libbpf.c

/*
 * 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.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation;
 * version 2.1 of the License (not later!)
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this program; if not,  see <http://www.gnu.org/licenses>
 */

#include <stdlib.h>
#include <stdio.h>
#include <stdarg.h>
#include <libgen.h>
#include <inttypes.h>
#include <string.h>
#include <unistd.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/list.h>
#include <linux/limits.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/vfs.h>
#include <libelf.h>
#include <gelf.h>

#include "libbpf.h"
#include "bpf.h"

#ifndef EM_BPF
#define EM_BPF 247
#endif

#ifndef BPF_FS_MAGIC
#define BPF_FS_MAGIC		0xcafe4a11
#endif

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

__printf(1, 2)
static int __base_pr(const char *format, ...)
{
	va_list args;
	int err;

	va_start(args, format);
	err = vfprintf(stderr, format, args);
	va_end(args);
	return err;
}

static __printf(1, 2) libbpf_print_fn_t __pr_warning = __base_pr;
static __printf(1, 2) libbpf_print_fn_t __pr_info = __base_pr;
static __printf(1, 2) libbpf_print_fn_t __pr_debug;

#define __pr(func, fmt, ...)	\
do {				\
	if ((func))		\
		(func)("libbpf: " fmt, ##__VA_ARGS__); \
} while (0)

#define pr_warning(fmt, ...)	__pr(__pr_warning, fmt, ##__VA_ARGS__)
#define pr_info(fmt, ...)	__pr(__pr_info, fmt, ##__VA_ARGS__)
#define pr_debug(fmt, ...)	__pr(__pr_debug, fmt, ##__VA_ARGS__)

void libbpf_set_print(libbpf_print_fn_t warn,
		      libbpf_print_fn_t info,
		      libbpf_print_fn_t debug)
{
	__pr_warning = warn;
	__pr_info = info;
	__pr_debug = debug;
}

#define STRERR_BUFSIZE  128

#define ERRNO_OFFSET(e)		((e) - __LIBBPF_ERRNO__START)
#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(LIBBPF_ERRNO__##c)
#define NR_ERRNO	(__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)

static const char *libbpf_strerror_table[NR_ERRNO] = {
	[ERRCODE_OFFSET(LIBELF)]	= "Something wrong in libelf",
	[ERRCODE_OFFSET(FORMAT)]	= "BPF object format invalid",
	[ERRCODE_OFFSET(KVERSION)]	= "'version' section incorrect or lost",
	[ERRCODE_OFFSET(ENDIAN)]	= "Endian mismatch",
	[ERRCODE_OFFSET(INTERNAL)]	= "Internal error in libbpf",
	[ERRCODE_OFFSET(RELOC)]		= "Relocation failed",
	[ERRCODE_OFFSET(VERIFY)]	= "Kernel verifier blocks program loading",
	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
};

int libbpf_strerror(int err, char *buf, size_t size)
{
	if (!buf || !size)
		return -1;

	err = err > 0 ? err : -err;

	if (err < __LIBBPF_ERRNO__START) {
		int ret;

		ret = strerror_r(err, buf, size);
		buf[size - 1] = '\0';
		return ret;
	}

	if (err < __LIBBPF_ERRNO__END) {
		const char *msg;

		msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
		snprintf(buf, size, "%s", msg);
		buf[size - 1] = '\0';
		return 0;
	}

	snprintf(buf, size, "Unknown libbpf error %d", err);
	buf[size - 1] = '\0';
	return -1;
}

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


/* 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

/*
 * bpf_prog should be a better name but it has been used in
 * linux/filter.h.
 */
struct bpf_program {
	/* Index in elf obj file, for relocation use. */
	int idx;
	char *section_name;
	struct bpf_insn *insns;
	size_t insns_cnt;
	enum bpf_prog_type type;

	struct {
		int insn_idx;
		int map_idx;
	} *reloc_desc;
	int nr_reloc;

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

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

struct bpf_map {
	int fd;
	char *name;
	size_t offset;
	struct bpf_map_def def;
	void *priv;
	bpf_map_clear_priv_t clear_priv;
};

static LIST_HEAD(bpf_objects_list);

struct bpf_object {
	char license[64];
	u32 kern_version;

	struct bpf_program *programs;
	size_t nr_programs;
	struct bpf_map *maps;
	size_t nr_maps;

	bool loaded;

