path: root/scripts/kallsyms.c

/* Generate assembler source containing symbol information
 *
 * Copyright 2002       by Kai Germaschewski
 *
 * This software may be used and distributed according to the terms
 * of the GNU General Public License, incorporated herein by reference.
 *
 * Usage: kallsyms [--all-symbols] [--absolute-percpu]
 *                         [--base-relative] [--lto-clang] in.map > out.S
 *
 *      Table compression uses all the unused char codes on the symbols and
 *  maps these to the most used substrings (tokens). For instance, it might
 *  map char code 0xF7 to represent "write_" and then in every symbol where
 *  "write_" appears it can be replaced by 0xF7, saving 5 bytes.
 *      The used codes themselves are also placed in the table so that the
 *  decompresion can work without "special cases".
 *      Applied to kernel symbols, this usually produces a compression ratio
 *  of about 50%.
 *
 */

#include <errno.h>
#include <getopt.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <limits.h>

#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))

#define KSYM_NAME_LEN		512

struct sym_entry {
	unsigned long long addr;
	unsigned int len;
	unsigned int seq;
	unsigned int start_pos;
	unsigned int percpu_absolute;
	unsigned char sym[];
};

struct addr_range {
	const char *start_sym, *end_sym;
	unsigned long long start, end;
};

static unsigned long long _text;
static unsigned long long relative_base;
static struct addr_range text_ranges[] = {
	{ "_stext",     "_etext"     },
	{ "_sinittext", "_einittext" },
};
#define text_range_text     (&text_ranges[0])
#define text_range_inittext (&text_ranges[1])

static struct addr_range percpu_range = {
	"__per_cpu_start", "__per_cpu_end", -1ULL, 0
};

static struct sym_entry **table;
static unsigned int table_size, table_cnt;
static int all_symbols;
static int absolute_percpu;
static int base_relative;
static int lto_clang;

static int token_profit[0x10000];

/* the table that holds the result of the compression */
static unsigned char best_table[256][2];
static unsigned char best_table_len[256];


static void usage(void)
{
	fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] "
			"[--base-relative] [--lto-clang] in.map > out.S\n");
	exit(1);
}

static char *sym_name(const struct sym_entry *s)
{
	return (char *)s->sym + 1;
}

static bool is_ignored_symbol(const char *name, char type)
{
	if (type == 'u' || type == 'n')
		return true;

	if (toupper(type) == 'A') {
		/* Keep these useful absolute symbols */
		if (strcmp(name, "__kernel_syscall_via_break") &&
		    strcmp(name, "__kernel_syscall_via_epc") &&
		    strcmp(name, "__kernel_sigtramp") &&
		    strcmp(name, "__gp"))
			return true;
	}

	return false;
}

static void check_symbol_range(const char *sym, unsigned long long addr,
			       struct addr_range *ranges, int entries)
{
	size_t i;
	struct addr_range *ar;

	for (i = 0; i < entries; ++i) {
		ar = &ranges[i];

		if (strcmp(sym, ar->start_sym) == 0) {
			ar->start = addr;
			return;
		} else if (strcmp(sym, ar->end_sym) == 0) {
			ar->end = addr;
			return;
		}
	}
}

static struct sym_entry *read_symbol(FILE *in, char **buf, size_t *buf_len)
{
	char *name, type, *p;
	unsigned long long addr;
	size_t len;
	ssize_t readlen;
	struct sym_entry *sym;

	errno = 0;
	readlen = getline(buf, buf_len, in);
	if (readlen < 0) {
		if (errno) {
			perror("read_symbol");
			exit(EXIT_FAILURE);
		}
		return NULL;
	}

	if ((*buf)[readlen - 1] == '\n')
		(*buf)[readlen - 1] = 0;

	addr = strtoull(*buf, &p, 16);

	if (*buf == p || *p++ != ' ' || !isascii((type = *p++)) || *p++ != ' ') {
		fprintf(stderr, "line format error\n");
		exit(EXIT_FAILURE);
	}

	name = p;
	len = strlen(name);

	if (len >= KSYM_NAME_LEN) {
		fprintf(stderr, "Symbol %s too long for kallsyms (%zu >= %d).\n"
				"Please increase KSYM_NAME_LEN both in kernel and kallsyms.c\n",
			name, len, KSYM_NAME_LEN);
		return NULL;
	}

	if (strcmp(name, "_text") == 0)
		_text = addr;

	/* Ignore most absolute/undefined (?) symbols. */
	if (is_ignored_symbol(name, type))
		return NULL;

	check_symbol_range(name, addr, text_ranges, ARRAY_SIZE(text_ranges));
	check_symbol_range(name, addr,