tools/lib/bpf/libbpf.c

// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)

/*
 * 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.
 * Copyright (C) 2017 Nicira, Inc.
 * Copyright (C) 2019 Isovalent, Inc.
 */

#ifndef _GNU_SOURCE
#define _GNU_SOURCE
#endif
#include <stdlib.h>
#include <stdio.h>
#include <stdarg.h>
#include <libgen.h>
#include <inttypes.h>
#include <string.h>
#include <unistd.h>
#include <endian.h>
#include <fcntl.h>
#include <errno.h>
#include <asm/unistd.h>
#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/filter.h>
#include <linux/list.h>
#include <linux/limits.h>
#include <linux/perf_event.h>
#include <linux/ring_buffer.h>
#include <sys/epoll.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
#include <sys/utsname.h>
#include <tools/libc_compat.h>
#include <libelf.h>
#include <gelf.h>

#include "libbpf.h"
#include "bpf.h"
#include "btf.h"
#include "str_error.h"
#include "libbpf_internal.h"
#include "hashmap.h"

#ifndef EM_BPF
#define EM_BPF 247
#endif

#ifndef BPF_FS_MAGIC
#define BPF_FS_MAGIC		0xcafe4a11
#endif

/* vsprintf() in __base_pr() uses nonliteral format string. It may break
 * compilation if user enables corresponding warning. Disable it explicitly.
 */
#pragma GCC diagnostic ignored "-Wformat-nonliteral"

#define __printf(a, b)	__attribute__((format(printf, a, b)))

static int __base_pr(enum libbpf_print_level level, const char *format,
		     va_list args)
{
	if (level == LIBBPF_DEBUG)
		return 0;

	return vfprintf(stderr, format, args);
}

static libbpf_print_fn_t __libbpf_pr = __base_pr;

libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn)
{
	libbpf_print_fn_t old_print_fn = __libbpf_pr;

	__libbpf_pr = fn;
	return old_print_fn;
}

__printf(2, 3)
void libbpf_print(enum libbpf_print_level level, const char *format, ...)
{
	va_list args;

	if (!__libbpf_pr)
		return;

	va_start(args, format);
	__libbpf_pr(level, format, args);
	va_end(args);
}

#define STRERR_BUFSIZE  128

#define CHECK_ERR(action, err, out) do {	\
	err = action;			\
	if (err)			\
		goto out;		\
} while(0)


/* 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

static inline __u64 ptr_to_u64(const void *ptr)
{
	return (__u64) (unsigned long) ptr;
}

struct bpf_capabilities {
	/* v4.14: kernel support for program & map names. */
	__u32 name:1;
	/* v5.2: kernel support for global data sections. */
	__u32 global_data:1;
	/* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */
	__u32 btf_func:1;
	/* BTF_KIND_VAR and BTF_KIND_DATASEC support */
	__u32 btf_datasec:1;
};

/*
 * 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 *name;
	int prog_ifindex;
	char *section_name;
	/* section_name with / replaced by _; makes recursive pinning
	 * in bpf_object__pin_programs easier
	 */
	char *pin_name;
	struct bpf_insn *insns;
	size_t insns_cnt, main_prog_cnt;
	enum bpf_prog_type type;

	struct reloc_desc {
		enum {
			RELO_LD64,
			RELO_CALL,
			RELO_DATA,
		} type;
		int insn_idx;
		union {
			int map_idx;
			int text_off;
		};
	} *reloc_desc;
	int nr_reloc;
	int log_level;

	struct {
		int nr;
		int *fds;
	} instances;
	bpf_program_prep_t preprocessor;

	struct bpf_object *obj;
	void *priv;
	bpf_program_clear_priv_t clear_priv;

	enum bpf_attach_type expected_attach_type;
	void *func_info;
	__u32 func_info_rec_size;
	__u32 func_info_cnt;

	struct bpf_capabilities *caps;

	void *line_info;
	__u32 line_info_rec_size;
	__u32 line_info_cnt;
	__u32 prog_flags;
};

enum libbpf_map_type {
	LIBBPF_MAP_UNSPEC,
	LIBBPF_MAP_DATA,
	LIBBPF_MAP_BSS,
	LIBBPF_MAP_RODATA,
};

static const char * const libbpf_type_to_btf_name[] = {
	[LIBBPF_MAP_DATA]	= ".data",
	[LIBBPF_MAP_BSS]	= ".bss",
	[LIBBPF_MAP_RODATA]	= ".rodata",
};

struct bpf_map {
	int fd;
	char *name;
	int sec_idx;
	size_t sec_offset;
	int map_ifindex;
	int inner_map_fd;
	struct bpf_map_def def;
	__u32 btf_key_type_id;
	__u32 btf_value_type_id;
	void *priv;
	bpf_map_clear_priv_t clear_priv;
	enum libbpf_map_type libbpf_type;
};

struct bpf_secdata {
	void *rodata;
	void *data;
};

static LIST_HEAD(bpf_objects_list);

struct bpf_object {
	char name[BPF_OBJ_NAME_LEN];
	char license[64];
	__u32 kern_version;

	struct bpf_program *programs;
	size_t nr_programs;
	struct bpf_map *maps;
	size_t nr_maps;
	size_t maps_cap;
	struct bpf_secdata sections;

	bool loaded;
	bool has_pseudo_calls;

	/*
	 * Information when doing elf related work. Only valid if fd
	 * is valid.
	 */
	struct {
		int fd;
		void *obj_buf;
		size_t obj_buf_sz;
		Elf *elf;
		GElf_Ehdr ehdr;
		Elf_Data *symbols;
		Elf_Data *data;
		Elf_Data *rodata;
		Elf_Data *bss;
		size_t strtabidx;
		struct {
			GElf_Shdr shdr;
			Elf_Data *data;
		} *reloc;
		int nr_reloc;
		int maps_shndx;
		int btf_maps_shndx;
		int text_shndx;
		int data_shndx;
		int rodata_shndx;
		int bss_shndx;
	} efile;
	/*
	 * 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;

	struct btf *btf;
	struct btf_ext *btf_ext;

	void *priv;
	bpf_object_clear_priv_t clear_priv;

	struct bpf_capabilities caps;

	char path[];
};
#define obj_elf_valid(o)	((o)->efile.elf)

void bpf_program__unload(struct bpf_program *prog)
{
	int i;

	if (!prog)
		return;

	/*
	 * 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);

	zfree(&prog->func_info);
	zfree(&prog->line_info);
}

static void bpf_program__exit(struct bpf_program *prog)
{
	if (!prog)
		return;

	if (prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

	prog->priv = NULL;
	prog->clear_priv = NULL;

	bpf_program__unload(prog);
	zfree(&prog->name);
	zfree(&prog->section_name);
	zfree(&prog->pin_name);
	zfree(&prog->insns);
	zfree(&prog->reloc_desc);

	prog->nr_reloc = 0;
	prog->insns_cnt = 0;
	prog->idx = -1;
}

static char *__bpf_program__pin_name(struct bpf_program *prog)
{
	char *name, *p;

	name = p = strdup(prog->section_name);
	while ((p = strchr(p, '/')))
		*p = '_';

	return name;
}

static int
bpf_program__init(void *data, size_t size, char *section_name, int idx,
		  struct bpf_program *prog)
{
	const size_t bpf_insn_sz = sizeof(struct bpf_insn);

	if (size == 0 || size % bpf_insn_sz) {
		pr_warning("corrupted section '%s', size: %zu\n",
			   section_name, size);
		return -EINVAL;
	}

	memset(prog, 0, sizeof(*prog));

	prog->section_name = strdup(section_name);
	if (!prog->section_name) {
		pr_warning("failed to alloc name for prog under section(%d) %s\n",
			   idx, section_name);
		goto errout;
	}

	prog->pin_name = __bpf_program__pin_name(prog);
	if (!prog->pin_name) {
		pr_warning("failed to alloc pin name for prog under section(%d) %s\n",
			   idx, section_name);
		goto errout;
	}

	prog->insns = malloc(size);
	if (!prog->insns) {
		pr_warning("failed to alloc insns for prog under section %s\n",
			   section_name);
		goto errout;
	}
	prog->insns_cnt = size / bpf_insn_sz;
	memcpy(prog->insns, data, size);
	prog->idx = idx;
	prog->instances.fds = NULL;
	prog->instances.nr = -1;
	prog->type = BPF_PROG_TYPE_UNSPEC;

	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 *section_name, int idx)
{
	struct bpf_program prog, *progs;
	int nr_progs, err;

	err = bpf_program__init(data, size, section_name, idx, &prog);
	if (err)
		return err;

	prog.caps = &obj->caps;
	progs = obj->programs;
	nr_progs = obj->nr_programs;

	progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
	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 under section '%s'\n",
			   section_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;
	prog.obj = obj;
	progs[nr_progs] = prog;
	return 0;
}

static int
bpf_object__init_prog_names(struct bpf_object *obj)
{
	Elf_Data *symbols = obj->efile.symbols;
	struct bpf_program *prog;
	size_t pi, si;

	for (pi = 0; pi < obj->nr_programs; pi++) {
		const char *name = NULL;

		prog = &obj->programs[pi];

		for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name;
		     si++) {
			GElf_Sym sym;

			if (!gelf_getsym(symbols, si, &sym))
				continue;
			if (sym.st_shndx != prog->idx)
				continue;
			if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL)
				continue;

			name = elf_strptr(obj->efile.elf,
					  obj->efile.strtabidx,
					  sym.st_name);
			if (!name) {
				pr_warning("failed to get sym name string for prog %s\n",
					   prog->section_name);
				return -LIBBPF_ERRNO__LIBELF;
			}
		}

		if (!name && prog->idx == obj->efile.text_shndx)
			name = ".text";

		if (!name) {
			pr_warning("failed to find sym for prog %s\n",
				   prog->section_name);
			return -EINVAL;
		}

		prog->name = strdup(name);
		if (!prog->name) {
			pr_warning("failed to allocate memory for prog sym %s\n",
				   name);
			return -ENOMEM;
		}
	}

	return 0;
}

static struct bpf_object *bpf_object__new(const char *path,
					  void *obj_buf,
					  size_t obj_buf_sz)
{
	struct bpf_object *obj;
	char *end;

	obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
	if (!obj) {
		pr_warning("alloc memory failed for %s\n", path);
		return ERR_PTR(-ENOMEM);
	}

	strcpy(obj->path, path);
	/* Using basename() GNU version which doesn't modify arg. */
	strncpy(obj->name, basename((void *)path), sizeof(obj->name) - 1);
	end = strchr(obj->name, '.');
	if (end)
		*end = 0;

	obj->efile.fd = -1;
	/*
	 * Caller of this function should also call
	 * 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;
	obj->efile.maps_shndx = -1;
	obj->efile.btf_maps_shndx = -1;
	obj->efile.data_shndx = -1;
	obj->efile.rodata_shndx = -1;
	obj->efile.bss_shndx = -1;

	obj->loaded = false;

