string_helpers.c 13.5 KB
Newer Older
1 2 3 4
/*
 * Helpers for formatting and printing strings
 *
 * Copyright 31 August 2008 James Bottomley
5
 * Copyright (C) 2013, Intel Corporation
6
 */
7
#include <linux/bug.h>
8 9
#include <linux/kernel.h>
#include <linux/math64.h>
10
#include <linux/export.h>
11
#include <linux/ctype.h>
12
#include <linux/errno.h>
13 14
#include <linux/fs.h>
#include <linux/limits.h>
15
#include <linux/mm.h>
16
#include <linux/slab.h>
17
#include <linux/string.h>
18 19 20 21
#include <linux/string_helpers.h>

/**
 * string_get_size - get the size in the specified units
22 23
 * @size:	The size to be converted in blocks
 * @blk_size:	Size of the block (use 1 for size in bytes)
24 25 26 27 28
 * @units:	units to use (powers of 1000 or 1024)
 * @buf:	buffer to format to
 * @len:	length of buffer
 *
 * This function returns a string formatted to 3 significant figures
29 30
 * giving the size in the required units.  @buf should have room for
 * at least 9 bytes and will always be zero terminated.
31 32
 *
 */
33
void string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
34
		     char *buf, int len)
35
{
36
	static const char *const units_10[] = {
37
		"B", "kB", "MB", "GB", "TB", "PB", "EB", "ZB", "YB"
38 39
	};
	static const char *const units_2[] = {
40
		"B", "KiB", "MiB", "GiB", "TiB", "PiB", "EiB", "ZiB", "YiB"
41 42 43
	};
	static const char *const *const units_str[] = {
		[STRING_UNITS_10] = units_10,
44 45
		[STRING_UNITS_2] = units_2,
	};
46
	static const unsigned int divisor[] = {
47 48 49
		[STRING_UNITS_10] = 1000,
		[STRING_UNITS_2] = 1024,
	};
50 51 52
	static const unsigned int rounding[] = { 500, 50, 5 };
	int i = 0, j;
	u32 remainder = 0, sf_cap;
53
	char tmp[8];
54
	const char *unit;
55 56

	tmp[0] = '\0';
57 58 59 60

	if (blk_size == 0)
		size = 0;
	if (size == 0)
61
		goto out;
62

63 64 65 66 67 68 69 70 71 72 73 74 75
	/* This is Napier's algorithm.  Reduce the original block size to
	 *
	 * coefficient * divisor[units]^i
	 *
	 * we do the reduction so both coefficients are just under 32 bits so
	 * that multiplying them together won't overflow 64 bits and we keep
	 * as much precision as possible in the numbers.
	 *
	 * Note: it's safe to throw away the remainders here because all the
	 * precision is in the coefficients.
	 */
	while (blk_size >> 32) {
		do_div(blk_size, divisor[units]);
76 77 78
		i++;
	}

79 80
	while (size >> 32) {
		do_div(size, divisor[units]);
81 82 83
		i++;
	}

84 85
	/* now perform the actual multiplication keeping i as the sum of the
	 * two logarithms */
86
	size *= blk_size;
87

88
	/* and logarithmically reduce it until it's just under the divisor */
89 90 91
	while (size >= divisor[units]) {
		remainder = do_div(size, divisor[units]);
		i++;
92 93
	}

94 95
	/* work out in j how many digits of precision we need from the
	 * remainder */
96 97 98 99
	sf_cap = size;
	for (j = 0; sf_cap*10 < 1000; j++)
		sf_cap *= 10;

100 101 102 103
	if (units == STRING_UNITS_2) {
		/* express the remainder as a decimal.  It's currently the
		 * numerator of a fraction whose denominator is
		 * divisor[units], which is 1 << 10 for STRING_UNITS_2 */
104
		remainder *= 1000;
105 106 107 108 109 110 111 112 113 114 115 116
		remainder >>= 10;
	}

	/* add a 5 to the digit below what will be printed to ensure
	 * an arithmetical round up and carry it through to size */
	remainder += rounding[j];
	if (remainder >= 1000) {
		remainder -= 1000;
		size += 1;
	}

	if (j) {
117 118 119 120 121 122 123 124 125 126
		snprintf(tmp, sizeof(tmp), ".%03u", remainder);
		tmp[j+1] = '\0';
	}

 out:
	if (i >= ARRAY_SIZE(units_2))
		unit = "UNK";
	else
		unit = units_str[units][i];

