[deliverable/linux.git] / 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: 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 <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>

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

#define KSYM_NAME_LEN		128

struct sym_entry {
	unsigned long long addr;
	unsigned int len;
	unsigned int start_pos;
	unsigned char *sym;
};

struct text_range {
	const char *stext, *etext;
	unsigned long long start, end;
};

static unsigned long long _text;
static struct text_range text_ranges[] = {
	{ "_stext",     "_etext"     },
	{ "_sinittext", "_einittext" },
	{ "_stext_l1",  "_etext_l1"  },	/* Blackfin on-chip L1 inst SRAM */
	{ "_stext_l2",  "_etext_l2"  },	/* Blackfin on-chip L2 SRAM */
};
#define text_range_text     (&text_ranges[0])
#define text_range_inittext (&text_ranges[1])

static struct sym_entry *table;
static unsigned int table_size, table_cnt;
static int all_symbols = 0;
static char symbol_prefix_char = '\0';
static unsigned long long kernel_start_addr = 0;

int token_profit[0x10000];

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


static void usage(void)
{
	fprintf(stderr, "Usage: kallsyms [--all-symbols] "
			"[--symbol-prefix=<prefix char>] "
			"[--page-offset=<CONFIG_PAGE_OFFSET>] "
			"< in.map > out.S\n");
	exit(1);
}

/*
 * This ignores the intensely annoying "mapping symbols" found
 * in ARM ELF files: $a, $t and $d.
 */
static inline int is_arm_mapping_symbol(const char *str)
{
	return str[0] == '$' && strchr("atd", str[1])
	       && (str[2] == '\0' || str[2] == '.');
}

static int read_symbol_tr(const char *sym, unsigned long long addr)
{
	size_t i;
	struct text_range *tr;

	for (i = 0; i < ARRAY_SIZE(text_ranges); ++i) {
		tr = &text_ranges[i];

		if (strcmp(sym, tr->stext) == 0) {
			tr->start = addr;
			return 0;
		} else if (strcmp(sym, tr->etext) == 0) {
			tr->end = addr;
			return 0;
		}
	}

	return 1;
}

static int read_symbol(FILE *in, struct sym_entry *s)
{
	char str[500];
	char *sym, stype;
	int rc;

	rc = fscanf(in, "%llx %c %499s\n", &s->addr, &stype, str);
	if (rc != 3) {
		if (rc != EOF && fgets(str, 500, in) == NULL)
			fprintf(stderr, "Read error or end of file.\n");
		return -1;
	}

	sym = str;
	/* skip prefix char */
	if (symbol_prefix_char && str[0] == symbol_prefix_char)
		sym++;

	/* Ignore most absolute/undefined (?) symbols. */
	if (strcmp(sym, "_text") == 0)
		_text = s->addr;
	else if (read_symbol_tr(sym, s->addr) == 0)
		/* nothing to do */;
	else if (toupper(stype) == 'A')
	{
		/* Keep these useful absolute symbols */
		if (strcmp(sym, "__kernel_syscall_via_break") &&
		    strcmp(sym, "__kernel_syscall_via_epc") &&
		    strcmp(sym, "__kernel_sigtramp") &&
		    strcmp(sym, "__gp"))
			return -1;

	}
	else if (toupper(stype) == 'U' ||
		 is_arm_mapping_symbol(sym))
		return -1;
	/* exclude also MIPS ELF local symbols ($L123 instead of .L123) */
	else if (str[0] == '$')
		return -1;
	/* exclude debugging symbols */
	else if (stype == 'N')
		return -1;

	/* include the type field in the symbol name, so that it gets
	 * compressed together */
	s->len = strlen(str) + 1;
	s->sym = malloc(s->len + 1);
	if (!s->sym) {
		fprintf(stderr, "kallsyms failure: "
			"unable to allocate required amount of memory\n");
		exit(EXIT_FAILURE);
	}
	strcpy((char *)s->sym + 1, str);
	s->sym[0] = stype;

	return 0;
}

static int symbol_valid_tr(struct sym_entry *s)
{
	size_t i;
	struct text_range *tr;

	for (i = 0; i < ARRAY_SIZE(text_ranges); ++i) {
		tr = &text_ranges[i];

		if (s->addr >= tr->start && s->addr <= tr->end)
			return 1;
	}

	return 0;
}

static int symbol_valid(struct sym_entry *s)
{
	/* 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.
	 */
	static char *special_symbols[] = {
		"kallsyms_addresses",
		"kallsyms_num_syms",
		"kallsyms_names",
		"kallsyms_markers",
		"kallsyms_token_table",
		"kallsyms_token_index",

	/* Exclude linker generated symbols which vary between passes */
		"_SDA_BASE_",		/* ppc */
		"_SDA2_BASE_",		/* ppc */
		NULL };
	int i;
	int offset = 1;

	if (s->addr < kernel_start_addr)
		return 0;

	/* skip prefix char */
	if (symbol_prefix_char && *(s->sym + 1) == symbol_prefix_char)
		offset++;

	/* if --all-symbols is not specified, then symbols outside the text
	 * and inittext sections are discarded */
	if (!all_symbols) {
		if (symbol_valid_tr(s) == 0)
			return 0;
		/* Corner case.  Discard any symbols with the same value as
		 * _etext _einittext; they can move between pass 1 and 2 when
		 * the kallsyms data are added.  If these symbols move then
		 * they may get dropped in pass 2, which breaks the kallsyms
		 * rules.
		 */
		if ((s->addr == text_range_text->end &&
				strcmp((char *)s->sym + offset, text_range_text->etext)) ||
		    (s->addr == text_range_inittext->end &&
				strcmp((char *)s->sym + offset, text_range_inittext->etext)))
			return 0;
	}