	INIT_LIST_HEAD(&obj->list);
	list_add(&obj->list, &bpf_objects_list);
	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;
	}
	obj->efile.symbols = NULL;
	obj->efile.data = NULL;
	obj->efile.rodata = NULL;
	obj->efile.bss = NULL;

	zfree(&obj->efile.reloc);
	obj->efile.nr_reloc = 0;
	zclose(obj->efile.fd);
	obj->efile.obj_buf = NULL;
	obj->efile.obj_buf_sz = 0;
}

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");
		return -LIBBPF_ERRNO__LIBELF;
	}

	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) {
			char errmsg[STRERR_BUFSIZE], *cp;

			err = -errno;
			cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
			pr_warning("failed to open %s: %s\n", obj->path, cp);
			return err;
		}

		obj->efile.elf = elf_begin(obj->efile.fd,
					   LIBBPF_ELF_C_READ_MMAP, NULL);
	}

	if (!obj->efile.elf) {
		pr_warning("failed to open %s as ELF file\n", obj->path);
		err = -LIBBPF_ERRNO__LIBELF;
		goto errout;
	}

	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
		pr_warning("failed to get EHDR from %s\n", obj->path);
		err = -LIBBPF_ERRNO__FORMAT;
		goto errout;
	}
	ep = &obj->efile.ehdr;

	/* Old LLVM set e_machine to EM_NONE */
	if (ep->e_type != ET_REL ||
	    (ep->e_machine && ep->e_machine != EM_BPF)) {
		pr_warning("%s is not an eBPF object file\n", obj->path);
		err = -LIBBPF_ERRNO__FORMAT;
		goto errout;
	}

	return 0;
errout:
	bpf_object__elf_finish(obj);
	return err;
}

static int bpf_object__check_endianness(struct bpf_object *obj)
{
#if __BYTE_ORDER == __LITTLE_ENDIAN
	if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB)
		return 0;
#elif __BYTE_ORDER == __BIG_ENDIAN
	if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB)
		return 0;
#else
# error "Unrecognized __BYTE_ORDER__"
#endif
	pr_warning("endianness mismatch.\n");
	return -LIBBPF_ERRNO__ENDIAN;
}

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);
		return -LIBBPF_ERRNO__FORMAT;
	}
	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;
}

static int compare_bpf_map(const void *_a, const void *_b)
{
	const struct bpf_map *a = _a;
	const struct bpf_map *b = _b;

	if (a->sec_idx != b->sec_idx)
		return a->sec_idx - b->sec_idx;
	return a->sec_offset - b->sec_offset;
}

static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
{
	if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
	    type == BPF_MAP_TYPE_HASH_OF_MAPS)
		return true;
	return false;
}

static int bpf_object_search_section_size(const struct bpf_object *obj,
					  const char *name, size_t *d_size)
{
	const GElf_Ehdr *ep = &obj->efile.ehdr;
	Elf *elf = obj->efile.elf;
	Elf_Scn *scn = NULL;
	int idx = 0;

	while ((scn = elf_nextscn(elf, scn)) != NULL) {
		const char *sec_name;
		Elf_Data *data;
		GElf_Shdr sh;

		idx++;
		if (gelf_getshdr(scn, &sh) != &sh) {
			pr_warning("failed to get section(%d) header from %s\n",
				   idx, obj->path);
			return -EIO;
		}

		sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
		if (!sec_name) {
			pr_warning("failed to get section(%d) name from %s\n",
				   idx, obj->path);
			return -EIO;
		}

		if (strcmp(name, sec_name))
			continue;

		data = elf_getdata(scn, 0);
		if (!data) {
			pr_warning("failed to get section(%d) data from %s(%s)\n",
				   idx, name, obj->path);
			return -EIO;
		}

		*d_size = data->d_size;
		return 0;
	}

	return -ENOENT;
}

int bpf_object__section_size(const struct bpf_object *obj, const char *name,
			     __u32 *size)
{
	int ret = -ENOENT;
	size_t d_size;

	*size = 0;
	if (!name) {
		return -EINVAL;
	} else if (!strcmp(name, ".data")) {
		if (obj->efile.data)
			*size = obj->efile.data->d_size;
	} else if (!strcmp(name, ".bss")) {
		if (obj->efile.bss)
			*size = obj->efile.bss->d_size;
	} else if (!strcmp(name, ".rodata")) {
		if (obj->efile.rodata)
			*size = obj->efile.rodata->d_size;
	} else {
		ret = bpf_object_search_section_size(obj, name, &d_size);
		if (!ret)
			*size = d_size;
	}

	return *size ? 0 : ret;
}

int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
				__u32 *off)
{
	Elf_Data *symbols = obj->efile.symbols;
	const char *sname;
	size_t si;

	if (!name || !off)
		return -EINVAL;

	for (si = 0; si < symbols->d_size / sizeof(GElf_Sym); si++) {
		GElf_Sym sym;

		if (!gelf_getsym(symbols, si, &sym))
			continue;
		if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL ||
		    GELF_ST_TYPE(sym.st_info) != STT_OBJECT)
			continue;

		sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
				   sym.st_name);
		if (!sname) {
			pr_warning("failed to get sym name string for var %s\n",
				   name);
			return -EIO;
		}
		if (strcmp(name, sname) == 0) {
			*off = sym.st_value;
			return 0;
		}
	}

	return -ENOENT;
}

static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
{
	struct bpf_map *new_maps;
	size_t new_cap;
	int i;

	if (obj->nr_maps < obj->maps_cap)
		return &obj->maps[obj->nr_maps++];

	new_cap = max((size_t)4, obj->maps_cap * 3 / 2);
	new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps));
	if (!new_maps) {
		pr_warning("alloc maps for object failed\n");
		return ERR_PTR(-ENOMEM);
	}

	obj->maps_cap = new_cap;
	obj->maps = new_maps;

	/* zero out new maps */
	memset(obj->maps + obj->nr_maps, 0,
	       (obj->maps_cap - obj->nr_maps) * sizeof(*obj->maps));
	/*
	 * fill all fd with -1 so won't close incorrect fd (fd=0 is stdin)
	 * when failure (zclose won't close negative fd)).
	 */
	for (i = obj->nr_maps; i < obj->maps_cap; i++) {
		obj->maps[i].fd = -1;
		obj->maps[i].inner_map_fd = -1;
	}

	return &obj->maps[obj->nr_maps++];
}

static int
bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
			      int sec_idx, Elf_Data *data, void **data_buff)
{
	char map_name[BPF_OBJ_NAME_LEN];
	struct bpf_map_def *def;
	struct bpf_map *map;

	map = bpf_object__add_map(obj);
	if (IS_ERR(map))
		return PTR_ERR(map);

	map->libbpf_type = type;
	map->sec_idx = sec_idx;
	map->sec_offset = 0;
	snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name,
		 libbpf_type_to_btf_name[type]);
	map->name = strdup(map_name);
	if (!map->name) {
		pr_warning("failed to alloc map name\n");
		return -ENOMEM;
	}
	pr_debug("map '%s' (global data): at sec_idx %d, offset %zu.\n",
		 map_name, map->sec_idx, map->sec_offset);

	def = &map->def;
	def->type = BPF_MAP_TYPE_ARRAY;
	def->key_size = sizeof(int);
	def->value_size = data->d_size;
	def->max_entries = 1;
	def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0;
	if (data_buff) {
		*data_buff = malloc(data->d_size);
		if (!*data_buff) {
			zfree(&map->name);
			pr_warning("failed to alloc map content buffer\n");
			return -ENOMEM;
		}
		memcpy(*data_buff, data->d_buf, data->d_size);
	}

	pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name);
	return 0;
}

static int bpf_object__init_global_data_maps(struct bpf_object *obj)
{
	int err;

	if (!obj->caps.global_data)
		return 0;
	/*
	 * Populate obj->maps with libbpf internal maps.
	 */
	if (obj->efile.data_shndx >= 0) {
		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA,
						    obj->efile.data_shndx,
						    obj->efile.data,
						    &obj->sections.data);
		if (err)
			return err;
	}
	if (obj->efile.rodata_shndx >= 0) {
		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA,
						    obj->efile.rodata_shndx,
						    obj->efile.rodata,
						    &obj->sections.rodata);
		if (err)
			return err;
	}
	if (obj->efile.bss_shndx >= 0) {
		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS,
						    obj->efile.bss_shndx,
						    obj->efile.bss, NULL);
		if (err)
			return err;
	}
	return 0;
}

static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
{
	Elf_Data *symbols = obj->efile.symbols;
	int i, map_def_sz = 0, nr_maps = 0, nr_syms;
	Elf_Data *data = NULL;
	Elf_Scn *scn;

	if (obj->efile.maps_shndx < 0)
		return 0;

	if (!symbols)
		return -EINVAL;

	scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx);
	if (scn)
		data = elf_getdata(scn, NULL);
	if (!scn || !data) {
		pr_warning("failed to get Elf_Data from map section %d\n",
			   obj->efile.maps_shndx);
		return -EINVAL;
	}