	/*
	 * 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;
		size_t strtabidx;
		struct {
			GElf_Shdr shdr;
			Elf_Data *data;
		} *reloc;
		int nr_reloc;
		int maps_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;

	void *priv;
	bpf_object_clear_priv_t clear_priv;

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

static 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);
}

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->section_name);
	zfree(&prog->insns);
	zfree(&prog->reloc_desc);

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

static int
bpf_program__init(void *data, size_t size, char *name, int idx,
		    struct bpf_program *prog)
{
	if (size < sizeof(struct bpf_insn)) {
		pr_warning("corrupted section '%s'\n", name);
		return -EINVAL;
	}

	bzero(prog, sizeof(*prog));

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

	prog->insns = malloc(size);
	if (!prog->insns) {
		pr_warning("failed to alloc insns for %s\n", name);
		goto errout;
	}
	prog->insns_cnt = size / sizeof(struct bpf_insn);
	memcpy(prog->insns, data,
	       prog->insns_cnt * sizeof(struct bpf_insn));
	prog->idx = idx;
	prog->instances.fds = NULL;
	prog->instances.nr = -1;
	prog->type = BPF_PROG_TYPE_KPROBE;

	return 0;
errout:
	bpf_program__exit(prog);
	return -ENOMEM;
}

static int
bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
			char *name, int idx)
{
	struct bpf_program prog, *progs;
	int nr_progs, err;

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

	progs = obj->programs;
	nr_progs = obj->nr_programs;

	progs = realloc(progs, sizeof(progs[0]) * (nr_progs + 1));
	if (!progs) {
		/*
		 * In this case the original obj->programs
		 * is still valid, so don't need special treat for
		 * bpf_close_object().
		 */
		pr_warning("failed to alloc a new program '%s'\n",
			   name);
		bpf_program__exit(&prog);
		return -ENOMEM;
	}

	pr_debug("found program %s\n", prog.section_name);
	obj->programs = progs;
	obj->nr_programs = nr_progs + 1;
	prog.obj = obj;
	progs[nr_progs] = prog;
	return 0;
}

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

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

	strcpy(obj->path, path);
	obj->efile.fd = -1;

	/*
	 * Caller of this function should also calls
	 * bpf_object__elf_finish() after data collection to return
	 * obj_buf to user. If not, we should duplicate the buffer to
	 * avoid user freeing them before elf finish.
	 */
	obj->efile.obj_buf = obj_buf;
	obj->efile.obj_buf_sz = obj_buf_sz;
	obj->efile.maps_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;

	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) {
			pr_warning("failed to open %s: %s\n", obj->path,
					strerror(errno));
			return -errno;
		}

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

	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)
{
	static unsigned int const endian = 1;

	switch (obj->efile.ehdr.e_ident[EI_DATA]) {
	case ELFDATA2LSB:
		/* We are big endian, BPF obj is little endian. */
		if (*(unsigned char const *)&endian != 1)
			goto mismatch;
		break;

	case ELFDATA2MSB:
		/* We are little endian, BPF obj is big endian. */
		if (*(unsigned char const *)&endian != 0)
			goto mismatch;
		break;
	default:
		return -LIBBPF_ERRNO__ENDIAN;
	}

	return 0;

mismatch:
	pr_warning("Error: 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
bpf_object__validate_maps(struct bpf_object *obj)
{
	int i;

	/*
	 * If there's only 1 map, the only error case should have been
	 * catched in bpf_object__init_maps().
	 */
	if (!obj->maps || !obj->nr_maps || (obj->nr_maps == 1))
		return 0;

	for (i = 1; i < obj->nr_maps; i++) {
		const struct bpf_map *a = &obj->maps[i - 1];
		const struct bpf_map *b = &obj->maps[i];

		if (b->offset - a->offset < sizeof(struct bpf_map_def)) {
			pr_warning("corrupted map section in %s: map \"%s\" too small\n",
				   obj->path, a->name);
			return -EINVAL;
		}
	}
	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;

	return a->offset - b->offset;
}

static int
bpf_object__init_maps(struct bpf_object *obj)
{
	int i, map_idx, nr_maps = 0;
	Elf_Scn *scn;
	Elf_Data *data;
	Elf_Data *symbols = obj->efile.symbols;

	if (obj->efile.maps_shndx < 0)
		return -EINVAL;
	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.
	 */
	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
		GElf_Sym sym;