	/* Exclude symbols which vary between passes. */
	if (strstr((char *)s->sym + offset, "_compiled."))
		return 0;

	for (i = 0; special_symbols[i]; i++)
		if( strcmp((char *)s->sym + offset, special_symbols[i]) == 0 )
			return 0;

	return 1;
}

static void read_map(FILE *in)
{
	while (!feof(in)) {
		if (table_cnt >= table_size) {
			table_size += 10000;
			table = realloc(table, sizeof(*table) * table_size);
			if (!table) {
				fprintf(stderr, "out of memory\n");
				exit (1);
			}
		}
		if (read_symbol(in, &table[table_cnt]) == 0) {
			table[table_cnt].start_pos = table_cnt;
			table_cnt++;
		}
	}
}

static void output_label(char *label)
{
	if (symbol_prefix_char)
		printf(".globl %c%s\n", symbol_prefix_char, label);
	else
		printf(".globl %s\n", label);
	printf("\tALGN\n");
	if (symbol_prefix_char)
		printf("%c%s:\n", symbol_prefix_char, label);
	else
		printf("%s:\n", label);
}

/* uncompress a compressed symbol. When this function is called, the best table
 * might still be compressed itself, so the function needs to be recursive */
static int expand_symbol(unsigned char *data, int len, char *result)
{
	int c, rlen, total=0;

	while (len) {
		c = *data;
		/* if the table holds a single char that is the same as the one
		 * we are looking for, then end the search */
		if (best_table[c][0]==c && best_table_len[c]==1) {
			*result++ = c;
			total++;
		} else {
			/* if not, recurse and expand */
			rlen = expand_symbol(best_table[c], best_table_len[c], result);
			total += rlen;
			result += rlen;
		}
		data++;
		len--;
	}
	*result=0;

	return total;
}

static void write_src(void)
{
	unsigned int i, k, off;
	unsigned int best_idx[256];
	unsigned int *markers;
	char buf[KSYM_NAME_LEN];

	printf("#include <asm/types.h>\n");
	printf("#if BITS_PER_LONG == 64\n");
	printf("#define PTR .quad\n");
	printf("#define ALGN .align 8\n");
	printf("#else\n");
	printf("#define PTR .long\n");
	printf("#define ALGN .align 4\n");
	printf("#endif\n");

	printf("\t.section .rodata, \"a\"\n");

	/* Provide proper symbols relocatability by their '_text'
	 * relativeness.  The symbol names cannot be used to construct
	 * normal symbol references as the list of symbols contains
	 * symbols that are declared static and are private to their
	 * .o files.  This prevents .tmp_kallsyms.o or any other
	 * object from referencing them.
	 */
	output_label("kallsyms_addresses");
	for (i = 0; i < table_cnt; i++) {
		if (toupper(table[i].sym[0]) != 'A') {
			if (_text <= table[i].addr)
				printf("\tPTR\t_text + %#llx\n",
					table[i].addr - _text);
			else
				printf("\tPTR\t_text - %#llx\n",
					_text - table[i].addr);
		} else {
			printf("\tPTR\t%#llx\n", table[i].addr);
		}
	}
	printf("\n");

	output_label("kallsyms_num_syms");
	printf("\tPTR\t%d\n", table_cnt);
	printf("\n");

	/* table of offset markers, that give the offset in the compressed stream
	 * every 256 symbols */
	markers = malloc(sizeof(unsigned int) * ((table_cnt + 255) / 256));
	if (!markers) {
		fprintf(stderr, "kallsyms failure: "
			"unable to allocate required memory\n");
		exit(EXIT_FAILURE);
	}

	output_label("kallsyms_names");
	off = 0;
	for (i = 0; i < table_cnt; i++) {
		if ((i & 0xFF) == 0)
			markers[i >> 8] = off;

		printf("\t.byte 0x%02x", table[i].len);
		for (k = 0; k < table[i].len; k++)
			printf(", 0x%02x", table[i].sym[k]);
		printf("\n");

		off += table[i].len + 1;
	}
	printf("\n");

	output_label("kallsyms_markers");
	for (i = 0; i < ((table_cnt + 255) >> 8); i++)
		printf("\tPTR\t%d\n", markers[i]);
	printf("\n");

	free(markers);

	output_label("kallsyms_token_table");
	off = 0;
	for (i = 0; i < 256; i++) {
		best_idx[i] = off;
		expand_symbol(best_table[i], best_table_len[i], buf);
		printf("\t.asciz\t\"%s\"\n", buf);
		off += strlen(buf) + 1;
	}
	printf("\n");

	output_label("kallsyms_token_index");
	for (i = 0; i < 256; i++)
		printf("\t.short\t%d\n", best_idx[i]);
	printf("\n");
}


/* table lookup compression functions */

/* count all the possible tokens in a symbol */
static void learn_symbol(unsigned char *symbol, int len)
{
	int i;

	for (i = 0; i < len - 1; i++)
		token_profit[ symbol[i] + (symbol[i + 1] << 8) ]++;
}

/* decrease the count for all the possible tokens in a symbol */
static void forget_symbol(unsigned char *symbol, int len)
{
	int i;

	for (i = 0; i < len - 1; i++)
		token_profit[ symbol[i] + (symbol[i + 1] << 8) ]--;
}

