linux-stable/tools/lib/bpf/libbpf_internal.h

425 lines
13 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
/*
* Internal libbpf helpers.
*
* Copyright (c) 2019 Facebook
*/
#ifndef __LIBBPF_LIBBPF_INTERNAL_H
#define __LIBBPF_LIBBPF_INTERNAL_H
#include <stdlib.h>
#include <limits.h>
/* make sure libbpf doesn't use kernel-only integer typedefs */
#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
/* prevent accidental re-addition of reallocarray() */
#pragma GCC poison reallocarray
#include "libbpf.h"
#include "btf.h"
libbpf: Add BPF static linker APIs Introduce BPF static linker APIs to libbpf. BPF static linker allows to perform static linking of multiple BPF object files into a single combined resulting object file, preserving all the BPF programs, maps, global variables, etc. Data sections (.bss, .data, .rodata, .maps, maps, etc) with the same name are concatenated together. Similarly, code sections are also concatenated. All the symbols and ELF relocations are also concatenated in their respective ELF sections and are adjusted accordingly to the new object file layout. Static variables and functions are handled correctly as well, adjusting BPF instructions offsets to reflect new variable/function offset within the combined ELF section. Such relocations are referencing STT_SECTION symbols and that stays intact. Data sections in different files can have different alignment requirements, so that is taken care of as well, adjusting sizes and offsets as necessary to satisfy both old and new alignment requirements. DWARF data sections are stripped out, currently. As well as LLLVM_ADDRSIG section, which is ignored by libbpf in bpf_object__open() anyways. So, in a way, BPF static linker is an analogue to `llvm-strip -g`, which is a pretty nice property, especially if resulting .o file is then used to generate BPF skeleton. Original string sections are ignored and instead we construct our own set of unique strings using libbpf-internal `struct strset` API. To reduce the size of the patch, all the .BTF and .BTF.ext processing was moved into a separate patch. The high-level API consists of just 4 functions: - bpf_linker__new() creates an instance of BPF static linker. It accepts output filename and (currently empty) options struct; - bpf_linker__add_file() takes input filename and appends it to the already processed ELF data; it can be called multiple times, one for each BPF ELF object file that needs to be linked in; - bpf_linker__finalize() needs to be called to dump final ELF contents into the output file, specified when bpf_linker was created; after bpf_linker__finalize() is called, no more bpf_linker__add_file() and bpf_linker__finalize() calls are allowed, they will return error; - regardless of whether bpf_linker__finalize() was called or not, bpf_linker__free() will free up all the used resources. Currently, BPF static linker doesn't resolve cross-object file references (extern variables and/or functions). This will be added in the follow up patch set. Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20210318194036.3521577-7-andrii@kernel.org
2021-03-18 19:40:30 +00:00
#ifndef EM_BPF
#define EM_BPF 247
#endif
#ifndef R_BPF_64_64
#define R_BPF_64_64 1
#endif
#ifndef R_BPF_64_32
#define R_BPF_64_32 10
#endif
#ifndef SHT_LLVM_ADDRSIG
#define SHT_LLVM_ADDRSIG 0x6FFF4C03
#endif
/* if libelf is old and doesn't support mmap(), fall back to read() */
#ifndef ELF_C_READ_MMAP
#define ELF_C_READ_MMAP ELF_C_READ
#endif
#define BTF_INFO_ENC(kind, kind_flag, vlen) \
((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
#define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type)
#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \
((encoding) << 24 | (bits_offset) << 16 | (nr_bits))
#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \
BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \
BTF_INT_ENC(encoding, bits_offset, bits)
#define BTF_MEMBER_ENC(name, type, bits_offset) (name), (type), (bits_offset)
#define BTF_PARAM_ENC(name, type) (name), (type)
#define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size)
#define BTF_TYPE_FLOAT_ENC(name, sz) \
BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz)
#ifndef likely
#define likely(x) __builtin_expect(!!(x), 1)
#endif
#ifndef unlikely
#define unlikely(x) __builtin_expect(!!(x), 0)
#endif
#ifndef min
# define min(x, y) ((x) < (y) ? (x) : (y))
#endif
#ifndef max
# define max(x, y) ((x) < (y) ? (y) : (x))
#endif
#ifndef offsetofend
# define offsetofend(TYPE, FIELD) \
(offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD))
#endif
libbpf: handle symbol versioning properly for libbpf.a bcc uses libbpf repo as a submodule. It brings in libbpf source code and builds everything together to produce shared libraries. With latest libbpf, I got the following errors: /bin/ld: libbcc_bpf.so.0.10.0: version node not found for symbol xsk_umem__create@LIBBPF_0.0.2 /bin/ld: failed to set dynamic section sizes: Bad value collect2: error: ld returned 1 exit status make[2]: *** [src/cc/libbcc_bpf.so.0.10.0] Error 1 In xsk.c, we have asm(".symver xsk_umem__create_v0_0_2, xsk_umem__create@LIBBPF_0.0.2"); asm(".symver xsk_umem__create_v0_0_4, xsk_umem__create@@LIBBPF_0.0.4"); The linker thinks the built is for LIBBPF but cannot find proper version LIBBPF_0.0.2/4, so emit errors. I also confirmed that using libbpf.a to produce a shared library also has issues: -bash-4.4$ cat t.c extern void *xsk_umem__create; void * test() { return xsk_umem__create; } -bash-4.4$ gcc -c -fPIC t.c -bash-4.4$ gcc -shared t.o libbpf.a -o t.so /bin/ld: t.so: version node not found for symbol xsk_umem__create@LIBBPF_0.0.2 /bin/ld: failed to set dynamic section sizes: Bad value collect2: error: ld returned 1 exit status -bash-4.4$ Symbol versioning does happens in commonly used libraries, e.g., elfutils and glibc. For static libraries, for a versioned symbol, the old definitions will be ignored, and the symbol will be an alias to the latest definition. For example, glibc sched_setaffinity is versioned. -bash-4.4$ readelf -s /usr/lib64/libc.so.6 | grep sched_setaffinity 756: 000000000013d3d0 13 FUNC GLOBAL DEFAULT 13 sched_setaffinity@GLIBC_2.3.3 757: 00000000000e2e70 455 FUNC GLOBAL DEFAULT 13 sched_setaffinity@@GLIBC_2.3.4 1800: 0000000000000000 0 FILE LOCAL DEFAULT ABS sched_setaffinity.c 4228: 00000000000e2e70 455 FUNC LOCAL DEFAULT 13 __sched_setaffinity_new 4648: 000000000013d3d0 13 FUNC LOCAL DEFAULT 13 __sched_setaffinity_old 7338: 000000000013d3d0 13 FUNC GLOBAL DEFAULT 13 sched_setaffinity@GLIBC_2 7380: 00000000000e2e70 455 FUNC GLOBAL DEFAULT 13 sched_setaffinity@@GLIBC_ -bash-4.4$ For static library, the definition of sched_setaffinity aliases to the new definition. -bash-4.4$ readelf -s /usr/lib64/libc.a | grep sched_setaffinity File: /usr/lib64/libc.a(sched_setaffinity.o) 8: 0000000000000000 455 FUNC GLOBAL DEFAULT 1 __sched_setaffinity_new 12: 0000000000000000 455 FUNC WEAK DEFAULT 1 sched_setaffinity For both elfutils and glibc, additional macros are used to control different handling of symbol versioning w.r.t static and shared libraries. For elfutils, the macro is SYMBOL_VERSIONING (https://sourceware.org/git/?p=elfutils.git;a=blob;f=lib/eu-config.h). For glibc, the macro is SHARED (https://sourceware.org/git/?p=glibc.git;a=blob;f=include/shlib-compat.h;hb=refs/heads/master) This patch used SHARED as the macro name. After this patch, the libbpf.a has -bash-4.4$ readelf -s libbpf.a | grep xsk_umem__create 372: 0000000000017145 1190 FUNC GLOBAL DEFAULT 1 xsk_umem__create_v0_0_4 405: 0000000000017145 1190 FUNC GLOBAL DEFAULT 1 xsk_umem__create 499: 00000000000175eb 103 FUNC GLOBAL DEFAULT 1 xsk_umem__create_v0_0_2 -bash-4.4$ No versioned symbols for xsk_umem__create. The libbpf.a can be used to build a shared library succesfully. -bash-4.4$ cat t.c extern void *xsk_umem__create; void * test() { return xsk_umem__create; } -bash-4.4$ gcc -c -fPIC t.c -bash-4.4$ gcc -shared t.o libbpf.a -o t.so -bash-4.4$ Fixes: 10d30e301732 ("libbpf: add flags to umem config") Cc: Kevin Laatz <kevin.laatz@intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andrii Nakryiko <andriin@fb.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-09-30 21:02:03 +00:00
/* Symbol versioning is different between static and shared library.