	/*
	 * Count number of maps. Each map has a name.
	 * Array of maps is not supported: only the first element is
	 * considered.
	 *
	 * TODO: Detect array of map and report error.
	 */
	nr_syms = symbols->d_size / sizeof(GElf_Sym);
	for (i = 0; i < nr_syms; i++) {
		GElf_Sym sym;

		if (!gelf_getsym(symbols, i, &sym))
			continue;
		if (sym.st_shndx != obj->efile.maps_shndx)
			continue;
		nr_maps++;
	}
	/* Assume equally sized map definitions */
	pr_debug("maps in %s: %d maps in %zd bytes\n",
		 obj->path, nr_maps, data->d_size);

	map_def_sz = data->d_size / nr_maps;
	if (!data->d_size || (data->d_size % nr_maps) != 0) {
		pr_warning("unable to determine map definition size "
			   "section %s, %d maps in %zd bytes\n",
			   obj->path, nr_maps, data->d_size);
		return -EINVAL;
	}

	/* Fill obj->maps using data in "maps" section.  */
	for (i = 0; i < nr_syms; i++) {
		GElf_Sym sym;
		const char *map_name;
		struct bpf_map_def *def;
		struct bpf_map *map;

		if (!gelf_getsym(symbols, i, &sym))
			continue;
		if (sym.st_shndx != obj->efile.maps_shndx)
			continue;

		map = bpf_object__add_map(obj);
		if (IS_ERR(map))
			return PTR_ERR(map);

		map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
				      sym.st_name);
		if (!map_name) {
			pr_warning("failed to get map #%d name sym string for obj %s\n",
				   i, obj->path);
			return -LIBBPF_ERRNO__FORMAT;
		}

		map->libbpf_type = LIBBPF_MAP_UNSPEC;
		map->sec_idx = sym.st_shndx;
		map->sec_offset = sym.st_value;
		pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n",
			 map_name, map->sec_idx, map->sec_offset);
		if (sym.st_value + map_def_sz > data->d_size) {
			pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
				   obj->path, map_name);
			return -EINVAL;
		}

		map->name = strdup(map_name);
		if (!map->name) {
			pr_warning("failed to alloc map name\n");
			return -ENOMEM;
		}
		pr_debug("map %d is \"%s\"\n", i, map->name);
		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
		/*
		 * If the definition of the map in the object file fits in
		 * bpf_map_def, copy it.  Any extra fields in our version
		 * of bpf_map_def will default to zero as a result of the
		 * calloc above.
		 */
		if (map_def_sz <= sizeof(struct bpf_map_def)) {
			memcpy(&map->def, def, map_def_sz);
		} else {
			/*
			 * Here the map structure being read is bigger than what
			 * we expect, truncate if the excess bits are all zero.
			 * If they are not zero, reject this map as
			 * incompatible.
			 */
			char *b;
			for (b = ((char *)def) + sizeof(struct bpf_map_def);
			     b < ((char *)def) + map_def_sz; b++) {
				if (*b != 0) {
					pr_warning("maps section in %s: \"%s\" "
						   "has unrecognized, non-zero "
						   "options\n",
						   obj->path, map_name);
					if (strict)
						return -EINVAL;
				}
			}
			memcpy(&map->def, def, sizeof(struct bpf_map_def));
		}
	}
	return 0;
}

static const struct btf_type *
skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id)
{
	const struct btf_type *t = btf__type_by_id(btf, id);

	if (res_id)
		*res_id = id;

	while (btf_is_mod(t) || btf_is_typedef(t)) {
		if (res_id)
			*res_id = t->type;
		t = btf__type_by_id(btf, t->type);
	}

	return t;
}

/*
 * Fetch integer attribute of BTF map definition. Such attributes are
 * represented using a pointer to an array, in which dimensionality of array
 * encodes specified integer value. E.g., int (*type)[BPF_MAP_TYPE_ARRAY];
 * encodes `type => BPF_MAP_TYPE_ARRAY` key/value pair completely using BTF
 * type definition, while using only sizeof(void *) space in ELF data section.
 */
static bool get_map_field_int(const char *map_name, const struct btf *btf,
			      const struct btf_type *def,
			      const struct btf_member *m, __u32 *res) {
	const struct btf_type *t = skip_mods_and_typedefs(btf, m->type, NULL);
	const char *name = btf__name_by_offset(btf, m->name_off);
	const struct btf_array *arr_info;
	const struct btf_type *arr_t;

	if (!btf_is_ptr(t)) {
		pr_warning("map '%s': attr '%s': expected PTR, got %u.\n",
			   map_name, name, btf_kind(t));
		return false;
	}

	arr_t = btf__type_by_id(btf, t->type);
	if (!arr_t) {
		pr_warning("map '%s': attr '%s': type [%u] not found.\n",
			   map_name, name, t->type);
		return false;
	}
	if (!btf_is_array(arr_t)) {
		pr_warning("map '%s': attr '%s': expected ARRAY, got %u.\n",
			   map_name, name, btf_kind(arr_t));
		return false;
	}
	arr_info = btf_array(arr_t);
	*res = arr_info->nelems;
	return true;
}

static int bpf_object__init_user_btf_map(struct bpf_object *obj,
					 const struct btf_type *sec,
					 int var_idx, int sec_idx,
					 const Elf_Data *data, bool strict)
{
	const struct btf_type *var, *def, *t;
	const struct btf_var_secinfo *vi;
	const struct btf_var *var_extra;
	const struct btf_member *m;
	const char *map_name;
	struct bpf_map *map;
	int vlen, i;

	vi = btf_var_secinfos(sec) + var_idx;
	var = btf__type_by_id(obj->btf, vi->type);
	var_extra = btf_var(var);
	map_name = btf__name_by_offset(obj->btf, var->name_off);
	vlen = btf_vlen(var);

	if (map_name == NULL || map_name[0] == '\0') {
		pr_warning("map #%d: empty name.\n", var_idx);
		return -EINVAL;
	}
	if ((__u64)vi->offset + vi->size > data->d_size) {
		pr_warning("map '%s' BTF data is corrupted.\n", map_name);
		return -EINVAL;
	}
	if (!btf_is_var(var)) {
		pr_warning("map '%s': unexpected var kind %u.\n",
			   map_name, btf_kind(var));
		return -EINVAL;
	}
	if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED &&
	    var_extra->linkage != BTF_VAR_STATIC) {
		pr_warning("map '%s': unsupported var linkage %u.\n",
			   map_name, var_extra->linkage);
		return -EOPNOTSUPP;
	}

	def = skip_mods_and_typedefs(obj->btf, var->type, NULL);
	if (!btf_is_struct(def)) {
		pr_warning("map '%s': unexpected def kind %u.\n",
			   map_name, btf_kind(var));
		return -EINVAL;
	}
	if (def->size > vi->size) {
		pr_warning("map '%s': invalid def size.\n", map_name);
		return -EINVAL;
	}

	map = bpf_object__add_map(obj);
	if (IS_ERR(map))
		return PTR_ERR(map);
	map->name = strdup(map_name);
	if (!map->name) {
		pr_warning("map '%s': failed to alloc map name.\n", map_name);
		return -ENOMEM;
	}
	map->libbpf_type = LIBBPF_MAP_UNSPEC;
	map->def.type = BPF_MAP_TYPE_UNSPEC;
	map->sec_idx = sec_idx;
	map->sec_offset = vi->offset;
	pr_debug("map '%s': at sec_idx %d, offset %zu.\n",
		 map_name, map->sec_idx, map->sec_offset);

	vlen = btf_vlen(def);
	m = btf_members(def);
	for (i = 0; i < vlen; i++, m++) {
		const char *name = btf__name_by_offset(obj->btf, m->name_off);

		if (!name) {
			pr_warning("map '%s': invalid field #%d.\n",
				   map_name, i);
			return -EINVAL;
		}
		if (strcmp(name, "type") == 0) {
			if (!get_map_field_int(map_name, obj->btf, def, m,
					       &map->def.type))
				return -EINVAL;
			pr_debug("map '%s': found type = %u.\n",
				 map_name, map->def.type);
		} else if (strcmp(name, "max_entries") == 0) {
			if (!get_map_field_int(map_name, obj->btf, def, m,
					       &map->def.max_entries))
				return -EINVAL;
			pr_debug("map '%s': found max_entries = %u.\n",
				 map_name, map->def.max_entries);
		} else if (strcmp(name, "map_flags") == 0) {
			if (!get_map_field_int(map_name, obj->btf, def, m,
					       &map->def.map_flags))
				return -EINVAL;
			pr_debug("map '%s': found map_flags = %u.\n",
				 map_name, map->def.map_flags);
		} else if (strcmp(name, "key_size") == 0) {
			__u32 sz;

			if (!get_map_field_int(map_name, obj->btf, def, m,
					       &sz))
				return -EINVAL;
			pr_debug("map '%s': found key_size = %u.\n",
				 map_name, sz);
			if (map->def.key_size && map->def.key_size != sz) {
				pr_warning("map '%s': conflicting key size %u != %u.\n",
					   map_name, map->def.key_size, sz);
				return -EINVAL;
			}
			map->def.key_size = sz;
		} else if (strcmp(name, "key") == 0) {
			__s64 sz;

			t = btf__type_by_id(obj->btf, m->type);
			if (!t) {
				pr_warning("map '%s': key type [%d] not found.\n",
					   map_name, m->type);
				return -EINVAL;
			}
			if (!btf_is_ptr(t)) {
				pr_warning("map '%s': key spec is not PTR: %u.\n",
					   map_name, btf_kind(t));
				return -EINVAL;
			}
			sz = btf__resolve_size(obj->btf, t->type);
			if (sz < 0) {
				pr_warning("map '%s': can't determine key size for type [%u]: %lld.\n",
					   map_name, t->type, sz);
				return sz;
			}
			pr_debug("map '%s': found key [%u], sz = %lld.\n",
				 map_name, t->type, sz);
			if (map->def.key_size && map->def.key_size != sz) {
				pr_warning("map '%s': conflicting key size %u != %lld.\n",
					   map_name, map->def.key_size, sz);
				return -EINVAL;
			}
			map->def.key_size = sz;
			map->btf_key_type_id = t->type;
		} else if (strcmp(name, "value_size") == 0) {
			__u32 sz;

			if (!get_map_field_int(map_name, obj->btf, def, m,
					       &sz))
				return -EINVAL;
			pr_debug("map '%s': found value_size = %u.\n",
				 map_name, sz);
			if (map->def.value_size && map->def.value_size != sz) {
				pr_warning("map '%s': conflicting value size %u != %u.\n",
					   map_name, map->def.value_size, sz);
				return -EINVAL;
			}
			map->def.value_size = sz;
		} else if (strcmp(name, "value") == 0) {
			__s64 sz;