/* remove all the invalid symbols from the table and do the initial token count */
static void build_initial_tok_table(void)
{
	unsigned int i, pos;

	pos = 0;
	for (i = 0; i < table_cnt; i++) {
		if ( symbol_valid(&table[i]) ) {
			if (pos != i)
				table[pos] = table[i];
			learn_symbol(table[pos].sym, table[pos].len);
			pos++;
		}
	}
	table_cnt = pos;
}

static void *find_token(unsigned char *str, int len, unsigned char *token)
{
	int i;

	for (i = 0; i < len - 1; i++) {
		if (str[i] == token[0] && str[i+1] == token[1])
			return &str[i];
	}
	return NULL;
}

/* replace a given token in all the valid symbols. Use the sampled symbols
 * to update the counts */
static void compress_symbols(unsigned char *str, int idx)
{
	unsigned int i, len, size;
	unsigned char *p1, *p2;

	for (i = 0; i < table_cnt; i++) {

		len = table[i].len;
		p1 = table[i].sym;

		/* find the token on the symbol */
		p2 = find_token(p1, len, str);
		if (!p2) continue;

		/* decrease the counts for this symbol's tokens */
		forget_symbol(table[i].sym, len);

		size = len;

		do {
			*p2 = idx;
			p2++;
			size -= (p2 - p1);
			memmove(p2, p2 + 1, size);
			p1 = p2;
			len--;

			if (size < 2) break;

			/* find the token on the symbol */
			p2 = find_token(p1, size, str);

		} while (p2);

		table[i].len = len;

		/* increase the counts for this symbol's new tokens */
		learn_symbol(table[i].sym, len);
	}
}

/* search the token with the maximum profit */
static int find_best_token(void)
{
	int i, best, bestprofit;

	bestprofit=-10000;
	best = 0;

	for (i = 0; i < 0x10000; i++) {
		if (token_profit[i] > bestprofit) {
			best = i;
			bestprofit = token_profit[i];
		}
	}
	return best;
}

/* this is the core of the algorithm: calculate the "best" table */
static void optimize_result(void)
{
	int i, best;

	/* using the '\0' symbol last allows compress_symbols to use standard
	 * fast string functions */
	for (i = 255; i >= 0; i--) {

		/* if this table slot is empty (it is not used by an actual
		 * original char code */
		if (!best_table_len[i]) {

			/* find the token with the breates profit value */
			best = find_best_token();
			if (token_profit[best] == 0)
				break;

			/* place it in the "best" table */
			best_table_len[i] = 2;
			best_table[i][0] = best & 0xFF;
			best_table[i][1] = (best >> 8) & 0xFF;

			/* replace this token in all the valid symbols */
			compress_symbols(best_table[i], i);
		}
	}
}

/* start by placing the symbols that are actually used on the table */
static void insert_real_symbols_in_table(void)
{
	unsigned int i, j, c;

	memset(best_table, 0, sizeof(best_table));
	memset(best_table_len, 0, sizeof(best_table_len));

	for (i = 0; i < table_cnt; i++) {
		for (j = 0; j < table[i].len; j++) {
			c = table[i].sym[j];
			best_table[c][0]=c;
			best_table_len[c]=1;
		}
	}
}

static void optimize_token_table(void)
{
	build_initial_tok_table();

	insert_real_symbols_in_table();

	/* When valid symbol is not registered, exit to error */
	if (!table_cnt) {
		fprintf(stderr, "No valid symbol.\n");
		exit(1);
	}

	optimize_result();
}

/* guess for "linker script provide" symbol */
static int may_be_linker_script_provide_symbol(const struct sym_entry *se)
{
	const char *symbol = (char *)se->sym + 1;
	int len = se->len - 1;

	if (len < 8)
		return 0;

	if (symbol[0] != '_' || symbol[1] != '_')
		return 0;

	/* __start_XXXXX */
	if (!memcmp(symbol + 2, "start_", 6))
		return 1;

	/* __stop_XXXXX */
	if (!memcmp(symbol + 2, "stop_", 5))
		return 1;

	/* __end_XXXXX */
	if (!memcmp(symbol + 2, "end_", 4))
		return 1;

	/* __XXXXX_start */
	if (!memcmp(symbol + len - 6, "_start", 6))
		return 1;

	/* __XXXXX_end */
	if (!memcmp(symbol + len - 4, "_end", 4))
		return 1;

	return 0;
}

static int prefix_underscores_count(const char *str)
{
	const char *tail = str;

	while (*tail == '_')
		tail++;

	return tail - str;
}

static int compare_symbols(const void *a, const void *b)
{
	const struct sym_entry *sa;
	const struct sym_entry *sb;
	int wa, wb;

	sa = a;
	sb = b;

	/* sort by address first */
	if (sa->addr > sb->addr)
		return 1;
	if (sa->addr < sb->addr)
		return -1;

	/* sort by "weakness" type */
	wa = (sa->sym[0] == 'w') || (sa->sym[0] == 'W');
	wb = (sb->sym[0] == 'w') || (sb->sym[0] == 'W');
	if (wa != wb)
		return wa - wb;

	/* sort by "linker script provide" type */
	wa = may_be_linker_script_provide_symbol(sa);
	wb = may_be_linker_script_provide_symbol(sb);
	if (wa != wb)
		return wa - wb;

	/* sort by the number of prefix underscores */
	wa = prefix_underscores_count((const char *)sa->sym + 1);
	wb = prefix_underscores_count((const char *)sb->sym + 1);
	if (wa != wb)
		return wa - wb;

