kernel_optimize_test/lib/kstrtox.c
Richard Fitzgerald 9e914f59cc lib: vsprintf: Fix handling of number field widths in vsscanf
[ Upstream commit 900fdc4573766dd43b847b4f54bd4a1ee2bc7360 ]

The existing code attempted to handle numbers by doing a strto[u]l(),
ignoring the field width, and then repeatedly dividing to extract the
field out of the full converted value. If the string contains a run of
valid digits longer than will fit in a long or long long, this would
overflow and no amount of dividing can recover the correct value.

This patch fixes vsscanf() to obey number field widths when parsing
the number.

A new _parse_integer_limit() is added that takes a limit for the number
of characters to parse. The number field conversion in vsscanf is changed
to use this new function.

If a number starts with a radix prefix, the field width  must be long
enough for at last one digit after the prefix. If not, it will be handled
like this:

 sscanf("0x4", "%1i", &i): i=0, scanning continues with the 'x'
 sscanf("0x4", "%2i", &i): i=0, scanning continues with the '4'

This is consistent with the observed behaviour of userland sscanf.

Note that this patch does NOT fix the problem of a single field value
overflowing the target type. So for example:

  sscanf("123456789abcdef", "%x", &i);

Will not produce the correct result because the value obviously overflows
INT_MAX. But sscanf will report a successful conversion.

Note that where a very large number is used to mean "unlimited", the value
INT_MAX is used for consistency with the behaviour of vsnprintf().

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20210514161206.30821-2-rf@opensource.cirrus.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
2021-07-14 16:55:57 +02:00