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

	/* Alloc obj->maps and fill nr_maps. */
	pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path,
		 nr_maps, data->d_size);

	if (!nr_maps)
		return 0;

	obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
	if (!obj->maps) {
		pr_warning("alloc maps for object failed\n");
		return -ENOMEM;
	}
	obj->nr_maps = nr_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 = 0; i < nr_maps; i++)
		obj->maps[i].fd = -1;

	/*
	 * Fill obj->maps using data in "maps" section.
	 */
	for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
		GElf_Sym sym;
		const char *map_name;
		struct bpf_map_def *def;

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

		map_name = elf_strptr(obj->efile.elf,
				      obj->efile.strtabidx,
				      sym.st_name);
		obj->maps[map_idx].offset = sym.st_value;
		if (sym.st_value + sizeof(struct bpf_map_def) > data->d_size) {
			pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
				   obj->path, map_name);
			return -EINVAL;
		}

		obj->maps[map_idx].name = strdup(map_name);
		if (!obj->maps[map_idx].name) {
			pr_warning("failed to alloc map name\n");
			return -ENOMEM;
		}
		pr_debug("map %d is \"%s\"\n", map_idx,
			 obj->maps[map_idx].name);
		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
		obj->maps[map_idx].def = *def;
		map_idx++;
	}

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

static int bpf_object__elf_collect(struct bpf_object *obj)
{
	Elf *elf = obj->efile.elf;
	GElf_Ehdr *ep = &obj->efile.ehdr;
	Elf_Scn *scn = NULL;
	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 header from %s\n",
				   obj->path);
			err = -LIBBPF_ERRNO__FORMAT;
			goto out;
		}

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

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

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

				strerror_r(-err, errmsg, sizeof(errmsg));
				pr_warning("failed to alloc program %s (%s): %s",
					   name, obj->path, errmsg);
			}
		} else if (sh.sh_type == SHT_REL) {
			void *reloc = obj->efile.reloc;
			int nr_reloc = obj->efile.nr_reloc + 1;

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

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

				obj->efile.reloc[n].shdr = sh;
				obj->efile.reloc[n].data = data;
			}
		}
		if (err)
			goto out;
	}

	if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
		pr_warning("Corrupted ELF file: index of strtab invalid\n");
		return LIBBPF_ERRNO__FORMAT;
	}
	if (obj->efile.maps_shndx >= 0)
		err = bpf_object__init_maps(obj);
out:
	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;
}

static int
bpf_program__collect_reloc(struct bpf_program *prog,
			   size_t nr_maps, GElf_Shdr *shdr,
			   Elf_Data *data, Elf_Data *symbols,
			   int maps_shndx, struct bpf_map *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++) {
		GElf_Sym sym;
		GElf_Rel rel;
		unsigned int insn_idx;
		struct bpf_insn *insns = prog->insns;
		size_t map_idx;

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

		if (sym.st_shndx != maps_shndx) {
			pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n",
				   prog->section_name, sym.st_shndx);
			return -LIBBPF_ERRNO__RELOC;
		}

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

		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;
		}

		/* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
		for (map_idx = 0; map_idx < nr_maps; map_idx++) {
			if (maps[map_idx].offset == sym.st_value) {
				pr_debug("relocation: find map %zd (%s) for insn %u\n",
					 map_idx, maps[map_idx].name, insn_idx);
				break;
			}
		}

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

		prog->reloc_desc[i].insn_idx = insn_idx;
		prog->reloc_desc[i].map_idx = map_idx;
	}
	return 0;
}

static int
bpf_object__create_maps(struct bpf_object *obj)
{
	unsigned int i;

	for (i = 0; i < obj->nr_maps; i++) {
		struct bpf_map_def *def = &obj->maps[i].def;
		int *pfd = &obj->maps[i].fd;