	/* sort by initial order, so that other symbols are left undisturbed */
	return sa->start_pos - sb->start_pos;
}

static void sort_symbols(void)
{
	qsort(table, table_cnt, sizeof(struct sym_entry), compare_symbols);
}

int main(int argc, char **argv)
{
	if (argc >= 2) {
		int i;
		for (i = 1; i < argc; i++) {
			if(strcmp(argv[i], "--all-symbols") == 0)
				all_symbols = 1;
			else if (strncmp(argv[i], "--symbol-prefix=", 16) == 0) {
				char *p = &argv[i][16];
				/* skip quote */
				if ((*p == '"' && *(p+2) == '"') || (*p == '\'' && *(p+2) == '\''))
					p++;
				symbol_prefix_char = *p;
			} else if (strncmp(argv[i], "--page-offset=", 14) == 0) {
				const char *p = &argv[i][14];
				kernel_start_addr = strtoull(p, NULL, 16);
			} else
				usage();
		}
	} else if (argc != 1)
		usage();

	read_map(stdin);
	sort_symbols();
	optimize_token_table();
	write_src();

	return 0;
}
Commit	Line	Data
1da177e4 LT	1	/* Generate assembler source containing symbol information
	2	*
	3	* Copyright 2002 by Kai Germaschewski
	4	*
	5	* This software may be used and distributed according to the terms
	6	* of the GNU General Public License, incorporated herein by reference.
	7	*
	8	* Usage: nm -n vmlinux \| scripts/kallsyms [--all-symbols] > symbols.S
	9	*
1da177e4 LT	10	* Table compression uses all the unused char codes on the symbols and
	11	* maps these to the most used substrings (tokens). For instance, it might
	12	* map char code 0xF7 to represent "write_" and then in every symbol where
	13	* "write_" appears it can be replaced by 0xF7, saving 5 bytes.
	14	* The used codes themselves are also placed in the table so that the
	15	* decompresion can work without "special cases".
	16	* Applied to kernel symbols, this usually produces a compression ratio
	17	* of about 50%.
	18	*
	19	*/
	20
	21	#include <stdio.h>
	22	#include <stdlib.h>
	23	#include <string.h>
	24	#include <ctype.h>
	25
17b1f0de MF	26	#ifndef ARRAY_SIZE
	27	#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
	28	#endif
	29
9281acea	30	#define KSYM_NAME_LEN 128
1da177e4	31
1da177e4 LT	32	struct sym_entry {
1da177e4 LT	33	unsigned long long addr;
b3dbb4ec	34	unsigned int len;
f2df3f65	35	unsigned int start_pos;
1da177e4 LT	36	unsigned char *sym;
	37	};
	38
17b1f0de MF	39	struct text_range {
	40	const char stext, etext;
	41	unsigned long long start, end;
	42	};
	43
	44	static unsigned long long _text;
	45	static struct text_range text_ranges[] = {
	46	{ "_stext", "_etext" },
	47	{ "_sinittext", "_einittext" },
	48	{ "_stext_l1", "_etext_l1" }, /* Blackfin on-chip L1 inst SRAM */
	49	{ "_stext_l2", "_etext_l2" }, /* Blackfin on-chip L2 SRAM */
	50	};
	51	#define text_range_text (&text_ranges[0])
	52	#define text_range_inittext (&text_ranges[1])
	53
1da177e4	54	static struct sym_entry *table;
b3dbb4ec	55	static unsigned int table_size, table_cnt;
1da177e4	56	static int all_symbols = 0;
41f11a4f	57	static char symbol_prefix_char = '\0';
f6537f2f	58	static unsigned long long kernel_start_addr = 0;
1da177e4	59
b3dbb4ec	60	int token_profit[0x10000];
1da177e4 LT	61
1da177e4 LT	62	/* the table that holds the result of the compression */
b3dbb4ec	63	unsigned char best_table[256][2];
1da177e4 LT	64	unsigned char best_table_len[256];
	65
	66
b3dbb4ec	67	static void usage(void)
1da177e4	68	{
f6537f2f ML	69	fprintf(stderr, "Usage: kallsyms [--all-symbols] "
	70	"[--symbol-prefix=<prefix char>] "
	71	"[--page-offset=<CONFIG_PAGE_OFFSET>] "
	72	"< in.map > out.S\n");
1da177e4 LT	73	exit(1);
	74	}
	75
	76	/*
	77	* This ignores the intensely annoying "mapping symbols" found
	78	* in ARM ELF files: $a, $t and $d.
	79	*/
b3dbb4ec	80	static inline int is_arm_mapping_symbol(const char *str)
1da177e4 LT	81	{
	82	return str[0] == '$' && strchr("atd", str[1])
	83	&& (str[2] == '\0' \|\| str[2] == '.');
	84	}
	85
17b1f0de MF	86	static int read_symbol_tr(const char *sym, unsigned long long addr)
	87	{
	88	size_t i;
	89	struct text_range *tr;
	90
	91	for (i = 0; i < ARRAY_SIZE(text_ranges); ++i) {
	92	tr = &text_ranges[i];
	93
	94	if (strcmp(sym, tr->stext) == 0) {
	95	tr->start = addr;
	96	return 0;
	97	} else if (strcmp(sym, tr->etext) == 0) {
	98	tr->end = addr;
	99	return 0;
	100	}
	101	}
	102
	103	return 1;
	104	}
	105
b3dbb4ec	106	static int read_symbol(FILE in, struct sym_entry s)