			t = btf__type_by_id(obj->btf, m->type);
			if (!t) {
				pr_warning("map '%s': value type [%d] not found.\n",
					   map_name, m->type);
				return -EINVAL;
			}
			if (!btf_is_ptr(t)) {
				pr_warning("map '%s': value spec is not PTR: %u.\n",
					   map_name, btf_kind(t));
				return -EINVAL;
			}
			sz = btf__resolve_size(obj->btf, t->type);
			if (sz < 0) {
				pr_warning("map '%s': can't determine value size for type [%u]: %lld.\n",
					   map_name, t->type, sz);
				return sz;
			}
			pr_debug("map '%s': found value [%u], sz = %lld.\n",
				 map_name, t->type, sz);
			if (map->def.value_size && map->def.value_size != sz) {
				pr_warning("map '%s': conflicting value size %u != %lld.\n",
					   map_name, map->def.value_size, sz);
				return -EINVAL;
			}
			map->def.value_size = sz;
			map->btf_value_type_id = t->type;
		} else {
			if (strict) {
				pr_warning("map '%s': unknown field '%s'.\n",
					   map_name, name);
				return -ENOTSUP;
			}
			pr_debug("map '%s': ignoring unknown field '%s'.\n",
				 map_name, name);
		}
	}

	if (map->def.type == BPF_MAP_TYPE_UNSPEC) {
		pr_warning("map '%s': map type isn't specified.\n", map_name);
		return -EINVAL;
	}

	return 0;
}

static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict)
{
	const struct btf_type *sec = NULL;
	int nr_types, i, vlen, err;
	const struct btf_type *t;
	const char *name;
	Elf_Data *data;
	Elf_Scn *scn;

	if (obj->efile.btf_maps_shndx < 0)
		return 0;

	scn = elf_getscn(obj->efile.elf, obj->efile.btf_maps_shndx);
	if (scn)
		data = elf_getdata(scn, NULL);
	if (!scn || !data) {
		pr_warning("failed to get Elf_Data from map section %d (%s)\n",
			   obj->efile.maps_shndx, MAPS_ELF_SEC);
		return -EINVAL;
	}

	nr_types = btf__get_nr_types(obj->btf);
	for (i = 1; i <= nr_types; i++) {
		t = btf__type_by_id(obj->btf, i);
		if (!btf_is_datasec(t))
			continue;
		name = btf__name_by_offset(obj->btf, t->name_off);
		if (strcmp(name, MAPS_ELF_SEC) == 0) {
			sec = t;
			break;
		}
	}

	if (!sec) {
		pr_warning("DATASEC '%s' not found.\n", MAPS_ELF_SEC);
		return -ENOENT;
	}

	vlen = btf_vlen(sec);
	for (i = 0; i < vlen; i++) {
		err = bpf_object__init_user_btf_map(obj, sec, i,
						    obj->efile.btf_maps_shndx,
						    data, strict);
		if (err)
			return err;
	}

	return 0;
}

static int bpf_object__init_maps(struct bpf_object *obj, int flags)
{
	bool strict = !(flags & MAPS_RELAX_COMPAT);
	int err;

	err = bpf_object__init_user_maps(obj, strict);
	if (err)
		return err;

	err = bpf_object__init_user_btf_maps(obj, strict);
	if (err)
		return err;

	err = bpf_object__init_global_data_maps(obj);
	if (err)
		return err;

	if (obj->nr_maps) {
		qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
		      compare_bpf_map);
	}
	return 0;
}

static bool section_have_execinstr(struct bpf_object *obj, int idx)
{
	Elf_Scn *scn;
	GElf_Shdr sh;

	scn = elf_getscn(obj->efile.elf, idx);
	if (!scn)
		return false;

	if (gelf_getshdr(scn, &sh) != &sh)
		return false;

	if (sh.sh_flags & SHF_EXECINSTR)
		return true;

	return false;
}

static void bpf_object__sanitize_btf(struct bpf_object *obj)
{
	bool has_datasec = obj->caps.btf_datasec;
	bool has_func = obj->caps.btf_func;
	struct btf *btf = obj->btf;
	struct btf_type *t;
	int i, j, vlen;

	if (!obj->btf || (has_func && has_datasec))
		return;

	for (i = 1; i <= btf__get_nr_types(btf); i++) {
		t = (struct btf_type *)btf__type_by_id(btf, i);

		if (!has_datasec && btf_is_var(t)) {
			/* replace VAR with INT */
			t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
			/*
			 * using size = 1 is the safest choice, 4 will be too
			 * big and cause kernel BTF validation failure if
			 * original variable took less than 4 bytes
			 */
			t->size = 1;
			*(int *)(t + 1) = BTF_INT_ENC(0, 0, 8);
		} else if (!has_datasec && btf_is_datasec(t)) {
			/* replace DATASEC with STRUCT */
			const struct btf_var_secinfo *v = btf_var_secinfos(t);
			struct btf_member *m = btf_members(t);
			struct btf_type *vt;
			char *name;

			name = (char *)btf__name_by_offset(btf, t->name_off);
			while (*name) {
				if (*name == '.')
					*name = '_';
				name++;
			}

			vlen = btf_vlen(t);
			t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, vlen);
			for (j = 0; j < vlen; j++, v++, m++) {
				/* order of field assignments is important */
				m->offset = v->offset * 8;
				m->type = v->type;
				/* preserve variable name as member name */
				vt = (void *)btf__type_by_id(btf, v->type);
				m->name_off = vt->name_off;
			}
		} else if (!has_func && btf_is_func_proto(t)) {
			/* replace FUNC_PROTO with ENUM */
			vlen = btf_vlen(t);
			t->info = BTF_INFO_ENC(BTF_KIND_ENUM, 0, vlen);
			t->size = sizeof(__u32); /* kernel enforced */
		} else if (!has_func && btf_is_func(t)) {
			/* replace FUNC with TYPEDEF */
			t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0);
		}
	}
}

static void bpf_object__sanitize_btf_ext(struct bpf_object *obj)
{
	if (!obj->btf_ext)
		return;

	if (!obj->caps.btf_func) {
		btf_ext__free(obj->btf_ext);
		obj->btf_ext = NULL;
	}
}

static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj)
{
	return obj->efile.btf_maps_shndx >= 0;
}

static int bpf_object__init_btf(struct bpf_object *obj,
				Elf_Data *btf_data,
				Elf_Data *btf_ext_data)
{
	bool btf_required = bpf_object__is_btf_mandatory(obj);
	int err = 0;

	if (btf_data) {
		obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
		if (IS_ERR(obj->btf)) {
			pr_warning("Error loading ELF section %s: %d.\n",
				   BTF_ELF_SEC, err);
			goto out;
		}
		err = btf__finalize_data(obj, obj->btf);
		if (err) {
			pr_warning("Error finalizing %s: %d.\n",
				   BTF_ELF_SEC, err);
			goto out;
		}
	}
	if (btf_ext_data) {
		if (!obj->btf) {
			pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n",
				 BTF_EXT_ELF_SEC, BTF_ELF_SEC);
			goto out;
		}
		obj->btf_ext = btf_ext__new(btf_ext_data->d_buf,
					    btf_ext_data->d_size);
		if (IS_ERR(obj->btf_ext)) {
			pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
				   BTF_EXT_ELF_SEC, PTR_ERR(obj->btf_ext));
			obj->btf_ext = NULL;
			goto out;
		}
	}
out:
	if (err || IS_ERR(obj->btf)) {
		if (btf_required)
			err = err ? : PTR_ERR(obj->btf);
		else
			err = 0;
		if (!IS_ERR_OR_NULL(obj->btf))
			btf__free(obj->btf);
		obj->btf = NULL;
	}
	if (btf_required && !obj->btf) {
		pr_warning("BTF is required, but is missing or corrupted.\n");
		return err == 0 ? -ENOENT : err;
	}
	return 0;
}

static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
{
	int err = 0;

	if (!obj->btf)
		return 0;

	bpf_object__sanitize_btf(obj);
	bpf_object__sanitize_btf_ext(obj);

	err = btf__load(obj->btf);
	if (err) {
		pr_warning("Error loading %s into kernel: %d.\n",
			   BTF_ELF_SEC, err);
		btf__free(obj->btf);
		obj->btf = NULL;
		/* btf_ext can't exist without btf, so free it as well */
		if (obj->btf_ext) {
			btf_ext__free(obj->btf_ext);
			obj->btf_ext = NULL;
		}

		if (bpf_object__is_btf_mandatory(obj))
			return err;
	}
	return 0;
}

static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
{
	Elf *elf = obj->efile.elf;
	GElf_Ehdr *ep = &obj->efile.ehdr;
	Elf_Data *btf_ext_data = NULL;
	Elf_Data *btf_data = NULL;
	Elf_Scn *scn = NULL;
	int idx = 0, err = 0;

	/* 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);
		return -LIBBPF_ERRNO__FORMAT;
	}