		*pfd = bpf_create_map(def->type,
				      def->key_size,
				      def->value_size,
				      def->max_entries,
				      0);
		if (*pfd < 0) {
			size_t j;
			int err = *pfd;

			pr_warning("failed to create map: %s\n",
				   strerror(errno));
			for (j = 0; j < i; j++)
				zclose(obj->maps[j].fd);
			return err;
		}
		pr_debug("create map %s: fd=%d\n", obj->maps[i].name, *pfd);
	}

	return 0;
}

static int
bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
{
	int i;

	if (!prog || !prog->reloc_desc)
		return 0;

	for (i = 0; i < prog->nr_reloc; i++) {
		int insn_idx, map_idx;
		struct bpf_insn *insns = prog->insns;

		insn_idx = prog->reloc_desc[i].insn_idx;
		map_idx = prog->reloc_desc[i].map_idx;

		if (insn_idx >= (int)prog->insns_cnt) {
			pr_warning("relocation out of range: '%s'\n",
				   prog->section_name);
			return -LIBBPF_ERRNO__RELOC;
		}
		insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
		insns[insn_idx].imm = obj->maps[map_idx].fd;
	}

	zfree(&prog->reloc_desc);
	prog->nr_reloc = 0;
	return 0;
}


static int
bpf_object__relocate(struct bpf_object *obj)
{
	struct bpf_program *prog;
	size_t i;
	int err;

	for (i = 0; i < obj->nr_programs; i++) {
		prog = &obj->programs[i];

		err = bpf_program__relocate(prog, obj);
		if (err) {
			pr_warning("failed to relocate '%s'\n",
				   prog->section_name);
			return err;
		}
	}
	return 0;
}

static int bpf_object__collect_reloc(struct bpf_object *obj)
{
	int i, err;

	if (!obj_elf_valid(obj)) {
		pr_warning("Internal error: elf object is closed\n");
		return -LIBBPF_ERRNO__INTERNAL;
	}

	for (i = 0; i < obj->efile.nr_reloc; i++) {
		GElf_Shdr *shdr = &obj->efile.reloc[i].shdr;
		Elf_Data *data = obj->efile.reloc[i].data;
		int idx = shdr->sh_info;
		struct bpf_program *prog;
		size_t nr_maps = obj->nr_maps;

		if (shdr->sh_type != SHT_REL) {
			pr_warning("internal error at %d\n", __LINE__);
			return -LIBBPF_ERRNO__INTERNAL;
		}

		prog = bpf_object__find_prog_by_idx(obj, idx);
		if (!prog) {
			pr_warning("relocation failed: no %d section\n",
				   idx);
			return -LIBBPF_ERRNO__RELOC;
		}

		err = bpf_program__collect_reloc(prog, nr_maps,
						 shdr, data,
						 obj->efile.symbols,
						 obj->efile.maps_shndx,
						 obj->maps);
		if (err)
			return err;
	}
	return 0;
}

static int
load_program(enum bpf_prog_type type, struct bpf_insn *insns,
	     int insns_cnt, char *license, u32 kern_version, int *pfd)
{
	int ret;
	char *log_buf;

	if (!insns || !insns_cnt)
		return -EINVAL;

	log_buf = malloc(BPF_LOG_BUF_SIZE);
	if (!log_buf)
		pr_warning("Alloc log buffer for bpf loader error, continue without log\n");

	ret = bpf_load_program(type, insns, insns_cnt, license,
			       kern_version, log_buf, BPF_LOG_BUF_SIZE);

	if (ret >= 0) {
		*pfd = ret;
		ret = 0;
		goto out;
	}

	ret = -LIBBPF_ERRNO__LOAD;
	pr_warning("load bpf program failed: %s\n", strerror(errno));

	if (log_buf && log_buf[0] != '\0') {
		ret = -LIBBPF_ERRNO__VERIFY;
		pr_warning("-- BEGIN DUMP LOG ---\n");
		pr_warning("\n%s\n", log_buf);
		pr_warning("-- END LOG --\n");
	} else if (insns_cnt >= BPF_MAXINSNS) {
		pr_warning("Program too large (%d insns), at most %d insns\n",
			   insns_cnt, BPF_MAXINSNS);
		ret = -LIBBPF_ERRNO__PROG2BIG;
	} else {
		/* Wrong program type? */
		if (type != BPF_PROG_TYPE_KPROBE) {
			int fd;

			fd = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
					      insns_cnt, license, kern_version,
					      NULL, 0);
			if (fd >= 0) {
				close(fd);
				ret = -LIBBPF_ERRNO__PROGTYPE;
				goto out;
			}
		}