1da177e4 LT	107	{
1da177e4 LT	108	char str[500];
b3dbb4ec	109	char *sym, stype;
1da177e4 LT	110	int rc;
1da177e4 LT	111
b3dbb4ec	112	rc = fscanf(in, "%llx %c %499s\n", &s->addr, &stype, str);
1da177e4	113	if (rc != 3) {
ef894870 JS	114	if (rc != EOF && fgets(str, 500, in) == NULL)
ef894870 JS	115	fprintf(stderr, "Read error or end of file.\n");
1da177e4 LT	116	return -1;
	117	}
	118
41f11a4f YS	119	sym = str;
	120	/* skip prefix char */
	121	if (symbol_prefix_char && str[0] == symbol_prefix_char)
	122	sym++;
	123
1da177e4	124	/* Ignore most absolute/undefined (?) symbols. */
fd593d12 EB	125	if (strcmp(sym, "_text") == 0)
fd593d12 EB	126	_text = s->addr;
17b1f0de MF	127	else if (read_symbol_tr(sym, s->addr) == 0)
17b1f0de MF	128	/* nothing to do */;
b3dbb4ec	129	else if (toupper(stype) == 'A')
1da177e4 LT	130	{
1da177e4 LT	131	/* Keep these useful absolute symbols */
41f11a4f YS	132	if (strcmp(sym, "__kernel_syscall_via_break") &&
	133	strcmp(sym, "__kernel_syscall_via_epc") &&
	134	strcmp(sym, "__kernel_sigtramp") &&
	135	strcmp(sym, "__gp"))
1da177e4 LT	136	return -1;
	137
	138	}
b3dbb4ec	139	else if (toupper(stype) == 'U' \|\|
41f11a4f	140	is_arm_mapping_symbol(sym))
1da177e4	141	return -1;
6f00df24 RB	142	/* exclude also MIPS ELF local symbols ($L123 instead of .L123) */
	143	else if (str[0] == '$')
	144	return -1;
aab34ac8 SR	145	/* exclude debugging symbols */
	146	else if (stype == 'N')
	147	return -1;
1da177e4 LT	148
	149	/* include the type field in the symbol name, so that it gets
	150	* compressed together */
	151	s->len = strlen(str) + 1;
b3dbb4ec	152	s->sym = malloc(s->len + 1);
f1a136e0 JJ	153	if (!s->sym) {
	154	fprintf(stderr, "kallsyms failure: "
	155	"unable to allocate required amount of memory\n");
	156	exit(EXIT_FAILURE);
	157	}
b3dbb4ec PM	158	strcpy((char *)s->sym + 1, str);
b3dbb4ec PM	159	s->sym[0] = stype;
1da177e4 LT	160
	161	return 0;
	162	}
	163
17b1f0de MF	164	static int symbol_valid_tr(struct sym_entry *s)
	165	{
	166	size_t i;
	167	struct text_range *tr;
	168
	169	for (i = 0; i < ARRAY_SIZE(text_ranges); ++i) {
	170	tr = &text_ranges[i];
	171
ac6ca5c8 MF	172	if (s->addr >= tr->start && s->addr <= tr->end)
ac6ca5c8 MF	173	return 1;
17b1f0de MF	174	}
17b1f0de MF	175
ac6ca5c8	176	return 0;
17b1f0de MF	177	}
17b1f0de MF	178
b3dbb4ec	179	static int symbol_valid(struct sym_entry *s)
1da177e4 LT	180	{
1da177e4 LT	181	/* Symbols which vary between passes. Passes 1 and 2 must have
2ea03891 SR	182	* identical symbol lists. The kallsyms_* symbols below are only added
	183	* after pass 1, they would be included in pass 2 when --all-symbols is
	184	* specified so exclude them to get a stable symbol list.
1da177e4 LT	185	*/
1da177e4 LT	186	static char *special_symbols[] = {
2ea03891 SR	187	"kallsyms_addresses",
	188	"kallsyms_num_syms",
	189	"kallsyms_names",
	190	"kallsyms_markers",
	191	"kallsyms_token_table",
	192	"kallsyms_token_index",
	193
1da177e4 LT	194	/* Exclude linker generated symbols which vary between passes */
	195	"_SDA_BASE_", /* ppc */
	196	"_SDA2_BASE_", /* ppc */
	197	NULL };
	198	int i;
41f11a4f YS	199	int offset = 1;
41f11a4f YS	200
f6537f2f ML	201	if (s->addr < kernel_start_addr)
	202	return 0;
	203
41f11a4f YS	204	/* skip prefix char */
	205	if (symbol_prefix_char && *(s->sym + 1) == symbol_prefix_char)
	206	offset++;
1da177e4 LT	207
	208	/* if --all-symbols is not specified, then symbols outside the text
	209	* and inittext sections are discarded */
	210	if (!all_symbols) {
17b1f0de	211	if (symbol_valid_tr(s) == 0)
1da177e4 LT	212	return 0;
1da177e4 LT	213	/* Corner case. Discard any symbols with the same value as
a3b81113 RG	214	* _etext _einittext; they can move between pass 1 and 2 when
	215	* the kallsyms data are added. If these symbols move then
	216	* they may get dropped in pass 2, which breaks the kallsyms
	217	* rules.
1da177e4	218	*/
17b1f0de MF	219	if ((s->addr == text_range_text->end &&
	220	strcmp((char *)s->sym + offset, text_range_text->etext)) \|\|
	221	(s->addr == text_range_inittext->end &&
	222	strcmp((char *)s->sym + offset, text_range_inittext->etext)))
1da177e4 LT	223	return 0;
	224	}
	225
	226	/* Exclude symbols which vary between passes. */
2ea03891	227	if (strstr((char *)s->sym + offset, "_compiled."))
