linux/lib/string_helpers.c

699 lines
16 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Helpers for formatting and printing strings
*
* Copyright 31 August 2008 James Bottomley
* Copyright (C) 2013, Intel Corporation
*/
#include <linux/bug.h>
#include <linux/kernel.h>
#include <linux/math64.h>
#include <linux/export.h>
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/limits.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/string_helpers.h>
/**
* string_get_size - get the size in the specified units
* @size: The size to be converted in blocks
* @blk_size: Size of the block (use 1 for size in bytes)
* @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
* giving the size in the required units. @buf should have room for
* at least 9 bytes and will always be zero terminated.
*
*/
void string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
char *buf, int len)
{
static const char *const units_10[] = {
"B", "kB", "MB", "GB", "TB", "PB", "EB", "ZB", "YB"
};
static const char *const units_2[] = {
"B", "KiB", "MiB", "GiB", "TiB", "PiB", "EiB", "ZiB", "YiB"
};
static const char *const *const units_str[] = {
[STRING_UNITS_10] = units_10,
[STRING_UNITS_2] = units_2,
};
static const unsigned int divisor[] = {
[STRING_UNITS_10] = 1000,
[STRING_UNITS_2] = 1024,
};
static const unsigned int rounding[] = { 500, 50, 5 };
int i = 0, j;
u32 remainder = 0, sf_cap;
char tmp[8];
const char *unit;
tmp[0] = '\0';
if (blk_size == 0)
size = 0;
if (size == 0)
goto out;
/* 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]);
i++;
}
while (size >> 32) {
do_div(size, divisor[units]);
i++;
}
/* now perform the actual multiplication keeping i as the sum of the
* two logarithms */
size *= blk_size;
/* and logarithmically reduce it until it's just under the divisor */
while (size >= divisor[units]) {
remainder = do_div(size, divisor[units]);
i++;
}
/* work out in j how many digits of precision we need from the
* remainder */
sf_cap = size;
for (j = 0; sf_cap*10 < 1000; j++)
sf_cap *= 10;
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 */
remainder *= 1000;
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) {
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];
snprintf(buf, len, "%u%s %s", (u32)size,
tmp, unit);
}
EXPORT_SYMBOL(string_get_size);
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;
}
/**
* 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.
*
* 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. The supported flags are::
*
* 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
*
* Return:
* The amount of the characters processed to the destination buffer excluding
* trailing '\0' is returned.
*/
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);
static bool escape_passthrough(unsigned char c, char **dst, char *end)
{
char *out = *dst;
if (out < end)
*out = c;
*dst = out + 1;
return true;
}
static bool escape_space(unsigned char c, char **dst, char *end)
{
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:
return false;
}
if (out < end)
*out = '\\';
++out;
if (out < end)
*out = to;
++out;
*dst = out;
return true;
}
static bool escape_special(unsigned char c, char **dst, char *end)
{
char *out = *dst;
unsigned char to;
switch (c) {
case '\\':
to = '\\';
break;
case '\a':
to = 'a';
break;
case '\e':
to = 'e';
break;
string_helpers: Escape double quotes in escape_special From an abstract point of view, escape_special's counterpart, unescape_special, already handles the unescaping of blackslashed double quote sequences. As a more practical example, printk indexing is an example case where this is already practically useful. Compare an example with `ESCAPE_SPECIAL | ESCAPE_SPACE`, with quotes not escaped: [root@ktst ~]# grep drivers/pci/pci-stub.c:69 /sys/kernel/debug/printk/index/vmlinux <4> drivers/pci/pci-stub.c:69 pci_stub_init "pci-stub: invalid ID string "%s"\n" ...and the same after this patch: [root@ktst ~]# grep drivers/pci/pci-stub.c:69 /sys/kernel/debug/printk/index/vmlinux <4> drivers/pci/pci-stub.c:69 pci_stub_init "pci-stub: invalid ID string \"%s\"\n" One can of course, alternatively, use ESCAPE_APPEND with a quote in @only, but without this patch quotes are coerced into hex or octal which can hurt readability quite significantly. I've checked uses of ESCAPE_SPECIAL and %pE across the codebase, and I'm pretty confident that this shouldn't affect any stable interfaces. Signed-off-by: Chris Down <chris@chrisdown.name> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/af144c5b75e41ce417386253ba2694456bc04118.1623775748.git.chris@chrisdown.name
2021-06-16 00:52:45 +08:00
case '"':
to = '"';
break;
default:
return false;
}
if (out < end)
*out = '\\';
++out;
if (out < end)
*out = to;
++out;
*dst = out;
return true;
}
static bool escape_null(unsigned char c, char **dst, char *end)
{
char *out = *dst;
if (c)
return false;
if (out < end)
*out = '\\';
++out;
if (out < end)
*out = '0';
++out;
*dst = out;
return true;
}
static bool escape_octal(unsigned char c, char **dst, char *end)
{
char *out = *dst;
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;
*dst = out;
return true;
}
static bool escape_hex(unsigned char c, char **dst, char *end)
{
char *out = *dst;
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;
*dst = out;
return true;
}
/**
* 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
* @only: NULL-terminated string containing characters used to limit
* the selected escape class. If characters are included in @only
* that would not normally be escaped by the classes selected
* in @flags, they will be copied to @dst unescaped.