		if (log_buf)
			ret = -LIBBPF_ERRNO__KVER;
	}

out:
	free(log_buf);
	return ret;
}

static int
bpf_program__load(struct bpf_program *prog,
		  char *license, u32 kern_version)
{
	int err = 0, fd, i;

	if (prog->instances.nr < 0 || !prog->instances.fds) {
		if (prog->preprocessor) {
			pr_warning("Internal error: can't load program '%s'\n",
				   prog->section_name);
			return -LIBBPF_ERRNO__INTERNAL;
		}

		prog->instances.fds = malloc(sizeof(int));
		if (!prog->instances.fds) {
			pr_warning("Not enough memory for BPF fds\n");
			return -ENOMEM;
		}
		prog->instances.nr = 1;
		prog->instances.fds[0] = -1;
	}

	if (!prog->preprocessor) {
		if (prog->instances.nr != 1) {
			pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
				   prog->section_name, prog->instances.nr);
		}
		err = load_program(prog->type, prog->insns, prog->insns_cnt,
				   license, kern_version, &fd);
		if (!err)
			prog->instances.fds[0] = fd;
		goto out;
	}

	for (i = 0; i < prog->instances.nr; i++) {
		struct bpf_prog_prep_result result;
		bpf_program_prep_t preprocessor = prog->preprocessor;

		bzero(&result, sizeof(result));
		err = preprocessor(prog, i, prog->insns,
				   prog->insns_cnt, &result);
		if (err) {
			pr_warning("Preprocessing the %dth instance of program '%s' failed\n",
				   i, prog->section_name);
			goto out;
		}

		if (!result.new_insn_ptr || !result.new_insn_cnt) {
			pr_debug("Skip loading the %dth instance of program '%s'\n",
				 i, prog->section_name);
			prog->instances.fds[i] = -1;
			if (result.pfd)
				*result.pfd = -1;
			continue;
		}

		err = load_program(prog->type, result.new_insn_ptr,
				   result.new_insn_cnt,
				   license, kern_version, &fd);

		if (err) {
			pr_warning("Loading the %dth instance of program '%s' failed\n",
					i, prog->section_name);
			goto out;
		}

		if (result.pfd)
			*result.pfd = fd;
		prog->instances.fds[i] = fd;
	}
out:
	if (err)
		pr_warning("failed to load program '%s'\n",
			   prog->section_name);
	zfree(&prog->insns);
	prog->insns_cnt = 0;
	return err;
}

static int
bpf_object__load_progs(struct bpf_object *obj)
{
	size_t i;
	int err;

	for (i = 0; i < obj->nr_programs; i++) {
		err = bpf_program__load(&obj->programs[i],
					obj->license,
					obj->kern_version);
		if (err)
			return err;
	}
	return 0;
}

static int bpf_object__validate(struct bpf_object *obj)
{
	if (obj->kern_version == 0) {
		pr_warning("%s doesn't provide kernel version\n",
			   obj->path);
		return -LIBBPF_ERRNO__KVERSION;
	}
	return 0;
}

static struct bpf_object *
__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz)
{
	struct bpf_object *obj;
	int err;

	if (elf_version(EV_CURRENT) == EV_NONE) {
		pr_warning("failed to init libelf for %s\n", path);
		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
	}

	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
	if (IS_ERR(obj))
		return obj;

	CHECK_ERR(bpf_object__elf_init(obj), err, out);
	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
	CHECK_ERR(bpf_object__elf_collect(obj), err, out);
	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
	CHECK_ERR(bpf_object__validate(obj), err, out);

	bpf_object__elf_finish(obj);
	return obj;
out:
	bpf_object__close(obj);
	return ERR_PTR(err);
}

struct bpf_object *bpf_object__open(const char *path)
{
	/* param validation */
	if (!path)
		return NULL;

	pr_debug("loading %s\n", path);

	return __bpf_object__open(path, NULL, 0);
}

struct bpf_object *bpf_object__open_buffer(void *obj_buf,
					   size_t obj_buf_sz,
					   const char *name)
{
	char tmp_name[64];