1da177e4 LT	228	return 0;
	229
	230	for (i = 0; special_symbols[i]; i++)
b3dbb4ec	231	if( strcmp((char *)s->sym + offset, special_symbols[i]) == 0 )
1da177e4 LT	232	return 0;
	233
	234	return 1;
	235	}
	236
b3dbb4ec	237	static void read_map(FILE *in)
1da177e4 LT	238	{
1da177e4 LT	239	while (!feof(in)) {
b3dbb4ec PM	240	if (table_cnt >= table_size) {
	241	table_size += 10000;
	242	table = realloc(table, sizeof(table) table_size);
1da177e4 LT	243	if (!table) {
	244	fprintf(stderr, "out of memory\n");
	245	exit (1);
	246	}
	247	}
f2df3f65 PM	248	if (read_symbol(in, &table[table_cnt]) == 0) {
f2df3f65 PM	249	table[table_cnt].start_pos = table_cnt;
b3dbb4ec	250	table_cnt++;
f2df3f65	251	}
1da177e4 LT	252	}
	253	}
	254
	255	static void output_label(char *label)
	256	{
41f11a4f YS	257	if (symbol_prefix_char)
	258	printf(".globl %c%s\n", symbol_prefix_char, label);
	259	else
	260	printf(".globl %s\n", label);
1da177e4	261	printf("\tALGN\n");
41f11a4f YS	262	if (symbol_prefix_char)
	263	printf("%c%s:\n", symbol_prefix_char, label);
	264	else
	265	printf("%s:\n", label);
1da177e4 LT	266	}
	267
	268	/* uncompress a compressed symbol. When this function is called, the best table
	269	* might still be compressed itself, so the function needs to be recursive */
	270	static int expand_symbol(unsigned char data, int len, char result)
	271	{
	272	int c, rlen, total=0;
	273
	274	while (len) {
	275	c = *data;
	276	/* if the table holds a single char that is the same as the one
	277	* we are looking for, then end the search */
	278	if (best_table[c][0]==c && best_table_len[c]==1) {
	279	*result++ = c;
	280	total++;
	281	} else {
	282	/* if not, recurse and expand */
	283	rlen = expand_symbol(best_table[c], best_table_len[c], result);
	284	total += rlen;
	285	result += rlen;
	286	}
	287	data++;
	288	len--;
	289	}
	290	*result=0;
	291
	292	return total;
	293	}
	294
b3dbb4ec	295	static void write_src(void)
1da177e4	296	{
b3dbb4ec	297	unsigned int i, k, off;
1da177e4 LT	298	unsigned int best_idx[256];
1da177e4 LT	299	unsigned int *markers;
9281acea	300	char buf[KSYM_NAME_LEN];
1da177e4 LT	301
	302	printf("#include <asm/types.h>\n");
	303	printf("#if BITS_PER_LONG == 64\n");
	304	printf("#define PTR .quad\n");
	305	printf("#define ALGN .align 8\n");
	306	printf("#else\n");
	307	printf("#define PTR .long\n");
	308	printf("#define ALGN .align 4\n");
	309	printf("#endif\n");
	310
aad09470	311	printf("\t.section .rodata, \"a\"\n");
1da177e4	312
fd593d12 EB	313	/* Provide proper symbols relocatability by their '_text'
	314	* relativeness. The symbol names cannot be used to construct
	315	* normal symbol references as the list of symbols contains
	316	* symbols that are declared static and are private to their
	317	* .o files. This prevents .tmp_kallsyms.o or any other
	318	* object from referencing them.
	319	*/
1da177e4	320	output_label("kallsyms_addresses");
b3dbb4ec	321	for (i = 0; i < table_cnt; i++) {
fd593d12	322	if (toupper(table[i].sym[0]) != 'A') {
2c22d8ba VG	323	if (_text <= table[i].addr)
	324	printf("\tPTR\t_text + %#llx\n",
	325	table[i].addr - _text);
	326	else
	327	printf("\tPTR\t_text - %#llx\n",
	328	_text - table[i].addr);
fd593d12 EB	329	} else {
	330	printf("\tPTR\t%#llx\n", table[i].addr);
	331	}
1da177e4 LT	332	}
	333	printf("\n");
	334
	335	output_label("kallsyms_num_syms");
b3dbb4ec	336	printf("\tPTR\t%d\n", table_cnt);
1da177e4 LT	337	printf("\n");
	338
	339	/* table of offset markers, that give the offset in the compressed stream
	340	* every 256 symbols */
f1a136e0 JJ	341	markers = malloc(sizeof(unsigned int) * ((table_cnt + 255) / 256));
	342	if (!markers) {
	343	fprintf(stderr, "kallsyms failure: "
	344	"unable to allocate required memory\n");
	345	exit(EXIT_FAILURE);
	346	}
1da177e4 LT	347
1da177e4 LT	348	output_label("kallsyms_names");
1da177e4	349	off = 0;
b3dbb4ec PM	350	for (i = 0; i < table_cnt; i++) {
	351	if ((i & 0xFF) == 0)
	352	markers[i >> 8] = off;
1da177e4 LT	353
	354	printf("\t.byte 0x%02x", table[i].len);
	355	for (k = 0; k < table[i].len; k++)
	356	printf(", 0x%02x", table[i].sym[k]);
	357	printf("\n");
	358
	359	off += table[i].len + 1;
1da177e4 LT	360	}
	361	printf("\n");
	362
	363	output_label("kallsyms_markers");
b3dbb4ec	364	for (i = 0; i < ((table_cnt + 255) >> 8); i++)
