preprocessor(prog, i, prog->insns,
|
|
|
|
prog->insns_cnt, &result);
|
|
|
|
if (err) {
|
|
|
|
pr_warning("Preprocessing the %dth instance of program '%s' failed\n",
|
|
|
|
i, prog->section_name);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!result.new_insn_ptr || !result.new_insn_cnt) {
|
|
|
|
pr_debug("Skip loading the %dth instance of program '%s'\n",
|
|
|
|
i, prog->section_name);
|
|
|
|
prog->instances.fds[i] = -1;
|
|
|
|
if (result.pfd)
|
|
|
|
*result.pfd = -1;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
err = load_program(result.new_insn_ptr,
|
|
|
|
result.new_insn_cnt,
|
|
|
|
license, kern_version, &fd);
|
|
|
|
|
|
|
|
if (err) {
|
|
|
|
pr_warning("Loading the %dth instance of program '%s' failed\n",
|
|
|
|
i, prog->section_name);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (result.pfd)
|
|
|
|
*result.pfd = fd;
|
|
|
|
prog->instances.fds[i] = fd;
|
|
|
|
}
|
|
|
|
out:
|
2015-07-01 10:14:07 +08:00
|
|
|
if (err)
|
|
|
|
pr_warning("failed to load program '%s'\n",
|
|
|
|
prog->section_name);
|
|
|
|
zfree(&prog->insns);
|
|
|
|
prog->insns_cnt = 0;
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
bpf_object__load_progs(struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
size_t i;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
for (i = 0; i < obj->nr_programs; i++) {
|
|
|
|
err = bpf_program__load(&obj->programs[i],
|
|
|
|
obj->license,
|
|
|
|
obj->kern_version);
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-07-01 10:13:57 +08:00
|
|
|
static int bpf_object__validate(struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
if (obj->kern_version == 0) {
|
|
|
|
pr_warning("%s doesn't provide kernel version\n",
|
|
|
|
obj->path);
|
2015-11-06 21:49:37 +08:00
|
|
|
return -LIBBPF_ERRNO__KVERSION;
|
2015-07-01 10:13:57 +08:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-07-01 10:13:53 +08:00
|
|
|
static struct bpf_object *
|
2015-07-01 10:13:54 +08:00
|
|
|
__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz)
|
2015-07-01 10:13:53 +08:00
|
|
|
{
|
|
|
|
struct bpf_object *obj;
|
2015-11-06 21:49:37 +08:00
|
|
|
int err;
|
2015-07-01 10:13:53 +08:00
|
|
|
|
|
|
|
if (elf_version(EV_CURRENT) == EV_NONE) {
|
|
|
|
pr_warning("failed to init libelf for %s\n", path);
|
2015-11-06 21:49:37 +08:00
|
|
|
return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
|
2015-07-01 10:13:53 +08:00
|
|
|
}
|
|
|
|
|
2015-07-01 10:13:54 +08:00
|
|
|
obj = bpf_object__new(path, obj_buf, obj_buf_sz);
|
2015-11-06 21:49:37 +08:00
|
|
|
if (IS_ERR(obj))
|
|
|
|
return obj;
|
2015-07-01 10:13:53 +08:00
|
|
|
|
2015-11-06 21:49:37 +08:00
|
|
|
CHECK_ERR(bpf_object__elf_init(obj), err, out);
|
|
|
|
CHECK_ERR(bpf_object__check_endianness(obj), err, out);
|
|
|
|
CHECK_ERR(bpf_object__elf_collect(obj), err, out);
|
|
|
|
CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
|
|
|
|
CHECK_ERR(bpf_object__validate(obj), err, out);
|
2015-07-01 10:13:53 +08:00
|
|
|
|
|
|
|
bpf_object__elf_finish(obj);
|
|
|
|
return obj;
|
|
|
|
out:
|
|
|
|
bpf_object__close(obj);
|
2015-11-06 21:49:37 +08:00
|
|
|
return ERR_PTR(err);
|
2015-07-01 10:13:53 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
struct bpf_object *bpf_object__open(const char *path)
|
|
|
|
{
|
|
|
|
/* param validation */
|
|
|
|
if (!path)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