	/* param validation */
	if (!obj_buf || obj_buf_sz <= 0)
		return NULL;

	if (!name) {
		snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
			 (unsigned long)obj_buf,
			 (unsigned long)obj_buf_sz);
		tmp_name[sizeof(tmp_name) - 1] = '\0';
		name = tmp_name;
	}
	pr_debug("loading object '%s' from buffer\n",
		 name);

	return __bpf_object__open(name, obj_buf, obj_buf_sz);
}

int bpf_object__unload(struct bpf_object *obj)
{
	size_t i;

	if (!obj)
		return -EINVAL;

	for (i = 0; i < obj->nr_maps; i++)
		zclose(obj->maps[i].fd);

	for (i = 0; i < obj->nr_programs; i++)
		bpf_program__unload(&obj->programs[i]);

	return 0;
}

int bpf_object__load(struct bpf_object *obj)
{
	int err;

	if (!obj)
		return -EINVAL;

	if (obj->loaded) {
		pr_warning("object should not be loaded twice\n");
		return -EINVAL;
	}

	obj->loaded = true;

	CHECK_ERR(bpf_object__create_maps(obj), err, out);
	CHECK_ERR(bpf_object__relocate(obj), err, out);
	CHECK_ERR(bpf_object__load_progs(obj), err, out);

	return 0;
out:
	bpf_object__unload(obj);
	pr_warning("failed to load object '%s'\n", obj->path);
	return err;
}

static int check_path(const char *path)
{
	struct statfs st_fs;
	char *dname, *dir;
	int err = 0;

	if (path == NULL)
		return -EINVAL;

	dname = strdup(path);
	if (dname == NULL)
		return -ENOMEM;

	dir = dirname(dname);
	if (statfs(dir, &st_fs)) {
		pr_warning("failed to statfs %s: %s\n", dir, strerror(errno));
		err = -errno;
	}
	free(dname);

	if (!err && st_fs.f_type != BPF_FS_MAGIC) {
		pr_warning("specified path %s is not on BPF FS\n", path);
		err = -EINVAL;
	}

	return err;
}

int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
			      int instance)
{
	int err;

	err = check_path(path);
	if (err)
		return err;

	if (prog == NULL) {
		pr_warning("invalid program pointer\n");
		return -EINVAL;
	}

	if (instance < 0 || instance >= prog->instances.nr) {
		pr_warning("invalid prog instance %d of prog %s (max %d)\n",
			   instance, prog->section_name, prog->instances.nr);
		return -EINVAL;
	}

	if (bpf_obj_pin(prog->instances.fds[instance], path)) {
		pr_warning("failed to pin program: %s\n", strerror(errno));
		return -errno;
	}
	pr_debug("pinned program '%s'\n", path);

	return 0;
}

static int make_dir(const char *path)
{
	int err = 0;

	if (mkdir(path, 0700) && errno != EEXIST)
		err = -errno;

	if (err)
		pr_warning("failed to mkdir %s: %s\n", path, strerror(-err));
	return err;
}

int bpf_program__pin(struct bpf_program *prog, const char *path)
{
	int i, err;

	err = check_path(path);
	if (err)
		return err;

	if (prog == NULL) {
		pr_warning("invalid program pointer\n");
		return -EINVAL;
	}

	if (prog->instances.nr <= 0) {
		pr_warning("no instances of prog %s to pin\n",
			   prog->section_name);
		return -EINVAL;
	}

	err = make_dir(path);
	if (err)
		return err;

	for (i = 0; i < prog->instances.nr; i++) {
		char buf[PATH_MAX];
		int len;

		len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
		if (len < 0)
			return -EINVAL;
		else if (len >= PATH_MAX)
			return -ENAMETOOLONG;

		err = bpf_program__pin_instance(prog, buf, i);
		if (err)
			return err;
	}

	return 0;
}

int bpf_map__pin(struct bpf_map *map, const char *path)
{
	int err;

	err = check_path(path);
	if (err)
		return err;

	if (map == NULL) {
		pr_warning("invalid map pointer\n");
		return -EINVAL;
	}

	if (bpf_obj_pin(map->fd, path)) {
		pr_warning("failed to pin map: %s\n", strerror(errno));
		return -errno;
	}

	pr_debug("pinned map '%s'\n", path);
	return 0;
}

int bpf_object__pin(struct bpf_object *obj, const char *path)
{
	struct bpf_program *prog;
	struct bpf_map *map;
	int err;