1da177e4 LT	365	printf("\tPTR\t%d\n", markers[i]);
	366	printf("\n");
	367
	368	free(markers);
	369
	370	output_label("kallsyms_token_table");
	371	off = 0;
	372	for (i = 0; i < 256; i++) {
	373	best_idx[i] = off;
b3dbb4ec	374	expand_symbol(best_table[i], best_table_len[i], buf);
1da177e4 LT	375	printf("\t.asciz\t\"%s\"\n", buf);
	376	off += strlen(buf) + 1;
	377	}
	378	printf("\n");
	379
	380	output_label("kallsyms_token_index");
	381	for (i = 0; i < 256; i++)
	382	printf("\t.short\t%d\n", best_idx[i]);
	383	printf("\n");
	384	}
	385
	386
	387	/* table lookup compression functions */
	388
1da177e4 LT	389	/* count all the possible tokens in a symbol */
	390	static void learn_symbol(unsigned char *symbol, int len)
	391	{
	392	int i;
	393
	394	for (i = 0; i < len - 1; i++)
b3dbb4ec	395	token_profit[ symbol[i] + (symbol[i + 1] << 8) ]++;
1da177e4 LT	396	}
	397
	398	/* decrease the count for all the possible tokens in a symbol */
	399	static void forget_symbol(unsigned char *symbol, int len)
	400	{
	401	int i;
	402
	403	for (i = 0; i < len - 1; i++)
b3dbb4ec	404	token_profit[ symbol[i] + (symbol[i + 1] << 8) ]--;
1da177e4 LT	405	}
1da177e4 LT	406
b3dbb4ec	407	/* remove all the invalid symbols from the table and do the initial token count */
1da177e4 LT	408	static void build_initial_tok_table(void)
1da177e4 LT	409	{
b3dbb4ec	410	unsigned int i, pos;
1da177e4	411
b3dbb4ec PM	412	pos = 0;
b3dbb4ec PM	413	for (i = 0; i < table_cnt; i++) {
1da177e4	414	if ( symbol_valid(&table[i]) ) {
b3dbb4ec PM	415	if (pos != i)
	416	table[pos] = table[i];
	417	learn_symbol(table[pos].sym, table[pos].len);
	418	pos++;
1da177e4	419	}
1da177e4	420	}
b3dbb4ec	421	table_cnt = pos;
1da177e4 LT	422	}
1da177e4 LT	423
7c5d249a PM	424	static void find_token(unsigned char str, int len, unsigned char *token)
	425	{
	426	int i;
	427
	428	for (i = 0; i < len - 1; i++) {
	429	if (str[i] == token[0] && str[i+1] == token[1])
	430	return &str[i];
	431	}
	432	return NULL;
	433	}
	434
1da177e4 LT	435	/* replace a given token in all the valid symbols. Use the sampled symbols
1da177e4 LT	436	* to update the counts */
b3dbb4ec	437	static void compress_symbols(unsigned char *str, int idx)
1da177e4	438	{
b3dbb4ec PM	439	unsigned int i, len, size;
b3dbb4ec PM	440	unsigned char p1, p2;
1da177e4	441
b3dbb4ec	442	for (i = 0; i < table_cnt; i++) {
1da177e4 LT	443
1da177e4 LT	444	len = table[i].len;
b3dbb4ec PM	445	p1 = table[i].sym;
	446
	447	/* find the token on the symbol */
7c5d249a	448	p2 = find_token(p1, len, str);
b3dbb4ec PM	449	if (!p2) continue;
	450
	451	/* decrease the counts for this symbol's tokens */
	452	forget_symbol(table[i].sym, len);
	453
	454	size = len;
1da177e4 LT	455
1da177e4 LT	456	do {
b3dbb4ec PM	457	*p2 = idx;
	458	p2++;
	459	size -= (p2 - p1);
	460	memmove(p2, p2 + 1, size);
	461	p1 = p2;
	462	len--;
	463
	464	if (size < 2) break;
	465
1da177e4	466	/* find the token on the symbol */
7c5d249a	467	p2 = find_token(p1, size, str);
1da177e4	468
b3dbb4ec	469	} while (p2);
1da177e4	470
b3dbb4ec	471	table[i].len = len;
1da177e4	472
b3dbb4ec PM	473	/* increase the counts for this symbol's new tokens */
b3dbb4ec PM	474	learn_symbol(table[i].sym, len);
1da177e4 LT	475	}
	476	}
	477
	478	/* search the token with the maximum profit */
b3dbb4ec	479	static int find_best_token(void)
1da177e4	480	{
b3dbb4ec	481	int i, best, bestprofit;
1da177e4 LT	482
1da177e4 LT	483	bestprofit=-10000;
b3dbb4ec	484	best = 0;
1da177e4	485
b3dbb4ec PM	486	for (i = 0; i < 0x10000; i++) {
	487	if (token_profit[i] > bestprofit) {
	488	best = i;
	489	bestprofit = token_profit[i];
1da177e4	490	}
1da177e4	491	}
1da177e4 LT	492	return best;
	493	}
	494
	495	/* this is the core of the algorithm: calculate the "best" table */
	496	static void optimize_result(void)
	497	{
b3dbb4ec	498	int i, best;
1da177e4 LT	499
	500	/* using the '\0' symbol last allows compress_symbols to use standard
	501	* fast string functions */
	502	for (i = 255; i >= 0; i--) {
	503
	504	/* if this table slot is empty (it is not used by an actual
	505	* original char code */
	506	if (!best_table_len[i]) {
	507
	508	/* find the token with the breates profit value */
	509	best = find_best_token();
e0a04b11 XW	510	if (token_profit[best] == 0)
e0a04b11 XW	511	break;
1da177e4 LT	512