	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(%d) header from %s\n",
				   idx, obj->path);
			return -LIBBPF_ERRNO__FORMAT;
		}

		name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
		if (!name) {
			pr_warning("failed to get section(%d) name from %s\n",
				   idx, obj->path);
			return -LIBBPF_ERRNO__FORMAT;
		}

		data = elf_getdata(scn, 0);
		if (!data) {
			pr_warning("failed to get section(%d) data from %s(%s)\n",
				   idx, name, obj->path);
			return -LIBBPF_ERRNO__FORMAT;
		}
		pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
			 idx, name, (unsigned long)data->d_size,
			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
			 (int)sh.sh_type);

		if (strcmp(name, "license") == 0) {
			err = bpf_object__init_license(obj,
						       data->d_buf,
						       data->d_size);
			if (err)
				return err;
		} else if (strcmp(name, "version") == 0) {
			err = bpf_object__init_kversion(obj,
							data->d_buf,
							data->d_size);
			if (err)
				return err;
		} else if (strcmp(name, "maps") == 0) {
			obj->efile.maps_shndx = idx;
		} else if (strcmp(name, MAPS_ELF_SEC) == 0) {
			obj->efile.btf_maps_shndx = idx;
		} else if (strcmp(name, BTF_ELF_SEC) == 0) {
			btf_data = data;
		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
			btf_ext_data = data;
		} else if (sh.sh_type == SHT_SYMTAB) {
			if (obj->efile.symbols) {
				pr_warning("bpf: multiple SYMTAB in %s\n",
					   obj->path);
				return -LIBBPF_ERRNO__FORMAT;
			}
			obj->efile.symbols = data;
			obj->efile.strtabidx = sh.sh_link;
		} else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) {
			if (sh.sh_flags & SHF_EXECINSTR) {
				if (strcmp(name, ".text") == 0)
					obj->efile.text_shndx = idx;
				err = bpf_object__add_program(obj, data->d_buf,
							      data->d_size, name, idx);
				if (err) {
					char errmsg[STRERR_BUFSIZE];
					char *cp = libbpf_strerror_r(-err, errmsg,
								     sizeof(errmsg));

					pr_warning("failed to alloc program %s (%s): %s",
						   name, obj->path, cp);
					return err;
				}
			} else if (strcmp(name, ".data") == 0) {
				obj->efile.data = data;
				obj->efile.data_shndx = idx;
			} else if (strcmp(name, ".rodata") == 0) {
				obj->efile.rodata = data;
				obj->efile.rodata_shndx = idx;
			} else {
				pr_debug("skip section(%d) %s\n", idx, name);
			}
		} else if (sh.sh_type == SHT_REL) {
			int nr_reloc = obj->efile.nr_reloc;
			void *reloc = obj->efile.reloc;
			int sec = sh.sh_info; /* points to other section */

			/* Only do relo for section with exec instructions */
			if (!section_have_execinstr(obj, sec)) {
				pr_debug("skip relo %s(%d) for section(%d)\n",
					 name, idx, sec);
				continue;
			}

			reloc = reallocarray(reloc, nr_reloc + 1,
					     sizeof(*obj->efile.reloc));
			if (!reloc) {
				pr_warning("realloc failed\n");
				return -ENOMEM;
			}

			obj->efile.reloc = reloc;
			obj->efile.nr_reloc++;

			obj->efile.reloc[nr_reloc].shdr = sh;
			obj->efile.reloc[nr_reloc].data = data;
		} else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) {
			obj->efile.bss = data;
			obj->efile.bss_shndx = idx;
		} else {
			pr_debug("skip section(%d) %s\n", idx, name);
		}
	}

	if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
		pr_warning("Corrupted ELF file: index of strtab invalid\n");
		return -LIBBPF_ERRNO__FORMAT;
	}
	err = bpf_object__init_btf(obj, btf_data, btf_ext_data);
	if (!err)
		err = bpf_object__init_maps(obj, flags);
	if (!err)
		err = bpf_object__sanitize_and_load_btf(obj);
	if (!err)
		err = bpf_object__init_prog_names(obj);
	return err;
}

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;
}

struct bpf_program *
bpf_object__find_program_by_title(const struct bpf_object *obj,
				  const char *title)
{
	struct bpf_program *pos;

	bpf_object__for_each_program(pos, obj) {
		if (pos->section_name && !strcmp(pos->section_name, title))
			return pos;
	}
	return NULL;
}

static bool bpf_object__shndx_is_data(const struct bpf_object *obj,
				      int shndx)
{
	return shndx == obj->efile.data_shndx ||
	       shndx == obj->efile.bss_shndx ||
	       shndx == obj->efile.rodata_shndx;
}

static bool bpf_object__shndx_is_maps(const struct bpf_object *obj,
				      int shndx)
{
	return shndx == obj->efile.maps_shndx ||
	       shndx == obj->efile.btf_maps_shndx;
}

static bool bpf_object__relo_in_known_section(const struct bpf_object *obj,
					      int shndx)
{
	return shndx == obj->efile.text_shndx ||
	       bpf_object__shndx_is_maps(obj, shndx) ||
	       bpf_object__shndx_is_data(obj, shndx);
}

static enum libbpf_map_type
bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx)
{
	if (shndx == obj->efile.data_shndx)
		return LIBBPF_MAP_DATA;
	else if (shndx == obj->efile.bss_shndx)
		return LIBBPF_MAP_BSS;
	else if (shndx == obj->efile.rodata_shndx)
		return LIBBPF_MAP_RODATA;
	else
		return LIBBPF_MAP_UNSPEC;
}

static int
bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
			   Elf_Data *data, struct bpf_object *obj)
{
	Elf_Data *symbols = obj->efile.symbols;
	struct bpf_map *maps = obj->maps;
	size_t nr_maps = obj->nr_maps;
	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++) {
		struct bpf_insn *insns = prog->insns;
		enum libbpf_map_type type;
		unsigned int insn_idx;
		unsigned int shdr_idx;
		const char *name;
		size_t map_idx;
		GElf_Sym sym;
		GElf_Rel rel;

		if (!gelf_getrel(data, i, &rel)) {
			pr_warning("relocation: failed to get %d reloc\n", i);
			return -LIBBPF_ERRNO__FORMAT;
		}

		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));
			return -LIBBPF_ERRNO__FORMAT;
		}

		name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
				  sym.st_name) ? : "<?>";

		pr_debug("relo for %lld value %lld name %d (\'%s\')\n",
			 (long long) (rel.r_info >> 32),
			 (long long) sym.st_value, sym.st_name, name);

		shdr_idx = sym.st_shndx;
		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
		pr_debug("relocation: insn_idx=%u, shdr_idx=%u\n",
			 insn_idx, shdr_idx);

		if (shdr_idx >= SHN_LORESERVE) {
			pr_warning("relocation: not yet supported relo for non-static global \'%s\' variable in special section (0x%x) found in insns[%d].code 0x%x\n",
				   name, shdr_idx, insn_idx,
				   insns[insn_idx].code);
			return -LIBBPF_ERRNO__RELOC;
		}
		if (!bpf_object__relo_in_known_section(obj, shdr_idx)) {
			pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n",
				   prog->section_name, shdr_idx);
			return -LIBBPF_ERRNO__RELOC;
		}

		if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) {
			if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) {
				pr_warning("incorrect bpf_call opcode\n");
				return -LIBBPF_ERRNO__RELOC;
			}
			prog->reloc_desc[i].type = RELO_CALL;
			prog->reloc_desc[i].insn_idx = insn_idx;
			prog->reloc_desc[i].text_off = sym.st_value;
			obj->has_pseudo_calls = true;
			continue;
		}

		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);
			return -LIBBPF_ERRNO__RELOC;
		}

		if (bpf_object__shndx_is_maps(obj, shdr_idx) ||
		    bpf_object__shndx_is_data(obj, shdr_idx)) {
			type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx);
			if (type != LIBBPF_MAP_UNSPEC) {
				if (GELF_ST_BIND(sym.st_info) == STB_GLOBAL) {
					pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n",
						   name, insn_idx, insns[insn_idx].code);
					return -LIBBPF_ERRNO__RELOC;
				}
				if (!obj->caps.global_data) {
					pr_warning("bpf: relocation: kernel does not support global \'%s\' variable access in insns[%d]\n",
						   name, insn_idx);
					return -LIBBPF_ERRNO__RELOC;
				}
			}

			for (map_idx = 0; map_idx < nr_maps; map_idx++) {
				if (maps[map_idx].libbpf_type != type)
					continue;
				if (type != LIBBPF_MAP_UNSPEC ||
				    (maps[map_idx].sec_idx == sym.st_shndx &&
				     maps[map_idx].sec_offset == sym.st_value)) {
					pr_debug("relocation: found map %zd (%s, sec_idx %d, offset %zu) for insn %u\n",
						 map_idx, maps[map_idx].name,
						 maps[map_idx].sec_idx,
						 maps[map_idx].sec_offset,
						 insn_idx);
					break;
				}
			}

			if (map_idx >= nr_maps) {
				pr_warning("bpf relocation: map_idx %d larger than %d\n",
					   (int)map_idx, (int)nr_maps - 1);
				return -LIBBPF_ERRNO__RELOC;
			}

			prog->reloc_desc[i].type = type != LIBBPF_MAP_UNSPEC ?
						   RELO_DATA : RELO_LD64;
			prog->reloc_desc[i].insn_idx = insn_idx;
			prog->reloc_desc[i].map_idx = map_idx;
		}
	}
	return 0;
}

static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
{
	struct bpf_map_def *def = &map->def;
	__u32 key_type_id = 0, value_type_id = 0;
	int ret;

	/* if it's BTF-defined map, we don't need to search for type IDs */
	if (map->sec_idx == obj->efile.btf_maps_shndx)
		return 0;

	if (!bpf_map__is_internal(map)) {
		ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size,
					   def->value_size, &key_type_id,
					   &value_type_id);
	} else {
		/*
		 * LLVM annotates global data differently in BTF, that is,
		 * only as '.data', '.bss' or '.rodata'.
		 */
		ret = btf__find_by_name(obj->btf,
				libbpf_type_to_btf_name[map->libbpf_type]);
	}
	if (ret < 0)
		return ret;

	map->btf_key_type_id = key_type_id;
	map->btf_value_type_id = bpf_map__is_internal(map) ?
				 ret : value_type_id;
	return 0;
}

int bpf_map__reuse_fd(struct bpf_map *map, int fd)
{
	struct bpf_map_info info = {};
	__u32 len = sizeof(info);
	int new_fd, err;
	char *new_name;

	err = bpf_obj_get_info_by_fd(fd, &info, &len);
	if (err)
		return err;

	new_name = strdup(info.name);
	if (!new_name)
		return -errno;

	new_fd = open("/", O_RDONLY | O_CLOEXEC);
	if (new_fd < 0) {
		err = -errno;
		goto err_free_new_name;
	}

	new_fd = dup3(fd, new_fd, O_CLOEXEC);
	if (new_fd < 0) {
		err = -errno;
		goto err_close_new_fd;
	}

	err = zclose(map->fd);
	if (err) {
		err = -errno;
		goto err_close_new_fd;
	}
	free(map->name);

	map->fd = new_fd;
	map->name = new_name;
	map->def.type = info.type;
	map->def.key_size = info.key_size;
	map->def.value_size = info.value_size;
	map->def.max_entries = info.max_entries;
	map->def.map_flags = info.map_flags;
	map->btf_key_type_id = info.btf_key_type_id;
	map->btf_value_type_id = info.btf_value_type_id;

	return 0;

err_close_new_fd:
	close(new_fd);
err_free_new_name:
	free(new_name);
	return err;
}

int bpf_map__resize(struct bpf_map *map, __u32 max_entries)
{
	if (!map || !max_entries)
		return -EINVAL;