	if (!obj)
		return -ENOENT;

	if (!obj->loaded) {
		pr_warning("object not yet loaded; load it first\n");
		return -ENOENT;
	}

	err = make_dir(path);
	if (err)
		return err;

	bpf_map__for_each(map, obj) {
		char buf[PATH_MAX];
		int len;

		len = snprintf(buf, PATH_MAX, "%s/%s", path,
			       bpf_map__name(map));
		if (len < 0)
			return -EINVAL;
		else if (len >= PATH_MAX)
			return -ENAMETOOLONG;

		err = bpf_map__pin(map, buf);
		if (err)
			return err;
	}

	bpf_object__for_each_program(prog, obj) {
		char buf[PATH_MAX];
		int len;

		len = snprintf(buf, PATH_MAX, "%s/%s", path,
			       prog->section_name);
		if (len < 0)
			return -EINVAL;
		else if (len >= PATH_MAX)
			return -ENAMETOOLONG;

		err = bpf_program__pin(prog, buf);
		if (err)
			return err;
	}

	return 0;
}

void bpf_object__close(struct bpf_object *obj)
{
	size_t i;

	if (!obj)
		return;

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

	bpf_object__elf_finish(obj);
	bpf_object__unload(obj);

	for (i = 0; i < obj->nr_maps; i++) {
		zfree(&obj->maps[i].name);
		if (obj->maps[i].clear_priv)
			obj->maps[i].clear_priv(&obj->maps[i],
						obj->maps[i].priv);
		obj->maps[i].priv = NULL;
		obj->maps[i].clear_priv = NULL;
	}
	zfree(&obj->maps);
	obj->nr_maps = 0;

	if (obj->programs && obj->nr_programs) {
		for (i = 0; i < obj->nr_programs; i++)
			bpf_program__exit(&obj->programs[i]);
	}
	zfree(&obj->programs);

	list_del(&obj->list);
	free(obj);
}

struct bpf_object *
bpf_object__next(struct bpf_object *prev)
{
	struct bpf_object *next;

	if (!prev)
		next = list_first_entry(&bpf_objects_list,
					struct bpf_object,
					list);
	else
		next = list_next_entry(prev, list);

	/* Empty list is noticed here so don't need checking on entry. */
	if (&next->list == &bpf_objects_list)
		return NULL;

	return next;
}

const char *bpf_object__name(struct bpf_object *obj)
{
	return obj ? obj->path : ERR_PTR(-EINVAL);
}

unsigned int bpf_object__kversion(struct bpf_object *obj)
{
	return obj ? obj->kern_version : 0;
}

int bpf_object__set_priv(struct bpf_object *obj, void *priv,
			 bpf_object_clear_priv_t clear_priv)
{
	if (obj->priv && obj->clear_priv)
		obj->clear_priv(obj, obj->priv);

	obj->priv = priv;
	obj->clear_priv = clear_priv;
	return 0;
}

void *bpf_object__priv(struct bpf_object *obj)
{
	return obj ? obj->priv : ERR_PTR(-EINVAL);
}

struct bpf_program *
bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
{
	size_t idx;

	if (!obj->programs)
		return NULL;
	/* First handler */
	if (prev == NULL)
		return &obj->programs[0];

	if (prev->obj != obj) {
		pr_warning("error: program handler doesn't match object\n");
		return NULL;
	}

	idx = (prev - obj->programs) + 1;
	if (idx >= obj->nr_programs)
		return NULL;
	return &obj->programs[idx];
}

int bpf_program__set_priv(struct bpf_program *prog, void *priv,
			  bpf_program_clear_priv_t clear_priv)
{
	if (prog->priv && prog->clear_priv)
		prog->clear_priv(prog, prog->priv);

	prog->priv = priv;
	prog->clear_priv = clear_priv;
	return 0;
}

void *bpf_program__priv(struct bpf_program *prog)
{
	return prog ? prog->priv : ERR_PTR(-EINVAL);
}

const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
{
	const char *title;

	title = prog->section_name;
	if (needs_copy) {
		title = strdup(title);
		if (!title) {
			pr_warning("failed to strdup program title\n");
			return ERR_PTR(-ENOMEM);
		}
	}

	return title;
}

int bpf_program__fd(struct bpf_program *prog)
{
	return bpf_program__nth_fd(prog, 0);
}

int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
			  bpf_program_prep_t prep)
{
	int *instances_fds;

	if (nr_instances <= 0 || !prep)
		return -EINVAL;

	if (prog->instances.nr > 0 || prog->instances.fds) {
		pr_warning("Can't set pre-processor after loading\n");
		return -EINVAL;
	}

	instances_fds = malloc(sizeof(int) * nr_instances);
	if (!instances_fds) {
		pr_warning("alloc memory failed for fds\n");
		return -ENOMEM;
	}