* Properly versioned symbols are needed for shared library, but
* only the symbol of the new version is needed for static library.
*/
#ifdef SHARED
# define COMPAT_VERSION(internal_name, api_name, version) \
asm(".symver " #internal_name "," #api_name "@" #version);
# define DEFAULT_VERSION(internal_name, api_name, version) \
asm(".symver " #internal_name "," #api_name "@@" #version);
#else
# define COMPAT_VERSION(internal_name, api_name, version)
# define DEFAULT_VERSION(internal_name, api_name, version) \
extern typeof(internal_name) api_name \
__attribute__((alias(#internal_name)));
#endif
extern void libbpf_print(enum libbpf_print_level level,
const char *format, ...)
__attribute__((format(printf, 2, 3)));
#define __pr(level, fmt, ...) \
do { \
libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__); \
} while (0)
#define pr_warn(fmt, ...) __pr(LIBBPF_WARN, fmt, ##__VA_ARGS__)
#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__)
#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__)
#ifndef __has_builtin
#define __has_builtin(x) 0
#endif
/*
* Re-implement glibc's reallocarray() for libbpf internal-only use.
* reallocarray(), unfortunately, is not available in all versions of glibc,
* so requires extra feature detection and using reallocarray() stub from
* <tools/libc_compat.h> and COMPAT_NEED_REALLOCARRAY. All this complicates
* build of libbpf unnecessarily and is just a maintenance burden. Instead,
* it's trivial to implement libbpf-specific internal version and use it
* throughout libbpf.
*/
static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size)
{
size_t total;
#if __has_builtin(__builtin_mul_overflow)
if (unlikely(__builtin_mul_overflow(nmemb, size, &total)))
return NULL;
#else
if (size == 0 || nmemb > ULONG_MAX / size)
return NULL;
total = nmemb * size;
#endif
return realloc(ptr, total);
}
struct btf;
struct btf_type;
struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id);
static inline __u32 btf_type_info(int kind, int vlen, int kflag)
{
return (kflag << 31) | (kind << 24) | vlen;
}
enum map_def_parts {
MAP_DEF_MAP_TYPE = 0x001,
MAP_DEF_KEY_TYPE = 0x002,
MAP_DEF_KEY_SIZE = 0x004,
MAP_DEF_VALUE_TYPE = 0x008,
MAP_DEF_VALUE_SIZE = 0x010,
MAP_DEF_MAX_ENTRIES = 0x020,
MAP_DEF_MAP_FLAGS = 0x040,
MAP_DEF_NUMA_NODE = 0x080,
MAP_DEF_PINNING = 0x100,
MAP_DEF_INNER_MAP = 0x200,
MAP_DEF_ALL = 0x3ff, /* combination of all above */
};
struct btf_map_def {
enum map_def_parts parts;
__u32 map_type;
__u32 key_type_id;
__u32 key_size;
__u32 value_type_id;
__u32 value_size;
__u32 max_entries;
__u32 map_flags;
__u32 numa_node;
__u32 pinning;
};
int parse_btf_map_def(const char *map_name, struct btf *btf,
const struct btf_type *def_t, bool strict,
struct btf_map_def *map_def, struct btf_map_def *inner_def);
void *libbpf_add_mem(void **data, size_t *cap_cnt, size_t elem_sz,
size_t cur_cnt, size_t max_cnt, size_t add_cnt);
int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_cnt);
static inline bool libbpf_validate_opts(const char *opts,
size_t opts_sz, size_t user_sz,
const char *type_name)
{
if (user_sz < sizeof(size_t)) {