127
	snprintf(buf, len, "%u%s %s", (u32)size,
128
		 tmp, unit);
129 130
}
EXPORT_SYMBOL(string_get_size);
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227

static bool unescape_space(char **src, char **dst)
{
	char *p = *dst, *q = *src;

	switch (*q) {
	case 'n':
		*p = '\n';
		break;
	case 'r':
		*p = '\r';
		break;
	case 't':
		*p = '\t';
		break;
	case 'v':
		*p = '\v';
		break;
	case 'f':
		*p = '\f';
		break;
	default:
		return false;
	}
	*dst += 1;
	*src += 1;
	return true;
}

static bool unescape_octal(char **src, char **dst)
{
	char *p = *dst, *q = *src;
	u8 num;

	if (isodigit(*q) == 0)
		return false;

	num = (*q++) & 7;
	while (num < 32 && isodigit(*q) && (q - *src < 3)) {
		num <<= 3;
		num += (*q++) & 7;
	}
	*p = num;
	*dst += 1;
	*src = q;
	return true;
}

static bool unescape_hex(char **src, char **dst)
{
	char *p = *dst, *q = *src;
	int digit;
	u8 num;

	if (*q++ != 'x')
		return false;

	num = digit = hex_to_bin(*q++);
	if (digit < 0)
		return false;

	digit = hex_to_bin(*q);
	if (digit >= 0) {
		q++;
		num = (num << 4) | digit;
	}
	*p = num;
	*dst += 1;
	*src = q;
	return true;
}

static bool unescape_special(char **src, char **dst)
{
	char *p = *dst, *q = *src;

	switch (*q) {
	case '\"':
		*p = '\"';
		break;
	case '\\':
		*p = '\\';
		break;
	case 'a':
		*p = '\a';
		break;
	case 'e':
		*p = '\e';
		break;
	default:
		return false;
	}
	*dst += 1;
	*src += 1;
	return true;
}

228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265
/**
 * string_unescape - unquote characters in the given string
 * @src:	source buffer (escaped)
 * @dst:	destination buffer (unescaped)
 * @size:	size of the destination buffer (0 to unlimit)
 * @flags:	combination of the flags (bitwise OR):
 *	%UNESCAPE_SPACE:
 *		'\f' - form feed
 *		'\n' - new line
 *		'\r' - carriage return
 *		'\t' - horizontal tab
 *		'\v' - vertical tab
 *	%UNESCAPE_OCTAL:
 *		'\NNN' - byte with octal value NNN (1 to 3 digits)
 *	%UNESCAPE_HEX:
 *		'\xHH' - byte with hexadecimal value HH (1 to 2 digits)
 *	%UNESCAPE_SPECIAL:
 *		'\"' - double quote
 *		'\\' - backslash
 *		'\a' - alert (BEL)
 *		'\e' - escape
 *	%UNESCAPE_ANY:
 *		all previous together
 *
 * Description:
 * The function unquotes characters in the given string.
 *
 * Because the size of the output will be the same as or less than the size of
 * the input, the transformation may be performed in place.
 *
 * Caller must provide valid source and destination pointers. Be aware that
 * destination buffer will always be NULL-terminated. Source string must be
 * NULL-terminated as well.
 *
 * Return:
 * The amount of the characters processed to the destination buffer excluding
 * trailing '\0' is returned.
 */
266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299
int string_unescape(char *src, char *dst, size_t size, unsigned int flags)
{
	char *out = dst;

	while (*src && --size) {
		if (src[0] == '\\' && src[1] != '\0' && size > 1) {
			src++;
			size--;

			if (flags & UNESCAPE_SPACE &&
					unescape_space(&src, &out))
				continue;

			if (flags & UNESCAPE_OCTAL &&
					unescape_octal(&src, &out))
				continue;

			if (flags & UNESCAPE_HEX &&
					unescape_hex(&src, &out))
				continue;

			if (flags & UNESCAPE_SPECIAL &&
					unescape_special(&src, &out))
				continue;

			*out++ = '\\';
		}
		*out++ = *src++;
	}
	*out = '\0';

	return out - dst;
}
EXPORT_SYMBOL(string_unescape);
300

301
static bool escape_passthrough(unsigned char c, char **dst, char *end)
302 303 304
{
	char *out = *dst;

305 306 307 308
	if (out < end)
		*out = c;
	*dst = out + 1;
	return true;
309 310
}

311
static bool escape_space(unsigned char c, char **dst, char *end)
312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332
{
	char *out = *dst;
	unsigned char to;

	switch (c) {
	case '\n':
		to = 'n';
		break;
	case '\r':
		to = 'r';
		break;
	case '\t':
		to = 't';
		break;
	case '\v':
		to = 'v';
		break;
	case '\f':
		to = 'f';
		break;
	default:
333
		return false;
334 335
	}