pr_debug("loading %s\n", path);
|
|
|
|
|
2015-07-01 10:13:54 +08:00
|
|
|
return __bpf_object__open(path, NULL, 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
struct bpf_object *bpf_object__open_buffer(void *obj_buf,
|
2015-08-27 10:30:55 +08:00
|
|
|
size_t obj_buf_sz,
|
|
|
|
const char *name)
|
2015-07-01 10:13:54 +08:00
|
|
|
{
|
2015-08-27 10:30:55 +08:00
|
|
|
char tmp_name[64];
|
|
|
|
|
2015-07-01 10:13:54 +08:00
|
|
|
/* param validation */
|
|
|
|
if (!obj_buf || obj_buf_sz <= 0)
|
|
|
|
return NULL;
|
|
|
|
|
2015-08-27 10:30:55 +08:00
|
|
|
if (!name) {
|
|
|
|
snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
|
|
|
|
(unsigned long)obj_buf,
|
|
|
|
(unsigned long)obj_buf_sz);
|
|
|
|
tmp_name[sizeof(tmp_name) - 1] = '\0';
|
|
|
|
name = tmp_name;
|
|
|
|
}
|
|
|
|
pr_debug("loading object '%s' from buffer\n",
|
|
|
|
name);
|
2015-07-01 10:13:54 +08:00
|
|
|
|
2015-08-27 10:30:55 +08:00
|
|
|
return __bpf_object__open(name, obj_buf, obj_buf_sz);
|
2015-07-01 10:13:53 +08:00
|
|
|
}
|
|
|
|
|
2015-07-01 10:14:04 +08:00
|
|
|
int bpf_object__unload(struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
size_t i;
|
|
|
|
|
|
|
|
if (!obj)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2015-11-27 16:47:35 +08:00
|
|
|
for (i = 0; i < obj->nr_maps; i++)
|
|
|
|
zclose(obj->maps[i].fd);
|
2015-07-01 10:14:04 +08:00
|
|
|
|
2015-07-01 10:14:07 +08:00
|
|
|
for (i = 0; i < obj->nr_programs; i++)
|
|
|
|
bpf_program__unload(&obj->programs[i]);
|
|
|
|
|
2015-07-01 10:14:04 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int bpf_object__load(struct bpf_object *obj)
|
|
|
|
{
|
2015-11-06 21:49:37 +08:00
|
|
|
int err;
|
|
|
|
|
2015-07-01 10:14:04 +08:00
|
|
|
if (!obj)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (obj->loaded) {
|
|
|
|
pr_warning("object should not be loaded twice\n");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
obj->loaded = true;
|
2015-11-06 21:49:37 +08:00
|
|
|
|
|
|
|
CHECK_ERR(bpf_object__create_maps(obj), err, out);
|
|
|
|
CHECK_ERR(bpf_object__relocate(obj), err, out);
|
|
|
|
CHECK_ERR(bpf_object__load_progs(obj), err, out);
|
2015-07-01 10:14:04 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
out:
|
|
|
|
bpf_object__unload(obj);
|
|
|
|
pr_warning("failed to load object '%s'\n", obj->path);
|
2015-11-06 21:49:37 +08:00
|
|
|
return err;
|
2015-07-01 10:14:04 +08:00
|
|
|
}
|
|
|
|
|
2015-07-01 10:13:53 +08:00
|
|
|
void bpf_object__close(struct bpf_object *obj)
|
|
|
|
{
|
2015-07-01 10:14:00 +08:00
|
|
|
size_t i;
|
|
|
|
|
2015-07-01 10:13:53 +08:00
|
|
|
if (!obj)
|
|
|
|
return;
|
|
|
|
|
|
|
|
bpf_object__elf_finish(obj);
|
2015-07-01 10:14:04 +08:00
|
|
|
bpf_object__unload(obj);
|
2015-07-01 10:13:53 +08:00
|
|
|
|
2015-11-27 16:47:35 +08:00
|
|
|
for (i = 0; i < obj->nr_maps; i++) {
|
2015-11-27 16:47:36 +08:00
|
|
|
zfree(&obj->maps[i].name);
|
2015-11-27 16:47:35 +08:00
|
|
|
if (obj->maps[i].clear_priv)
|
|
|
|
obj->maps[i].clear_priv(&obj->maps[i],
|
|
|
|
obj->maps[i].priv);
|
|
|
|
obj->maps[i].priv = NULL;
|
|
|
|
obj->maps[i].clear_priv = NULL;
|
|
|
|
}
|
|
|
|
zfree(&obj->maps);
|
|
|
|
obj->nr_maps = 0;
|
2015-07-01 10:14:00 +08:00
|
|
|
|
|
|
|
if (obj->programs && obj->nr_programs) {
|
|
|
|
for (i = 0; i < obj->nr_programs; i++)
|
|
|
|
bpf_program__exit(&obj->programs[i]);
|
|
|
|
}
|
|
|