pr_warn("%s size (%zu) is too small\n", type_name, user_sz);
return false;
}
if (user_sz > opts_sz) {
size_t i;
for (i = opts_sz; i < user_sz; i++) {
if (opts[i]) {
pr_warn("%s has non-zero extra bytes\n",
type_name);
return false;
}
}
}
return true;
}
#define OPTS_VALID(opts, type) \
(!(opts) || libbpf_validate_opts((const char *)opts, \
offsetofend(struct type, \
type##__last_field), \
(opts)->sz, #type))
#define OPTS_HAS(opts, field) \
((opts) && opts->sz >= offsetofend(typeof(*(opts)), field))
#define OPTS_GET(opts, field, fallback_value) \
(OPTS_HAS(opts, field) ? (opts)->field : fallback_value)
#define OPTS_SET(opts, field, value) \
do { \
if (OPTS_HAS(opts, field)) \
(opts)->field = value; \
} while (0)
int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz);
int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz);
int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
const char *str_sec, size_t str_len);
struct bpf_prog_load_params {
enum bpf_prog_type prog_type;
enum bpf_attach_type expected_attach_type;
const char *name;
const struct bpf_insn *insns;
size_t insn_cnt;
const char *license;
__u32 kern_version;
__u32 attach_prog_fd;
__u32 attach_btf_obj_fd;
__u32 attach_btf_id;
__u32 prog_ifindex;
__u32 prog_btf_fd;
__u32 prog_flags;
__u32 func_info_rec_size;
const void *func_info;
__u32 func_info_cnt;
__u32 line_info_rec_size;
const void *line_info;
__u32 line_info_cnt;
__u32 log_level;
char *log_buf;
size_t log_buf_sz;
};
int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr);
int bpf_object__section_size(const struct bpf_object *obj, const char *name,
__u32 *size);
int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
__u32 *off);
struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
struct btf_ext_info {
/*
* info points to the individual info section (e.g. func_info and
* line_info) from the .BTF.ext. It does not include the __u32 rec_size.
*/
void *info;
__u32 rec_size;
__u32 len;
};
#define for_each_btf_ext_sec(seg, sec) \
for (sec = (seg)->info; \
(void *)sec < (seg)->info + (seg)->len; \
sec = (void *)sec + sizeof(struct btf_ext_info_sec) + \
(seg)->rec_size * sec->num_info)
#define for_each_btf_ext_rec(seg, sec, i, rec) \
for (i = 0, rec = (void *)&(sec)->data; \
i < (sec)->num_info; \
i++, rec = (void *)rec + (seg)->rec_size)
/*
* The .BTF.ext ELF section layout defined as
* struct btf_ext_header
* func_info subsection
*
* The func_info subsection layout:
* record size for struct bpf_func_info in the func_info subsection
* struct btf_sec_func_info for section #1
* a list of bpf_func_info records for section #1
* where struct bpf_func_info mimics one in include/uapi/linux/bpf.h
* but may not be identical
* struct btf_sec_func_info for section #2
* a list of bpf_func_info records for section #2
* ......
*
* Note that the bpf_func_info record size in .BTF.ext may not
* be the same as the one defined in include/uapi/linux/bpf.h.
* The loader should ensure that record_size meets minimum
* requirement and pass the record as is to the kernel. The
* kernel will handle the func_info properly based on its contents.