	/* fill all fd with -1 */
	memset(instances_fds, -1, sizeof(int) * nr_instances);

	prog->instances.nr = nr_instances;
	prog->instances.fds = instances_fds;
	prog->preprocessor = prep;
	return 0;
}

int bpf_program__nth_fd(struct bpf_program *prog, int n)
{
	int fd;

	if (n >= prog->instances.nr || n < 0) {
		pr_warning("Can't get the %dth fd from program %s: only %d instances\n",
			   n, prog->section_name, prog->instances.nr);
		return -EINVAL;
	}

	fd = prog->instances.fds[n];
	if (fd < 0) {
		pr_warning("%dth instance of program '%s' is invalid\n",
			   n, prog->section_name);
		return -ENOENT;
	}

	return fd;
}

static void bpf_program__set_type(struct bpf_program *prog,
				  enum bpf_prog_type type)
{
	prog->type = type;
}

static bool bpf_program__is_type(struct bpf_program *prog,
				 enum bpf_prog_type type)
{
	return prog ? (prog->type == type) : false;
}

#define BPF_PROG_TYPE_FNS(NAME, TYPE)			\
int bpf_program__set_##NAME(struct bpf_program *prog)	\
{							\
	if (!prog)					\
		return -EINVAL;				\
	bpf_program__set_type(prog, TYPE);		\
	return 0;					\
}							\
							\
bool bpf_program__is_##NAME(struct bpf_program *prog)	\
{							\
	return bpf_program__is_type(prog, TYPE);	\
}							\

BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);

int bpf_map__fd(struct bpf_map *map)
{
	return map ? map->fd : -EINVAL;
}

const struct bpf_map_def *bpf_map__def(struct bpf_map *map)
{
	return map ? &map->def : ERR_PTR(-EINVAL);
}

const char *bpf_map__name(struct bpf_map *map)
{
	return map ? map->name : NULL;
}

int bpf_map__set_priv(struct bpf_map *map, void *priv,
		     bpf_map_clear_priv_t clear_priv)
{
	if (!map)
		return -EINVAL;

	if (map->priv) {
		if (map->clear_priv)
			map->clear_priv(map, map->priv);
	}

	map->priv = priv;
	map->clear_priv = clear_priv;
	return 0;
}

void *bpf_map__priv(struct bpf_map *map)
{
	return map ? map->priv : ERR_PTR(-EINVAL);
}

struct bpf_map *
bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
{
	size_t idx;
	struct bpf_map *s, *e;

	if (!obj || !obj->maps)
		return NULL;

	s = obj->maps;
	e = obj->maps + obj->nr_maps;

	if (prev == NULL)
		return s;

	if ((prev < s) || (prev >= e)) {
		pr_warning("error in %s: map handler doesn't belong to object\n",
			   __func__);
		return NULL;
	}

	idx = (prev - obj->maps) + 1;
	if (idx >= obj->nr_maps)
		return NULL;
	return &obj->maps[idx];
}

struct bpf_map *
bpf_object__find_map_by_name(struct bpf_object *obj, const char *name)
{
	struct bpf_map *pos;

	bpf_map__for_each(pos, obj) {
		if (pos->name && !strcmp(pos->name, name))
			return pos;
	}
	return NULL;
}

struct bpf_map *
bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
{
	int i;

	for (i = 0; i < obj->nr_maps; i++) {
		if (obj->maps[i].offset == offset)
			return &obj->maps[i];
	}
	return ERR_PTR(-ENOENT);
}

long libbpf_get_error(const void *ptr)
{
	if (IS_ERR(ptr))
		return PTR_ERR(ptr);
	return 0;
}