1da177e4 LT	513	/* place it in the "best" table */
b3dbb4ec PM	514	best_table_len[i] = 2;
	515	best_table[i][0] = best & 0xFF;
	516	best_table[i][1] = (best >> 8) & 0xFF;
1da177e4 LT	517
1da177e4 LT	518	/* replace this token in all the valid symbols */
b3dbb4ec	519	compress_symbols(best_table[i], i);
1da177e4 LT	520	}
	521	}
	522	}
	523
	524	/* start by placing the symbols that are actually used on the table */
	525	static void insert_real_symbols_in_table(void)
	526	{
b3dbb4ec	527	unsigned int i, j, c;
1da177e4 LT	528
	529	memset(best_table, 0, sizeof(best_table));
	530	memset(best_table_len, 0, sizeof(best_table_len));
	531
b3dbb4ec PM	532	for (i = 0; i < table_cnt; i++) {
	533	for (j = 0; j < table[i].len; j++) {
	534	c = table[i].sym[j];
	535	best_table[c][0]=c;
	536	best_table_len[c]=1;
1da177e4 LT	537	}
	538	}
	539	}
	540
	541	static void optimize_token_table(void)
	542	{
1da177e4 LT	543	build_initial_tok_table();
	544
	545	insert_real_symbols_in_table();
	546
41f11a4f	547	/* When valid symbol is not registered, exit to error */
b3dbb4ec	548	if (!table_cnt) {
41f11a4f YS	549	fprintf(stderr, "No valid symbol.\n");
	550	exit(1);
	551	}
	552
1da177e4 LT	553	optimize_result();
	554	}
	555
b478b782 LJ	556	/* guess for "linker script provide" symbol */
	557	static int may_be_linker_script_provide_symbol(const struct sym_entry *se)
	558	{
	559	const char symbol = (char )se->sym + 1;
	560	int len = se->len - 1;
	561
	562	if (len < 8)
	563	return 0;
	564
	565	if (symbol[0] != '_' \|\| symbol[1] != '_')
	566	return 0;
	567
	568	/* __start_XXXXX */
	569	if (!memcmp(symbol + 2, "start_", 6))
	570	return 1;
	571
	572	/* __stop_XXXXX */
	573	if (!memcmp(symbol + 2, "stop_", 5))
	574	return 1;
	575
	576	/* __end_XXXXX */
	577	if (!memcmp(symbol + 2, "end_", 4))
	578	return 1;
	579
	580	/* __XXXXX_start */
	581	if (!memcmp(symbol + len - 6, "_start", 6))
	582	return 1;
	583
	584	/* __XXXXX_end */
	585	if (!memcmp(symbol + len - 4, "_end", 4))
	586	return 1;
	587
	588	return 0;
	589	}
	590
	591	static int prefix_underscores_count(const char *str)
	592	{
	593	const char *tail = str;
	594
a9ece53c	595	while (*tail == '_')
b478b782 LJ	596	tail++;
	597
	598	return tail - str;
	599	}
	600
f2df3f65 PM	601	static int compare_symbols(const void a, const void b)
	602	{
	603	const struct sym_entry *sa;
	604	const struct sym_entry *sb;
	605	int wa, wb;
	606
	607	sa = a;
	608	sb = b;
	609
	610	/* sort by address first */
	611	if (sa->addr > sb->addr)
	612	return 1;
	613	if (sa->addr < sb->addr)
	614	return -1;
	615
	616	/* sort by "weakness" type */
	617	wa = (sa->sym[0] == 'w') \|\| (sa->sym[0] == 'W');
	618	wb = (sb->sym[0] == 'w') \|\| (sb->sym[0] == 'W');
	619	if (wa != wb)
	620	return wa - wb;
	621
b478b782 LJ	622	/* sort by "linker script provide" type */
	623	wa = may_be_linker_script_provide_symbol(sa);
	624	wb = may_be_linker_script_provide_symbol(sb);
	625	if (wa != wb)
	626	return wa - wb;
	627
	628	/* sort by the number of prefix underscores */
	629	wa = prefix_underscores_count((const char *)sa->sym + 1);
	630	wb = prefix_underscores_count((const char *)sb->sym + 1);
	631	if (wa != wb)
	632	return wa - wb;
	633
f2df3f65 PM	634	/* sort by initial order, so that other symbols are left undisturbed */
	635	return sa->start_pos - sb->start_pos;
	636	}
	637
	638	static void sort_symbols(void)
	639	{
	640	qsort(table, table_cnt, sizeof(struct sym_entry), compare_symbols);
	641	}
1da177e4	642
b3dbb4ec	643	int main(int argc, char **argv)
1da177e4	644	{
41f11a4f YS	645	if (argc >= 2) {
	646	int i;
	647	for (i = 1; i < argc; i++) {
	648	if(strcmp(argv[i], "--all-symbols") == 0)
	649	all_symbols = 1;
	650	else if (strncmp(argv[i], "--symbol-prefix=", 16) == 0) {
	651	char *p = &argv[i][16];
	652	/* skip quote */
	653	if ((p == '"' && (p+2) == '"') \|\| (p == '\'' && (p+2) == '\''))
	654	p++;
	655	symbol_prefix_char = *p;
f6537f2f ML	656	} else if (strncmp(argv[i], "--page-offset=", 14) == 0) {
	657	const char *p = &argv[i][14];
	658	kernel_start_addr = strtoull(p, NULL, 16);
41f11a4f YS	659	} else
	660	usage();
	661	}
	662	} else if (argc != 1)
1da177e4 LT	663	usage();
	664
	665	read_map(stdin);
2ea03891 SR	666	sort_symbols();
2ea03891 SR	667	optimize_token_table();
1da177e4 LT	668	write_src();
	669
	670	return 0;
	671	}