336 337 338 339 340 341
	if (out < end)
		*out = '\\';
	++out;
	if (out < end)
		*out = to;
	++out;
342

343 344
	*dst = out;
	return true;
345 346
}

347
static bool escape_special(unsigned char c, char **dst, char *end)
348 349 350 351 352 353 354 355 356 357 358 359 360 361 362
{
	char *out = *dst;
	unsigned char to;

	switch (c) {
	case '\\':
		to = '\\';
		break;
	case '\a':
		to = 'a';
		break;
	case '\e':
		to = 'e';
		break;
	default:
363
		return false;
364 365
	}

366 367 368 369 370 371
	if (out < end)
		*out = '\\';
	++out;
	if (out < end)
		*out = to;
	++out;
372

373 374
	*dst = out;
	return true;
375 376
}

377
static bool escape_null(unsigned char c, char **dst, char *end)
378 379 380 381
{
	char *out = *dst;

	if (c)
382
		return false;
383

384 385 386 387 388 389
	if (out < end)
		*out = '\\';
	++out;
	if (out < end)
		*out = '0';
	++out;
390

391 392
	*dst = out;
	return true;
393 394
}

395
static bool escape_octal(unsigned char c, char **dst, char *end)
396 397 398
{
	char *out = *dst;

399 400 401 402 403 404 405 406 407 408 409 410
	if (out < end)
		*out = '\\';
	++out;
	if (out < end)
		*out = ((c >> 6) & 0x07) + '0';
	++out;
	if (out < end)
		*out = ((c >> 3) & 0x07) + '0';
	++out;
	if (out < end)
		*out = ((c >> 0) & 0x07) + '0';
	++out;
411 412

	*dst = out;
413
	return true;
414 415
}

416
static bool escape_hex(unsigned char c, char **dst, char *end)
417 418 419
{
	char *out = *dst;

420 421 422 423 424 425 426 427 428 429 430 431
	if (out < end)
		*out = '\\';
	++out;
	if (out < end)
		*out = 'x';
	++out;
	if (out < end)
		*out = hex_asc_hi(c);
	++out;
	if (out < end)
		*out = hex_asc_lo(c);
	++out;
432 433

	*dst = out;
434
	return true;
435 436 437 438 439 440 441 442 443
}

/**
 * string_escape_mem - quote characters in the given memory buffer
 * @src:	source buffer (unescaped)
 * @isz:	source buffer size
 * @dst:	destination buffer (escaped)
 * @osz:	destination buffer size
 * @flags:	combination of the flags (bitwise OR):
444
 *	%ESCAPE_SPACE: (special white space, not space itself)
445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465
 *		'\f' - form feed
 *		'\n' - new line
 *		'\r' - carriage return
 *		'\t' - horizontal tab
 *		'\v' - vertical tab
 *	%ESCAPE_SPECIAL:
 *		'\\' - backslash
 *		'\a' - alert (BEL)
 *		'\e' - escape
 *	%ESCAPE_NULL:
 *		'\0' - null
 *	%ESCAPE_OCTAL:
 *		'\NNN' - byte with octal value NNN (3 digits)
 *	%ESCAPE_ANY:
 *		all previous together
 *	%ESCAPE_NP:
 *		escape only non-printable characters (checked by isprint)
 *	%ESCAPE_ANY_NP:
 *		all previous together
 *	%ESCAPE_HEX:
 *		'\xHH' - byte with hexadecimal value HH (2 digits)
466 467
 * @only:	NULL-terminated string containing characters used to limit
 *		the selected escape class. If characters are included in @only
468 469
 *		that would not normally be escaped by the classes selected
 *		in @flags, they will be copied to @dst unescaped.
470 471 472 473 474 475
 *
 * Description:
 * The process of escaping byte buffer includes several parts. They are applied
 * in the following sequence.
 *	1. The character is matched to the printable class, if asked, and in
 *	   case of match it passes through to the output.
476
 *	2. The character is not matched to the one from @only string and thus
477
 *	   must go as-is to the output.
478 479 480 481 482 483 484 485 486 487
 *	3. The character is checked if it falls into the class given by @flags.
 *	   %ESCAPE_OCTAL and %ESCAPE_HEX are going last since they cover any
 *	   character. Note that they actually can't go together, otherwise
 *	   %ESCAPE_HEX will be ignored.
 *
 * Caller must provide valid source and destination pointers. Be aware that
 * destination buffer will not be NULL-terminated, thus caller have to append
 * it if needs.
 *
 * Return:
488 489 490 491
 * The total size of the escaped output that would be generated for
 * the given input and flags. To check whether the output was
 * truncated, compare the return value to osz. There is room left in
 * dst for a '\0' terminator if and only if ret < osz.
492
 */
493
int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz,
494
		      unsigned int flags, const char *only)
495
{
496
	char *p = dst;
497
	char *end = p + osz;
498
	bool is_dict = only && *only;
499 500 501 502 503 504 505 506

	while (isz--) {
		unsigned char c = *src++;