	/* If map already created, its attributes can't be changed. */
	if (map->fd >= 0)
		return -EBUSY;

	map->def.max_entries = max_entries;

	return 0;
}

static int
bpf_object__probe_name(struct bpf_object *obj)
{
	struct bpf_load_program_attr attr;
	char *cp, errmsg[STRERR_BUFSIZE];
	struct bpf_insn insns[] = {
		BPF_MOV64_IMM(BPF_REG_0, 0),
		BPF_EXIT_INSN(),
	};
	int ret;

	/* make sure basic loading works */

	memset(&attr, 0, sizeof(attr));
	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
	attr.insns = insns;
	attr.insns_cnt = ARRAY_SIZE(insns);
	attr.license = "GPL";

	ret = bpf_load_program_xattr(&attr, NULL, 0);
	if (ret < 0) {
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
		pr_warning("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n",
			   __func__, cp, errno);
		return -errno;
	}
	close(ret);

	/* now try the same program, but with the name */

	attr.name = "test";
	ret = bpf_load_program_xattr(&attr, NULL, 0);
	if (ret >= 0) {
		obj->caps.name = 1;
		close(ret);
	}

	return 0;
}

static int
bpf_object__probe_global_data(struct bpf_object *obj)
{
	struct bpf_load_program_attr prg_attr;
	struct bpf_create_map_attr map_attr;
	char *cp, errmsg[STRERR_BUFSIZE];
	struct bpf_insn insns[] = {
		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16),
		BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
		BPF_MOV64_IMM(BPF_REG_0, 0),
		BPF_EXIT_INSN(),
	};
	int ret, map;

	memset(&map_attr, 0, sizeof(map_attr));
	map_attr.map_type = BPF_MAP_TYPE_ARRAY;
	map_attr.key_size = sizeof(int);
	map_attr.value_size = 32;
	map_attr.max_entries = 1;

	map = bpf_create_map_xattr(&map_attr);
	if (map < 0) {
		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
		pr_warning("Error in %s():%s(%d). Couldn't create simple array map.\n",
			   __func__, cp, errno);
		return -errno;
	}

	insns[0].imm = map;

	memset(&prg_attr, 0, sizeof(prg_attr));
	prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
	prg_attr.insns = insns;
	prg_attr.insns_cnt = ARRAY_SIZE(insns);
	prg_attr.license = "GPL";

	ret = bpf_load_program_xattr(&prg_attr, NULL, 0);
	if (ret >= 0) {
		obj->caps.global_data = 1;
		close(ret);
	}

	close(map);
	return 0;
}

static int bpf_object__probe_btf_func(struct bpf_object *obj)
{
	const char strs[] = "\0int\0x\0a";
	/* void x(int a) {} */
	__u32 types[] = {
		/* int */
		BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
		/* FUNC_PROTO */                                /* [2] */
		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0),
		BTF_PARAM_ENC(7, 1),
		/* FUNC x */                                    /* [3] */
		BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2),
	};
	int btf_fd;

	btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types),
				      strs, sizeof(strs));
	if (btf_fd >= 0) {
		obj->caps.btf_func = 1;
		close(btf_fd);
		return 1;
	}

	return 0;
}

static int bpf_object__probe_btf_datasec(struct bpf_object *obj)
{
	const char strs[] = "\0x\0.data";
	/* static int a; */
	__u32 types[] = {
		/* int */
		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
		/* VAR x */                                     /* [2] */
		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
		BTF_VAR_STATIC,
		/* DATASEC val */                               /* [3] */
		BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
		BTF_VAR_SECINFO_ENC(2, 0, 4),
	};
	int btf_fd;

	btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types),
				      strs, sizeof(strs));
	if (btf_fd >= 0) {
		obj->caps.btf_datasec = 1;
		close(btf_fd);
		return 1;
	}

	return 0;
}

static int
bpf_object__probe_caps(struct bpf_object *obj)
{
	int (*probe_fn[])(struct bpf_object *obj) = {
		bpf_object__probe_name,
		bpf_object__probe_global_data,
		bpf_object__probe_btf_func,
		bpf_object__probe_btf_datasec,
	};
	int i, ret;

	for (i = 0; i < ARRAY_SIZE(probe_fn); i++) {
		ret = probe_fn[i](obj);
		if (ret < 0)
			pr_debug("Probe #%d failed with %d.\n", i, ret);
	}

	return 0;
}

static int
bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
{
	char *cp, errmsg[STRERR_BUFSIZE];
	int err, zero = 0;
	__u8 *data;

	/* Nothing to do here since kernel already zero-initializes .bss map. */
	if (map->libbpf_type == LIBBPF_MAP_BSS)
		return 0;

	data = map->libbpf_type == LIBBPF_MAP_DATA ?
	       obj->sections.data : obj->sections.rodata;

	err = bpf_map_update_elem(map->fd, &zero, data, 0);
	/* Freeze .rodata map as read-only from syscall side. */
	if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) {
		err = bpf_map_freeze(map->fd);
		if (err) {
			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
			pr_warning("Error freezing map(%s) as read-only: %s\n",
				   map->name, cp);
			err = 0;
		}
	}
	return err;
}

static int
bpf_object__create_maps(struct bpf_object *obj)
{
	struct bpf_create_map_attr create_attr = {};
	int nr_cpus = 0;
	unsigned int i;
	int err;

	for (i = 0; i < obj->nr_maps; i++) {
		struct bpf_map *map = &obj->maps[i];
		struct bpf_map_def *def = &map->def;
		char *cp, errmsg[STRERR_BUFSIZE];
		int *pfd = &map->fd;

		if (map->fd >= 0) {
			pr_debug("skip map create (preset) %s: fd=%d\n",
				 map->name, map->fd);
			continue;
		}

		if (obj->caps.name)
			create_attr.name = map->name;
		create_attr.map_ifindex = map->map_ifindex;
		create_attr.map_type = def->type;
		create_attr.map_flags = def->map_flags;
		create_attr.key_size = def->key_size;
		create_attr.value_size = def->value_size;
		if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY &&
		    !def->max_entries) {
			if (!nr_cpus)
				nr_cpus = libbpf_num_possible_cpus();
			if (nr_cpus < 0) {
				pr_warning("failed to determine number of system CPUs: %d\n",
					   nr_cpus);
				err = nr_cpus;
				goto err_out;
			}
			pr_debug("map '%s': setting size to %d\n",
				 map->name, nr_cpus);
			create_attr.max_entries = nr_cpus;
		} else {
			create_attr.max_entries = def->max_entries;
		}
		create_attr.btf_fd = 0;
		create_attr.btf_key_type_id = 0;
		create_attr.btf_value_type_id = 0;
		if (bpf_map_type__is_map_in_map(def->type) &&
		    map->inner_map_fd >= 0)
			create_attr.inner_map_fd = map->inner_map_fd;

		if (obj->btf && !bpf_map_find_btf_info(obj, map)) {
			create_attr.btf_fd = btf__fd(obj->btf);
			create_attr.btf_key_type_id = map->btf_key_type_id;
			create_attr.btf_value_type_id = map->btf_value_type_id;
		}

		*pfd = bpf_create_map_xattr(&create_attr);
		if (*pfd < 0 && (create_attr.btf_key_type_id ||
				 create_attr.btf_value_type_id)) {
			err = -errno;
			cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
			pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
				   map->name, cp, err);
			create_attr.btf_fd = 0;
			create_attr.btf_key_type_id = 0;
			create_attr.btf_value_type_id = 0;
			map->btf_key_type_id = 0;
			map->btf_value_type_id = 0;
			*pfd = bpf_create_map_xattr(&create_attr);
		}

		if (*pfd < 0) {
			size_t j;

			err = -errno;
err_out:
			cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg));
			pr_warning("failed to create map (name: '%s'): %s(%d)\n",
				   map->name, cp, err);
			for (j = 0; j < i; j++)
				zclose(obj->maps[j].fd);
			return err;
		}

		if (bpf_map__is_internal(map)) {
			err = bpf_object__populate_internal_map(obj, map);
			if (err < 0) {
				zclose(*pfd);
				goto err_out;
			}
		}

		pr_debug("created map %s: fd=%d\n", map->name, *pfd);
	}

	return 0;
}

static int
check_btf_ext_reloc_err(struct bpf_program *prog, int err,
			void *btf_prog_info, const char *info_name)
{
	if (err != -ENOENT) {
		pr_warning("Error in loading %s for sec %s.\n",
			   info_name, prog->section_name);
		return err;
	}

	/* err == -ENOENT (i.e. prog->section_name not found in btf_ext) */

	if (btf_prog_info) {
		/*
		 * Some info has already been found but has problem
		 * in the last btf_ext reloc. Must have to error out.
		 */
		pr_warning("Error in relocating %s for sec %s.\n",
			   info_name, prog->section_name);
		return err;
	}