|
zfree(&obj->programs);
|
|
|
|
|
2015-07-01 10:14:10 +08:00
|
|
|
list_del(&obj->list);
|
2015-07-01 10:13:53 +08:00
|
|
|
free(obj);
|
|
|
|
}
|
2015-07-01 10:14:08 +08:00
|
|
|
|
2015-07-01 10:14:10 +08:00
|
|
|
struct bpf_object *
|
|
|
|
bpf_object__next(struct bpf_object *prev)
|
|
|
|
{
|
|
|
|
struct bpf_object *next;
|
|
|
|
|
|
|
|
if (!prev)
|
|
|
|
next = list_first_entry(&bpf_objects_list,
|
|
|
|
struct bpf_object,
|
|
|
|
list);
|
|
|
|
else
|
|
|
|
next = list_next_entry(prev, list);
|
|
|
|
|
|
|
|
/* Empty list is noticed here so don't need checking on entry. */
|
|
|
|
if (&next->list == &bpf_objects_list)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
return next;
|
|
|
|
}
|
|
|
|
|
2015-08-27 10:30:55 +08:00
|
|
|
const char *
|
|
|
|
bpf_object__get_name(struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
if (!obj)
|
2015-11-06 21:49:37 +08:00
|
|
|
return ERR_PTR(-EINVAL);
|
2015-08-27 10:30:55 +08:00
|
|
|
return obj->path;
|
|
|
|
}
|
|
|
|
|
2015-11-06 21:49:38 +08:00
|
|
|
unsigned int
|
|
|
|
bpf_object__get_kversion(struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
if (!obj)
|
|
|
|
return 0;
|
|
|
|
return obj->kern_version;
|
|
|
|
}
|
|
|
|
|
2015-07-01 10:14:08 +08:00
|
|
|
struct bpf_program *
|
|
|
|
bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
size_t idx;
|
|
|
|
|
|
|
|
if (!obj->programs)
|
|
|
|
return NULL;
|
|
|
|
/* First handler */
|
|
|
|
if (prev == NULL)
|
|
|
|
return &obj->programs[0];
|
|
|
|
|
|
|
|
if (prev->obj != obj) {
|
|
|
|
pr_warning("error: program handler doesn't match object\n");
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
idx = (prev - obj->programs) + 1;
|
|
|
|
if (idx >= obj->nr_programs)
|
|
|
|
return NULL;
|
|
|
|
return &obj->programs[idx];
|
|
|
|
}
|
|
|
|
|
|
|
|
int bpf_program__set_private(struct bpf_program *prog,
|
|
|
|
void *priv,
|
|
|
|
bpf_program_clear_priv_t clear_priv)
|
|
|
|
{
|
|
|
|
if (prog->priv && prog->clear_priv)
|
|
|
|
prog->clear_priv(prog, prog->priv);
|
|
|
|
|
|
|
|
prog->priv = priv;
|
|
|
|
prog->clear_priv = clear_priv;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int bpf_program__get_private(struct bpf_program *prog, void **ppriv)
|
|
|
|
{
|
|
|
|
*ppriv = prog->priv;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-11-03 19:21:05 +08:00
|
|
|
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
|
2015-07-01 10:14:08 +08:00
|
|
|
{
|
|
|
|
const char *title;
|
|
|
|
|
|
|
|
title = prog->section_name;
|
2015-11-03 19:21:05 +08:00
|
|
|
if (needs_copy) {
|
2015-07-01 10:14:08 +08:00
|
|
|
title = strdup(title);
|
|
|
|
if (!title) {
|
|
|
|
pr_warning("failed to strdup program title\n");
|
2015-11-06 21:49:37 +08:00
|
|
|
return ERR_PTR(-ENOMEM);
|
2015-07-01 10:14:08 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return title;
|
|
|
|
}
|
|
|
|
|
|
|
|
int bpf_program__fd(struct bpf_program *prog)
|
|
|
|
{
|
2015-11-16 20:10:09 +08:00
|
|
|
return bpf_program__nth_fd(prog, 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
|
|
|
|
bpf_program_prep_t prep)
|
|
|
|
{
|
|
|
|
int *instances_fds;
|
|
|
|
|
|
|
|
if (nr_instances <= 0 || !prep)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (prog->instances.nr > 0 || prog->instances.fds) {
|
|
|
|
pr_warning("Can't set pre-processor after loading\n");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