		/*
		 * Apply rules in the following sequence:
		 *	- the character is printable, when @flags has
		 *	  %ESCAPE_NP bit set
507
		 *	- the @only string is supplied and does not contain a
508 509 510 511 512 513 514
		 *	  character under question
		 *	- the character doesn't fall into a class of symbols
		 *	  defined by given @flags
		 * In these cases we just pass through a character to the
		 * output buffer.
		 */
		if ((flags & ESCAPE_NP && isprint(c)) ||
515
		    (is_dict && !strchr(only, c))) {
516 517
			/* do nothing */
		} else {
518 519 520 521 522 523 524 525
			if (flags & ESCAPE_SPACE && escape_space(c, &p, end))
				continue;

			if (flags & ESCAPE_SPECIAL && escape_special(c, &p, end))
				continue;

			if (flags & ESCAPE_NULL && escape_null(c, &p, end))
				continue;
526 527

			/* ESCAPE_OCTAL and ESCAPE_HEX always go last */
528
			if (flags & ESCAPE_OCTAL && escape_octal(c, &p, end))
529
				continue;
530 531

			if (flags & ESCAPE_HEX && escape_hex(c, &p, end))
532 533 534
				continue;
		}

535
		escape_passthrough(c, &p, end);
536 537
	}

538
	return p - dst;
539 540
}
EXPORT_SYMBOL(string_escape_mem);
541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567

/*
 * Return an allocated string that has been escaped of special characters
 * and double quotes, making it safe to log in quotes.
 */
char *kstrdup_quotable(const char *src, gfp_t gfp)
{
	size_t slen, dlen;
	char *dst;
	const int flags = ESCAPE_HEX;
	const char esc[] = "\f\n\r\t\v\a\e\\\"";

	if (!src)
		return NULL;
	slen = strlen(src);

	dlen = string_escape_mem(src, slen, NULL, 0, flags, esc);
	dst = kmalloc(dlen + 1, gfp);
	if (!dst)
		return NULL;

	WARN_ON(string_escape_mem(src, slen, dst, dlen, flags, esc) != dlen);
	dst[dlen] = '\0';

	return dst;
}
EXPORT_SYMBOL_GPL(kstrdup_quotable);
568 569 570 571 572 573 574 575 576 577 578

/*
 * Returns allocated NULL-terminated string containing process
 * command line, with inter-argument NULLs replaced with spaces,
 * and other special characters escaped.
 */
char *kstrdup_quotable_cmdline(struct task_struct *task, gfp_t gfp)
{
	char *buffer, *quoted;
	int i, res;

579
	buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600
	if (!buffer)
		return NULL;

	res = get_cmdline(task, buffer, PAGE_SIZE - 1);
	buffer[res] = '\0';

	/* Collapse trailing NULLs, leave res pointing to last non-NULL. */
	while (--res >= 0 && buffer[res] == '\0')
		;

	/* Replace inter-argument NULLs. */
	for (i = 0; i <= res; i++)
		if (buffer[i] == '\0')
			buffer[i] = ' ';

	/* Make sure result is printable. */
	quoted = kstrdup_quotable(buffer, gfp);
	kfree(buffer);
	return quoted;
}
EXPORT_SYMBOL_GPL(kstrdup_quotable_cmdline);
601 602 603 604 605 606 607 608 609 610 611 612 613 614

/*
 * Returns allocated NULL-terminated string containing pathname,
 * with special characters escaped, able to be safely logged. If
 * there is an error, the leading character will be "<".
 */
char *kstrdup_quotable_file(struct file *file, gfp_t gfp)
{
	char *temp, *pathname;

	if (!file)
		return kstrdup("<unknown>", gfp);

	/* We add 11 spaces for ' (deleted)' to be appended */
615
	temp = kmalloc(PATH_MAX + 11, GFP_KERNEL);
616 617 618 619 620 621 622 623 624 625 626 627 628
	if (!temp)
		return kstrdup("<no_memory>", gfp);

	pathname = file_path(file, temp, PATH_MAX + 11);
	if (IS_ERR(pathname))
		pathname = kstrdup("<too_long>", gfp);
	else
		pathname = kstrdup_quotable(pathname, gfp);

	kfree(temp);
	return pathname;
}
EXPORT_SYMBOL_GPL(kstrdup_quotable_file);