*/
struct btf_ext_header {
__u16 magic;
__u8 version;
__u8 flags;
__u32 hdr_len;
/* All offsets are in bytes relative to the end of this header */
__u32 func_info_off;
__u32 func_info_len;
__u32 line_info_off;
__u32 line_info_len;
/* optional part of .BTF.ext header */
__u32 core_relo_off;
__u32 core_relo_len;
};
struct btf_ext {
union {
struct btf_ext_header *hdr;
void *data;
};
struct btf_ext_info func_info;
struct btf_ext_info line_info;
struct btf_ext_info core_relo_info;
__u32 data_size;
};
struct btf_ext_info_sec {
__u32 sec_name_off;
__u32 num_info;
/* Followed by num_info * record_size number of bytes */
bpf, libbpf: Replace zero-length array with flexible-array The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertently introduced[3] to the codebase from now on. Also, notice that, dynamic memory allocations won't be affected by this change: "Flexible array members have incomplete type, and so the sizeof operator may not be applied. As a quirk of the original implementation of zero-length arrays, sizeof evaluates to zero."[1] sizeof(flexible-array-member) triggers a warning because flexible array members have incomplete type[1]. There are some instances of code in which the sizeof operator is being incorrectly/erroneously applied to zero-length arrays and the result is zero. Such instances may be hiding some bugs. So, this work (flexible-array member conversions) will also help to get completely rid of those sorts of issues. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200507185057.GA13981@embeddedor
2020-05-07 18:50:57 +00:00
__u8 data[];
};
/* The minimum bpf_func_info checked by the loader */
struct bpf_func_info_min {
__u32 insn_off;
__u32 type_id;
};
/* The minimum bpf_line_info checked by the loader */
struct bpf_line_info_min {
__u32 insn_off;
__u32 file_name_off;
__u32 line_off;
__u32 line_col;
};
/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value
* has to be adjusted by relocations.
*/
enum bpf_core_relo_kind {
BPF_FIELD_BYTE_OFFSET = 0, /* field byte offset */
BPF_FIELD_BYTE_SIZE = 1, /* field size in bytes */
BPF_FIELD_EXISTS = 2, /* field existence in target kernel */
BPF_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */
BPF_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */
BPF_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */
2020-08-19 19:45:15 +00:00
BPF_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */
BPF_TYPE_ID_TARGET = 7, /* type ID in target kernel */
BPF_TYPE_EXISTS = 8, /* type existence in target kernel */
BPF_TYPE_SIZE = 9, /* type size in bytes */
BPF_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */
BPF_ENUMVAL_VALUE = 11, /* enum value integer value */
};
/* The minimum bpf_core_relo checked by the loader
*
* CO-RE relocation captures the following data:
* - insn_off - instruction offset (in bytes) within a BPF program that needs
* its insn->imm field to be relocated with actual field info;
* - type_id - BTF type ID of the "root" (containing) entity of a relocatable
* type or field;
* - access_str_off - offset into corresponding .BTF string section. String
* interpretation depends on specific relocation kind:
* - for field-based relocations, string encodes an accessed field using
* a sequence of field and array indices, separated by colon (:). It's
* conceptually very close to LLVM's getelementptr ([0]) instruction's
* arguments for identifying offset to a field.
* - for type-based relocations, strings is expected to be just "0";
* - for enum value-based relocations, string contains an index of enum
* value within its enum type;
*
* Example to provide a better feel.
*
* struct sample {
* int a;
* struct {
* int b[10];
* };
* };
*
* struct sample *s = ...;
* int x = &s->a; // encoded as "0:0" (a is field #0)
* int y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1,
* // b is field #0 inside anon struct, accessing elem #5)
* int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
*
* type_id for all relocs in this example will capture BTF type id of
* `struct sample`.
*
* Such relocation is emitted when using __builtin_preserve_access_index()
* Clang built-in, passing expression that captures field address, e.g.:
*
* bpf_probe_read(&dst, sizeof(dst),
* __builtin_preserve_access_index(&src->a.b.c));
*
* In this case Clang will emit field relocation recording necessary data to
* be able to find offset of embedded `a.b.c` field within `src` struct.
*
* [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
*/
struct bpf_core_relo {
__u32 insn_off;
__u32 type_id;
__u32 access_str_off;
enum bpf_core_relo_kind kind;
};
typedef int (*type_id_visit_fn)(__u32 *type_id, void *ctx);
typedef int (*str_off_visit_fn)(__u32 *str_off, void *ctx);
int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx);
int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx);
int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx);
int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx);
#endif /* __LIBBPF_LIBBPF_INTERNAL_H */