2
     ˆÃÂ„qÿÁ¾Ä ?÷     /* 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: nm -n vmlinux | scripts/kallsyms [--all-symbols] > symbols.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 <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 _stringify_1(x)	#x
#define _stringify(x)	_stringify_1(x)

#define KSYM_NAME_LEN		512

/*
 * A substantially bigger size than the current maximum.
 *
 * It cannot be defined as an expression because it gets stringified
 * for the fscanf() format string. Therefore, a _Static_assert() is
 * used instead to maintain the relationship with KSYM_NAME_LEN.
 */
#define KSYM_NAME_LEN_BUFFER	2048
_Static_assert(
	KSYM_NAME_LEN_BUFFER == KSYM_NAME_LEN * 4,
	"Please keep KSYM_NAME_LEN_BUFFER in sync with KSYM_NAME_LEN"
);

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 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] "
			"[--base-relative] < 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)
{
	/* Symbol names that exactly match to the following are ignored.*/
	static const char * const ignored_symbols[] = {
		/*
		 * Symbols which vary between passes. Passes 1 and 2 must have
		 * identical symbol lists. The kallsyms_* symbols below are
		 * only added after pass 1, they would be included in pass 2
		 * when --all-symbols is specified so exclude them to get a
		 * stable symbol list.
		 */
		"kallsyms_addresses",
		"kallsyms_offsets",
		"kallsyms_relative_base",
		"kallsyms_num_syms",
		"kallsyms_names",
		"kallsyms_markers",
		"kallsyms_token_table",
		"kallsyms_token_index",
		"kallsyms_seqs_of_names",
		/* Exclude linker generated symbols which vary between passes */
		"_SDA_BASE_",		/* ppc */
		"_SDA2_BASE_",		/* ppc */
		NULL
	};

	/* Symbol names that begin with the following are ignored.*/
	static const char * const ignored_prefixes[] = {
		"$",			/* local symbols for ARM, MIPS, etc. */
		".LASANPC",		/* s390 kasan local symbols */
		"__crc_",		/* modversions */
		"__efistub_",		/* arm64 EFI stub namespace */
		"__kvm_nvhe_$",		/* arm64 local symbols in non-VHE KVM namespace */
		"__kvm_nvhe_.L",	/* arm64 local symbols in non-VHE KVM namespace */
		"__AArch64ADRPThunk_",	/* arm64 lld */
		"__ARMV5PILongThunk_",	/* arm lld */
		"__ARMV7PILo