	/* Have problem loading the very first info. Ignore the rest. */
	pr_warning("Cannot find %s for main program sec %s. Ignore all %s.\n",
		   info_name, prog->section_name, info_name);
	return 0;
}

static int
bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj,
			  const char *section_name,  __u32 insn_offset)
{
	int err;

	if (!insn_offset || prog->func_info) {
		/*
		 * !insn_offset => main program
		 *
		 * For sub prog, the main program's func_info has to
		 * be loaded first (i.e. prog->func_info != NULL)
		 */
		err = btf_ext__reloc_func_info(obj->btf, obj->btf_ext,
					       section_name, insn_offset,
					       &prog->func_info,
					       &prog->func_info_cnt);
		if (err)
			return check_btf_ext_reloc_err(prog, err,
						       prog->func_info,
						       "bpf_func_info");

		prog->func_info_rec_size = btf_ext__func_info_rec_size(obj->btf_ext);
	}

	if (!insn_offset || prog->line_info) {
		err = btf_ext__reloc_line_info(obj->btf, obj->btf_ext,
					       section_name, insn_offset,
					       &prog->line_info,
					       &prog->line_info_cnt);
		if (err)
			return check_btf_ext_reloc_err(prog, err,
						       prog->line_info,
						       "bpf_line_info");

		prog->line_info_rec_size = btf_ext__line_info_rec_size(obj->btf_ext);
	}

	return 0;
}

#define BPF_CORE_SPEC_MAX_LEN 64

/* represents BPF CO-RE field or array element accessor */
struct bpf_core_accessor {
	__u32 type_id;		/* struct/union type or array element type */
	__u32 idx;		/* field index or array index */
	const char *name;	/* field name or NULL for array accessor */
};

struct bpf_core_spec {
	const struct btf *btf;
	/* high-level spec: named fields and array indices only */
	struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN];
	/* high-level spec length */
	int len;
	/* raw, low-level spec: 1-to-1 with accessor spec string */
	int raw_spec[BPF_CORE_SPEC_MAX_LEN];
	/* raw spec length */
	int raw_len;
	/* field byte offset represented by spec */
	__u32 offset;
};

static bool str_is_empty(const char *s)
{
	return !s || !s[0];
}

/*
 * Turn bpf_offset_reloc into a low- and high-level spec representation,
 * validating correctness along the way, as well as calculating resulting
 * field offset (in bytes), specified by accessor string. Low-level spec
 * captures every single level of nestedness, including traversing anonymous
 * struct/union members. High-level one only captures semantically meaningful
 * "turning points": named fields and array indicies.
 * E.g., for this case:
 *
 *   struct sample {
 *       int __unimportant;
 *       struct {
 *           int __1;
 *           int __2;
 *           int a[7];
 *       };
 *   };
 *
 *   struct sample *s = ...;
 *
 *   int x = &s->a[3]; // access string = '0:1:2:3'
 *
 * Low-level spec has 1:1 mapping with each element of access string (it's
 * just a parsed access string representation): [0, 1, 2, 3].
 *
 * High-level spec will capture only 3 points:
 *   - intial zero-index access by pointer (&s->... is the same as &s[0]...);
 *   - field 'a' access (corresponds to '2' in low-level spec);
 *   - array element #3 access (corresponds to '3' in low-level spec).
 *
 */
static int bpf_core_spec_parse(const struct btf *btf,
			       __u32 type_id,
			       const char *spec_str,
			       struct bpf_core_spec *spec)
{
	int access_idx, parsed_len, i;
	const struct btf_type *t;
	const char *name;
	__u32 id;
	__s64 sz;

	if (str_is_empty(spec_str) || *spec_str == ':')
		return -EINVAL;

	memset(spec, 0, sizeof(*spec));
	spec->btf = btf;

	/* parse spec_str="0:1:2:3:4" into array raw_spec=[0, 1, 2, 3, 4] */
	while (*spec_str) {
		if (*spec_str == ':')
			++spec_str;
		if (sscanf(spec_str, "%d%n", &access_idx, &parsed_len) != 1)
			return -EINVAL;
		if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
			return -E2BIG;
		spec_str += parsed_len;
		spec->raw_spec[spec->raw_len++] = access_idx;
	}

	if (spec->raw_len == 0)
		return -EINVAL;

	/* first spec value is always reloc type array index */
	t = skip_mods_and_typedefs(btf, type_id, &id);
	if (!t)
		return -EINVAL;

	access_idx = spec->raw_spec[0];
	spec->spec[0].type_id = id;
	spec->spec[0].idx = access_idx;
	spec->len++;

	sz = btf__resolve_size(btf, id);
	if (sz < 0)
		return sz;
	spec->offset = access_idx * sz;

	for (i = 1; i < spec->raw_len; i++) {
		t = skip_mods_and_typedefs(btf, id, &id);
		if (!t)
			return -EINVAL;

		access_idx = spec->raw_spec[i];

		if (btf_is_composite(t)) {
			const struct btf_member *m;
			__u32 offset;

			if (access_idx >= btf_vlen(t))
				return -EINVAL;
			if (btf_member_bitfield_size(t, access_idx))
				return -EINVAL;

			offset = btf_member_bit_offset(t, access_idx);
			if (offset % 8)
				return -EINVAL;
			spec->offset += offset / 8;

			m = btf_members(t) + access_idx;
			if (m->name_off) {
				name = btf__name_by_offset(btf, m->name_off);
				if (str_is_empty(name))
					return -EINVAL;

				spec->spec[spec->len].type_id = id;
				spec->spec[spec->len].idx = access_idx;
				spec->spec[spec->len].name = name;
				spec->len++;
			}

			id = m->type;
		} else if (btf_is_array(t)) {
			const struct btf_array *a = btf_array(t);

			t = skip_mods_and_typedefs(btf, a->type, &id);
			if (!t || access_idx >= a->nelems)
				return -EINVAL;

			spec->spec[spec->len].type_id = id;
			spec->spec[spec->len].idx = access_idx;
			spec->len++;

			sz = btf__resolve_size(btf, id);
			if (sz < 0)
				return sz;
			spec->offset += access_idx * sz;
		} else {
			pr_warning("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %d\n",
				   type_id, spec_str, i, id, btf_kind(t));
			return -EINVAL;
		}
	}

	return 0;
}

static bool bpf_core_is_flavor_sep(const char *s)
{
	/* check X___Y name pattern, where X and Y are not underscores */
	return s[0] != '_' &&				      /* X */
	       s[1] == '_' && s[2] == '_' && s[3] == '_' &&   /* ___ */
	       s[4] != '_';				      /* Y */
}

/* Given 'some_struct_name___with_flavor' return the length of a name prefix
 * before last triple underscore. Struct name part after last triple
 * underscore is ignored by BPF CO-RE relocation during relocation matching.
 */
static size_t bpf_core_essential_name_len(const char *name)
{
	size_t n = strlen(name);
	int i;

	for (i = n - 5; i >= 0; i--) {
		if (bpf_core_is_flavor_sep(name + i))
			return i + 1;
	}
	return n;
}

/* dynamically sized list of type IDs */
struct ids_vec {
	__u32 *data;
	int len;
};

static void bpf_core_free_cands(struct ids_vec *cand_ids)
{
	free(cand_ids->data);
	free(cand_ids);
}

static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf,
					   __u32 local_type_id,
					   const struct btf *targ_btf)
{
	size_t local_essent_len, targ_essent_len;
	const char *local_name, *targ_name;
	const struct btf_type *t;
	struct ids_vec *cand_ids;
	__u32 *new_ids;
	int i, err, n;

	t = btf__type_by_id(local_btf, local_type_id);
	if (!t)
		return ERR_PTR(-EINVAL);

	local_name = btf__name_by_offset(local_btf, t->name_off);
	if (str_is_empty(local_name))
		return ERR_PTR(-EINVAL);
	local_essent_len = bpf_core_essential_name_len(local_name);

	cand_ids = calloc(1, sizeof(*cand_ids));
	if (!cand_ids)
		return ERR_PTR(-ENOMEM);

	n = btf__get_nr_types(targ_btf);
	for (i = 1; i <= n; i++) {
		t = btf__type_by_id(targ_btf, i);
		targ_name = btf__name_by_offset(targ_btf, t->name_off);
		if (str_is_empty(targ_name))
			continue;

		targ_essent_len = bpf_core_essential_name_len(targ_name);
		if (targ_essent_len != local_essent_len)
			continue;

		if (strncmp(local_name, targ_name, local_essent_len) == 0) {
			pr_debug("[%d] %s: found candidate [%d] %s\n",
				 local_type_id, local_name, i, targ_name);
			new_ids = reallocarray(cand_ids->data,
					       cand_ids->len + 1,
					       sizeof(*cand_ids->data));
			if (!new_ids) {
				err = -ENOMEM;
				goto err_out;
			}
			cand_ids->data = new_ids;
			cand_ids->data[cand_ids->len++] = i;
		}
	}
	return cand_ids;
err_out:
	bpf_core_free_cands(cand_ids);
	return ERR_PTR(err);
}

/* Check two types for compatibility, skipping const/volatile/restrict and
 * typedefs, to ensure we are relocating offset to the compatible entities:
 *   - any two STRUCTs/UNIONs are compatible and can be mixed;
 *   - any two FWDs are compatible;
 *   - any two PTRs are always compatible;
 *   - for ENUMs, check sizes, names are ignored;
 *   - for INT, size and bitness should match, signedness is ignored;
 *   - for ARRAY, dimensionality is ignored, element types are checked for
 *     compatibility recursively;
 *   - everything else shouldn't be ever a target of relocation.
 * These rules are not set in stone and probably will be adjusted as we get
 * more experience with using BPF CO-RE relocations.
 */
static int bpf_core_fields_are_compat(const struct btf *local_btf,
				      __u32 local_id,
				      const struct btf *targ_btf,
				      __u32 targ_id)
{
	const struct btf_type *local_type, *targ_type;

recur:
	local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id);
	targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id);
	if (!local_type || !targ_type)
		return -EINVAL;

	if (btf_is_composite(local_type) && btf_is_composite(targ_type))
		return 1;
	if (btf_kind(local_type) != btf_kind(targ_type))
		return 0;

	switch (btf_kind(local_type)) {
	case BTF_KIND_FWD:
	case BTF_KIND_PTR:
		return 1;
	case BTF_KIND_ENUM:
		return local_type->size == targ_type->size;
	case BTF_KIND_INT:
		return btf_int_offset(local_type) == 0 &&
		       btf_int_offset(targ_type) == 0 &&
		       local_type->size == targ_type->size &&
		       btf_int_bits(local_type) == btf_int_bits(targ_type);
	case BTF_KIND_ARRAY:
		local_id = btf_array(local_type)->type;
		targ_id = btf_array(targ_type)->type;
		goto recur;
	default:
		pr_warning("unexpected kind %d relocated, local [%d], target [%d]\n",
			   btf_kind(local_type), local_id, targ_id);
		return 0;
	}
}