414 lines
11 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Convert integer string representation to an integer.
* If an integer doesn't fit into specified type, -E is returned.
*
* Integer starts with optional sign.
* kstrtou*() functions do not accept sign "-".
*
* Radix 0 means autodetection: leading "0x" implies radix 16,
* leading "0" implies radix 8, otherwise radix is 10.
* Autodetection hints work after optional sign, but not before.
*
* If -E is returned, result is not touched.
*/
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/math64.h>
#include <linux/export.h>
#include <linux/types.h>
#include <linux/uaccess.h>
#include "kstrtox.h"
const char *_parse_integer_fixup_radix(const char *s, unsigned int *base)
{
if (*base == 0) {
if (s[0] == '0') {
if (_tolower(s[1]) == 'x' && isxdigit(s[2]))
*base = 16;
else
*base = 8;
} else
*base = 10;
}
if (*base == 16 && s[0] == '0' && _tolower(s[1]) == 'x')
s += 2;
return s;
}
/*
* Convert non-negative integer string representation in explicitly given radix
* to an integer. A maximum of max_chars characters will be converted.
*
* Return number of characters consumed maybe or-ed with overflow bit.
* If overflow occurs, result integer (incorrect) is still returned.
*
* Don't you dare use this function.
*/
unsigned int _parse_integer_limit(const char *s, unsigned int base, unsigned long long *p,
size_t max_chars)
{
unsigned long long res;
unsigned int rv;
res = 0;
rv = 0;
while (max_chars--) {
unsigned int c = *s;
unsigned int lc = c | 0x20; /* don't tolower() this line */
unsigned int val;
if ('0' <= c && c <= '9')
val = c - '0';
else if ('a' <= lc && lc <= 'f')
val = lc - 'a' + 10;
else
break;
if (val >= base)
break;
/*
* Check for overflow only if we are within range of
* it in the max base we support (16)
*/
if (unlikely(res & (~0ull << 60))) {
if (res > div_u64(ULLONG_MAX - val, base))
rv |= KSTRTOX_OVERFLOW;
}
res = res * base + val;
rv++;
s++;
}
*p = res;
return rv;
}
unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p)
{
return _parse_integer_limit(s, base, p, INT_MAX);
}
static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
{
unsigned long long _res;
unsigned int rv;
s = _parse_integer_fixup_radix(s, &base);
rv = _parse_integer(s, base, &_res);
if (rv & KSTRTOX_OVERFLOW)
return -ERANGE;
if (rv == 0)
return -EINVAL;
s += rv;
if (*s == '\n')
s++;
if (*s)
return -EINVAL;
*res = _res;
return 0;
}
/**
* kstrtoull - convert a string to an unsigned long long
* @s: The start of the string. The string must be null-terminated, and may also
* include a single newline before its terminating null. The first character
* may also be a plus sign, but not a minus sign.
* @base: The number base to use. The maximum supported base is 16. If base is
* given as 0, then the base of the string is automatically detected with the
* conventional semantics - If it begins with 0x the number will be parsed as a
* hexadecimal (case insensitive), if it otherwise begins with 0, it will be
* parsed as an octal number. Otherwise it will be parsed as a decimal.
* @res: Where to write the result of the conversion on success.
*
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Preferred over simple_strtoull(). Return code must be checked.
*/
int kstrtoull(const char *s, unsigned int base, unsigned long long *res)
{
if (s[0] == '+')
s++;
return _kstrtoull(s, base, res);
}
EXPORT_SYMBOL(kstrtoull);
/**
* kstrtoll - convert a string to a long long
* @s: The start of the string. The string must be null-terminated, and may also
* include a single newline before its terminating null. The first character
* may also be a plus sign or a minus sign.
* @base: The number base to use. The maximum supported base is 16. If base is
* given as 0, then the base of the string is automatically detected with the
* conventional semantics - If it begins with 0x the number will be parsed as a
* hexadecimal (case insensitive), if it otherwise begins with 0, it will be
* parsed as an octal number. Otherwise it will be parsed as a decimal.
* @res: Where to write the result of the conversion on success.
*
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Preferred over simple_strtoll(). Return code must be checked.
*/
int kstrtoll(const char *s, unsigned int base, long long *res)
{
unsigned long long tmp;
int rv;
if (s[0] == '-') {
rv = _kstrtoull(s + 1, base, &tmp);
if (rv < 0)
return rv;
if ((long long)-tmp > 0)
return -ERANGE;
*res = -tmp;
} else {
rv = kstrtoull(s, base, &tmp);
if (rv < 0)
return rv;
if ((long long)tmp < 0)
return -ERANGE;
*res = tmp;
}
return 0;
}
EXPORT_SYMBOL(kstrtoll);
/* Internal, do not use. */
int _kstrtoul(const char *s, unsigned int base, unsigned long *res)
{
unsigned long long tmp;
int rv;
rv = kstrtoull(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (unsigned long)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(_kstrtoul);
/* Internal, do not use. */
int _kstrtol(const char *s, unsigned int base, long *res)
{
long long tmp;
int rv;
rv = kstrtoll(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (long)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(_kstrtol);