instances_fds = malloc(sizeof(int) * nr_instances);
|
|
|
|
if (!instances_fds) {
|
|
|
|
pr_warning("alloc memory failed for fds\n");
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* fill all fd with -1 */
|
|
|
|
memset(instances_fds, -1, sizeof(int) * nr_instances);
|
|
|
|
|
|
|
|
prog->instances.nr = nr_instances;
|
|
|
|
prog->instances.fds = instances_fds;
|
|
|
|
prog->preprocessor = prep;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int bpf_program__nth_fd(struct bpf_program *prog, int n)
|
|
|
|
{
|
|
|
|
int fd;
|
|
|
|
|
|
|
|
if (n >= prog->instances.nr || n < 0) {
|
|
|
|
pr_warning("Can't get the %dth fd from program %s: only %d instances\n",
|
|
|
|
n, prog->section_name, prog->instances.nr);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
fd = prog->instances.fds[n];
|
|
|
|
if (fd < 0) {
|
|
|
|
pr_warning("%dth instance of program '%s' is invalid\n",
|
|
|
|
n, prog->section_name);
|
|
|
|
return -ENOENT;
|
|
|
|
}
|
|
|
|
|
|
|
|
return fd;
|
2015-07-01 10:14:08 +08:00
|
|
|
}
|
2015-11-27 16:47:35 +08:00
|
|
|
|
|
|
|
int bpf_map__get_fd(struct bpf_map *map)
|
|
|
|
{
|
|
|
|
if (!map)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
return map->fd;
|
|
|
|
}
|
|
|
|
|
|
|
|
int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef)
|
|
|
|
{
|
|
|
|
if (!map || !pdef)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
*pdef = map->def;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-11-27 16:47:36 +08:00
|
|
|
const char *bpf_map__get_name(struct bpf_map *map)
|
|
|
|
{
|
|
|
|
if (!map)
|
|
|
|
return NULL;
|
|
|
|
return map->name;
|
|
|
|
}
|
|
|
|
|
2015-11-27 16:47:35 +08:00
|
|
|
int bpf_map__set_private(struct bpf_map *map, void *priv,
|
|
|
|
bpf_map_clear_priv_t clear_priv)
|
|
|
|
{
|
|
|
|
if (!map)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (map->priv) {
|
|
|
|
if (map->clear_priv)
|
|
|
|
map->clear_priv(map, map->priv);
|
|
|
|
}
|
|
|
|
|
|
|
|
map->priv = priv;
|
|
|
|
map->clear_priv = clear_priv;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int bpf_map__get_private(struct bpf_map *map, void **ppriv)
|
|
|
|
{
|
|
|
|
if (!map)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (ppriv)
|
|
|
|
*ppriv = map->priv;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct bpf_map *
|
|
|
|
bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
|
|
|
|
{
|
|
|
|
size_t idx;
|
|
|
|
struct bpf_map *s, *e;
|
|
|
|
|
|
|
|
if (!obj || !obj->maps)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
s = obj->maps;
|
|
|
|
e = obj->maps + obj->nr_maps;
|
|
|
|
|
|
|
|
if (prev == NULL)
|
|
|
|
return s;
|
|
|
|
|
|
|
|
if ((prev < s) || (prev >= e)) {
|
|
|
|
pr_warning("error in %s: map handler doesn't belong to object\n",
|
|
|
|
__func__);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
idx = (prev - obj->maps) + 1;
|
|
|
|
if (idx >= obj->nr_maps)
|
|
|
|
return NULL;
|
|
|
|
return &obj->maps[idx];
|
|
|
|
}
|
2015-11-27 16:47:36 +08:00
|
|
|
|
|
|
|
struct bpf_map *
|
|
|
|
bpf_object__get_map_by_name(struct bpf_object *obj, const char *name)
|
|
|
|
{
|
|
|
|
struct bpf_map *pos;
|
|
|
|
|
|
|
|
bpf_map__for_each(pos, obj) {
|
2015-12-08 10:25:29 +08:00
|
|
|
if (pos->name && !strcmp(pos->name, name))
|
2015-11-27 16:47:36 +08:00
|
|
|
return pos;
|
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
}
|