/*
 * Given single high-level named field accessor in local type, find
 * corresponding high-level accessor for a target type. Along the way,
 * maintain low-level spec for target as well. Also keep updating target
 * offset.
 *
 * Searching is performed through recursive exhaustive enumeration of all
 * fields of a struct/union. If there are any anonymous (embedded)
 * structs/unions, they are recursively searched as well. If field with
 * desired name is found, check compatibility between local and target types,
 * before returning result.
 *
 * 1 is returned, if field is found.
 * 0 is returned if no compatible field is found.
 * <0 is returned on error.
 */
static int bpf_core_match_member(const struct btf *local_btf,
				 const struct bpf_core_accessor *local_acc,
				 const struct btf *targ_btf,
				 __u32 targ_id,
				 struct bpf_core_spec *spec,
				 __u32 *next_targ_id)
{
	const struct btf_type *local_type, *targ_type;
	const struct btf_member *local_member, *m;
	const char *local_name, *targ_name;
	__u32 local_id;
	int i, n, found;

	targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id);
	if (!targ_type)
		return -EINVAL;
	if (!btf_is_composite(targ_type))
		return 0;

	local_id = local_acc->type_id;
	local_type = btf__type_by_id(local_btf, local_id);
	local_member = btf_members(local_type) + local_acc->idx;
	local_name = btf__name_by_offset(local_btf, local_member->name_off);

	n = btf_vlen(targ_type);
	m = btf_members(targ_type);
	for (i = 0; i < n; i++, m++) {
		__u32 offset;

		/* bitfield relocations not supported */
		if (btf_member_bitfield_size(targ_type, i))
			continue;
		offset = btf_member_bit_offset(targ_type, i);
		if (offset % 8)
			continue;

		/* too deep struct/union/array nesting */
		if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
			return -E2BIG;

		/* speculate this member will be the good one */
		spec->offset += offset / 8;
		spec->raw_spec[spec->raw_len++] = i;

		targ_name = btf__name_by_offset(targ_btf, m->name_off);
		if (str_is_empty(targ_name)) {
			/* embedded struct/union, we need to go deeper */
			found = bpf_core_match_member(local_btf, local_acc,
						      targ_btf, m->type,
						      spec, next_targ_id);
			if (found) /* either found or error */
				return found;
		} else if (strcmp(local_name, targ_name) == 0) {
			/* matching named field */
			struct bpf_core_accessor *targ_acc;

			targ_acc = &spec->spec[spec->len++];
			targ_acc->type_id = targ_id;
			targ_acc->idx = i;
			targ_acc->name = targ_name;

			*next_targ_id = m->type;
			found = bpf_core_fields_are_compat(local_btf,
							   local_member->type,
							   targ_btf, m->type);
			if (!found)
				spec->len--; /* pop accessor */
			return found;
		}
		/* member turned out not to be what we looked for */
		spec->offset -= offset / 8;
		spec->raw_len--;
	}

	return 0;
}

/*
 * Try to match local spec to a target type and, if successful, produce full
 * target spec (high-level, low-level + offset).
 */
static int bpf_core_spec_match(struct bpf_core_spec *local_spec,
			       const struct btf *targ_btf, __u32 targ_id,
			       struct bpf_core_spec *targ_spec)
{
	const struct btf_type *targ_type;
	const struct bpf_core_accessor *local_acc;
	struct bpf_core_accessor *targ_acc;
	int i, sz, matched;

	memset(targ_spec, 0, sizeof(*targ_spec));
	targ_spec->btf = targ_btf;

	local_acc = &local_spec->spec[0];
	targ_acc = &targ_spec->spec[0];

	for (i = 0; i < local_spec->len; i++, local_acc++, targ_acc++) {
		targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id,
						   &targ_id);
		if (!targ_type)
			return -EINVAL;

		if (local_acc->name) {
			matched = bpf_core_match_member(local_spec->btf,
							local_acc,
							targ_btf, targ_id,
							targ_spec, &targ_id);
			if (matched <= 0)
				return matched;
		} else {
			/* for i=0, targ_id is already treated as array element
			 * type (because it's the original struct), for others
			 * we should find array element type first
			 */
			if (i > 0) {
				const struct btf_array *a;

				if (!btf_is_array(targ_type))
					return 0;

				a = btf_array(targ_type);
				if (local_acc->idx >= a->nelems)
					return 0;
				if (!skip_mods_and_typedefs(targ_btf, a->type,
							    &targ_id))
					return -EINVAL;
			}

			/* too deep struct/union/array nesting */
			if (targ_spec->raw_len == BPF_CORE_SPEC_MAX_LEN)
				return -E2BIG;

			targ_acc->type_id = targ_id;
			targ_acc->idx = local_acc->idx;
			targ_acc->name = NULL;
			targ_spec->len++;
			targ_spec->raw_spec[targ_spec->raw_len] = targ_acc->idx;
			targ_spec->raw_len++;

			sz = btf__resolve_size(targ_btf, targ_id);
			if (sz < 0)
				return sz;
			targ_spec->offset += local_acc->idx * sz;
		}
	}

	return 1;
}

/*
 * Patch relocatable BPF instruction.
 * Expected insn->imm value is provided for validation, as well as the new
 * relocated value.
 *
 * Currently three kinds of BPF instructions are supported:
 * 1. rX = <imm> (assignment with immediate operand);
 * 2. rX += <imm> (arithmetic operations with immediate operand);
 * 3. *(rX) = <imm> (indirect memory assignment with immediate operand).
 *
 * If actual insn->imm value is wrong, bail out.
 */
static int bpf_core_reloc_insn(struct bpf_program *prog, int insn_off,
			       __u32 orig_off, __u32 new_off)
{
	struct bpf_insn *insn;
	int insn_idx;
	__u8 class;

	if (insn_off % sizeof(struct bpf_insn))
		return -EINVAL;
	insn_idx = insn_off / sizeof(struct bpf_insn);

	insn = &prog->insns[insn_idx];
	class = BPF_CLASS(insn->code);

	if (class == BPF_ALU || class == BPF_ALU64) {
		if (BPF_SRC(insn->code) != BPF_K)
			return -EINVAL;
		if (insn->imm != orig_off)
			return -EINVAL;
		insn->imm = new_off;
		pr_debug("prog '%s': patched insn #%d (ALU/ALU64) imm %d -> %d\n",
			 bpf_program__title(prog, false),
			 insn_idx, orig_off, new_off);
	} else {
		pr_warning("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n",
			   bpf_program__title(prog, false),
			   insn_idx, insn->code, insn->src_reg, insn->dst_reg,
			   insn->off, insn->imm);
		return -EINVAL;
	}
	return 0;
}

static struct btf *btf_load_raw(const char *path)
{
	struct btf *btf;
	size_t read_cnt;
	struct stat st;
	void *data;
	FILE *f;

	if (stat(path, &st))
		return ERR_PTR(-errno);

	data = malloc(st.st_size);
	if (!data)
		return ERR_PTR(-ENOMEM);

	f = fopen(path, "rb");
	if (!f) {
		btf = ERR_PTR(-errno);
		goto cleanup;
	}

	read_cnt = fread(data, 1, st.st_size, f);
	fclose(f);
	if (read_cnt < st.st_size) {
		btf = ERR_PTR(-EBADF);
		goto cleanup;
	}

	btf = btf__new(data, read_cnt);

cleanup:
	free(data);
	return btf;
}

/*
 * Probe few well-known locations for vmlinux kernel image and try to load BTF
 * data out of it to use for target BTF.
 */
static struct btf *bpf_core_find_kernel_btf(void)
{
	struct {
		const char *path_fmt;
		bool raw_btf;
	} locations[] = {
		/* try canonical vmlinux BTF through sysfs first */
		{ "/sys/kernel/btf/vmlinux", true /* raw BTF */ },
		/* fall back to trying to find vmlinux ELF on disk otherwise */
		{ "/boot/vmlinux-%1$s" },
		{ "/lib/modules/%1$s/vmlinux-%1$s" },
		{ "/lib/modules/%1$s/build/vmlinux" },
		{ "/usr/lib/modules/%1$s/kernel/vmlinux" },
		{ "/usr/lib/debug/boot/vmlinux-%1$s" },
		{ "/usr/lib/debug/boot/vmlinux-%1$s.debug" },
		{ "/usr/lib/debug/lib/modules/%1$s/vmlinux" },
	};
	char path[PATH_MAX + 1];
	struct utsname buf;
	struct btf *btf;
	int i;

	uname(&buf);

	for (i = 0; i < ARRAY_SIZE(locations); i++) {
		snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release);

		if (access(path, R_OK))
			continue;

		if (locations[i].raw_btf)
			btf = btf_load_raw(path);
		else
			btf = btf__parse_elf(path, NULL);

		pr_debug("loading kernel BTF '%s': %ld\n",
			 path, IS_ERR(btf) ? PTR_ERR(btf) : 0);
		if (IS_ERR(btf))
			continue;

		return btf;
	}

	pr_warning("failed to find valid kernel BTF\n");
	return ERR_PTR(-ESRCH);
}

/* Output spec definition in the format:
 * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>,
 * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b
 */
static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec)
{
	const struct btf_type *t;
	const char *s;
	__u32 type_id;
	int i;

	type_id = spec->spec[0].type_id;
	t = btf__type_by_id(spec->btf, type_id);
	s = btf__name_by_offset(spec->btf, t->name_off);
	libbpf_print(level, "[%u] %s + ", type_id, s);

	for (i = 0; i < spec->raw_len; i++)
		libbpf_print(level, "%d%s", spec->raw_spec[i],
			     i == spec->raw_len - 1 ? " => " : ":");

	libbpf_print(level, "%u @ &x", spec->offset);

	for (i = 0; i < spec->len; i++) {
		if (spec->spec[i].name)
			libbpf_print(level, ".%s", spec->spec[i].name);
		else
			libbpf_print(level, "[%u]", spec->spec[i].idx);
	}

}

static size_t bpf_core_hash_fn(const void *key, void *ctx)
{
	return (size_t)key;
}

static bool bpf_core_equal_fn(const void *k1, const void *k2, void *ctx)
{
	return k1 == k2;
}

static void *u32_as_hash_key(__u32 x)
{
	return (void *)(uintptr_t)x;
}

/*
 * CO-RE relocate single instruction.
 *
 * The outline and important points of the algorithm:
 * 1. For given local type, find corresponding candidate target types.