/**
* kstrtouint - convert a string to an unsigned int
* @s: The start of the string. The string must be null-terminated, and may also
* include a single newline before its terminating null. The first character
* may also be a plus sign, but not a minus sign.
* @base: The number base to use. The maximum supported base is 16. If base is
* given as 0, then the base of the string is automatically detected with the
* conventional semantics - If it begins with 0x the number will be parsed as a
* hexadecimal (case insensitive), if it otherwise begins with 0, it will be
* parsed as an octal number. Otherwise it will be parsed as a decimal.
* @res: Where to write the result of the conversion on success.
*
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Preferred over simple_strtoul(). Return code must be checked.
*/
int kstrtouint(const char *s, unsigned int base, unsigned int *res)
{
unsigned long long tmp;
int rv;
rv = kstrtoull(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (unsigned int)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(kstrtouint);
/**
* kstrtoint - convert a string to an int
* @s: The start of the string. The string must be null-terminated, and may also
* include a single newline before its terminating null. The first character
* may also be a plus sign or a minus sign.
* @base: The number base to use. The maximum supported base is 16. If base is
* given as 0, then the base of the string is automatically detected with the
* conventional semantics - If it begins with 0x the number will be parsed as a
* hexadecimal (case insensitive), if it otherwise begins with 0, it will be
* parsed as an octal number. Otherwise it will be parsed as a decimal.
* @res: Where to write the result of the conversion on success.
*
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Preferred over simple_strtol(). Return code must be checked.
*/
int kstrtoint(const char *s, unsigned int base, int *res)
{
long long tmp;
int rv;
rv = kstrtoll(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (int)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(kstrtoint);
int kstrtou16(const char *s, unsigned int base, u16 *res)
{
unsigned long long tmp;
int rv;
rv = kstrtoull(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (u16)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(kstrtou16);
int kstrtos16(const char *s, unsigned int base, s16 *res)
{
long long tmp;
int rv;
rv = kstrtoll(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (s16)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(kstrtos16);
int kstrtou8(const char *s, unsigned int base, u8 *res)
{
unsigned long long tmp;
int rv;
rv = kstrtoull(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (u8)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(kstrtou8);
int kstrtos8(const char *s, unsigned int base, s8 *res)
{
long long tmp;
int rv;
rv = kstrtoll(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (s8)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(kstrtos8);
/**
* kstrtobool - convert common user inputs into boolean values
* @s: input string
* @res: result
*
* This routine returns 0 iff the first character is one of 'Yy1Nn0', or
* [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL. Value
* pointed to by res is updated upon finding a match.
*/
int kstrtobool(const char *s, bool *res)
{
if (!s)
return -EINVAL;
switch (s[0]) {
case 'y':
case 'Y':
case '1':
*res = true;
return 0;
case 'n':
case 'N':
case '0':
*res = false;
return 0;
case 'o':
case 'O':
switch (s[1]) {
case 'n':
case 'N':
*res = true;
return 0;
case 'f':
case 'F':
*res = false;
return 0;
default:
break;
}
default:
break;
}
return -EINVAL;
}
EXPORT_SYMBOL(kstrtobool);
/*
* Since "base" would be a nonsense argument, this open-codes the
* _from_user helper instead of using the helper macro below.
*/
int kstrtobool_from_user(const char __user *s, size_t count, bool *res)
{
/* Longest string needed to differentiate, newline, terminator */
char buf[4];
count = min(count, sizeof(buf) - 1);
if (copy_from_user(buf, s, count))
return -EFAULT;
buf[count] = '\0';
return kstrtobool(buf, res);
}
EXPORT_SYMBOL(kstrtobool_from_user);
#define kstrto_from_user(f, g, type) \
int f(const char __user *s, size_t count, unsigned int base, type *res) \
{ \
/* sign, base 2 representation, newline, terminator */ \
char buf[1 + sizeof(type) * 8 + 1 + 1]; \
\
count = min(count, sizeof(buf) - 1); \
if (copy_from_user(buf, s, count)) \
return -EFAULT; \
buf[count] = '\0'; \
return g(buf, base, res); \
} \
EXPORT_SYMBOL(f)
kstrto_from_user(kstrtoull_from_user, kstrtoull, unsigned long long);
kstrto_from_user(kstrtoll_from_user, kstrtoll, long long);
kstrto_from_user(kstrtoul_from_user, kstrtoul, unsigned long);
kstrto_from_user(kstrtol_from_user, kstrtol, long);
kstrto_from_user(kstrtouint_from_user, kstrtouint, unsigned int);
kstrto_from_user(kstrtoint_from_user, kstrtoint, int);
kstrto_from_user(kstrtou16_from_user, kstrtou16, u16);
kstrto_from_user(kstrtos16_from_user, kstrtos16, s16);
kstrto_from_user(kstrtou8_from_user, kstrtou8, u8);
kstrto_from_user(kstrtos8_from_user, kstrtos8, s8);