*
* Description:
* The process of escaping byte buffer includes several parts. They are applied
* in the following sequence.
*
* 1. The character is not matched to the one from @only string and thus
* must go as-is to the output.
* 2. The character is matched to the printable and ASCII classes, if asked,
* and in case of match it passes through to the output.
* 3. The character is matched to the printable or ASCII class, if asked,
* and in case of match it passes through to the output.
* 4. 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. The supported flags are::
*
* %ESCAPE_SPACE: (special white space, not space itself)
* '\f' - form feed
* '\n' - new line
* '\r' - carriage return
* '\t' - horizontal tab
* '\v' - vertical tab
* %ESCAPE_SPECIAL:
string_helpers: Escape double quotes in escape_special From an abstract point of view, escape_special's counterpart, unescape_special, already handles the unescaping of blackslashed double quote sequences. As a more practical example, printk indexing is an example case where this is already practically useful. Compare an example with `ESCAPE_SPECIAL | ESCAPE_SPACE`, with quotes not escaped: [root@ktst ~]# grep drivers/pci/pci-stub.c:69 /sys/kernel/debug/printk/index/vmlinux <4> drivers/pci/pci-stub.c:69 pci_stub_init "pci-stub: invalid ID string "%s"\n" ...and the same after this patch: [root@ktst ~]# grep drivers/pci/pci-stub.c:69 /sys/kernel/debug/printk/index/vmlinux <4> drivers/pci/pci-stub.c:69 pci_stub_init "pci-stub: invalid ID string \"%s\"\n" One can of course, alternatively, use ESCAPE_APPEND with a quote in @only, but without this patch quotes are coerced into hex or octal which can hurt readability quite significantly. I've checked uses of ESCAPE_SPECIAL and %pE across the codebase, and I'm pretty confident that this shouldn't affect any stable interfaces. Signed-off-by: Chris Down <chris@chrisdown.name> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com> Signed-off-by: Petr Mladek <pmladek@suse.com> Link: https://lore.kernel.org/r/af144c5b75e41ce417386253ba2694456bc04118.1623775748.git.chris@chrisdown.name
2021-06-16 00:52:45 +08:00
* '\"' - double quote
* '\\' - 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)
* %ESCAPE_NA:
* escape only non-ascii characters, checked by isascii()
* %ESCAPE_NAP:
* escape only non-printable or non-ascii characters
* %ESCAPE_APPEND:
* append characters from @only to be escaped by the given classes
*
* %ESCAPE_APPEND would help to pass additional characters to the escaped, when
* one of %ESCAPE_NP, %ESCAPE_NA, or %ESCAPE_NAP is provided.
*
* One notable caveat, the %ESCAPE_NAP, %ESCAPE_NP and %ESCAPE_NA have the
* higher priority than the rest of the flags (%ESCAPE_NAP is the highest).
* It doesn't make much sense to use either of them without %ESCAPE_OCTAL
* or %ESCAPE_HEX, because they cover most of the other character classes.
* %ESCAPE_NAP can utilize %ESCAPE_SPACE or %ESCAPE_SPECIAL in addition to
* the above.
*
* Return:
lib/string_helpers.c: change semantics of string_escape_mem The current semantics of string_escape_mem are inadequate for one of its current users, vsnprintf(). If that is to honour its contract, it must know how much space would be needed for the entire escaped buffer, and string_escape_mem provides no way of obtaining that (short of allocating a large enough buffer (~4 times input string) to let it play with, and that's definitely a big no-no inside vsnprintf). So change the semantics for string_escape_mem to be more snprintf-like: Return the size of the output that would be generated if the destination buffer was big enough, but of course still only write to the part of dst it is allowed to, and (contrary to snprintf) don't do '\0'-termination. It is then up to the caller to detect whether output was truncated and to append a '\0' if desired. Also, we must output partial escape sequences, otherwise a call such as snprintf(buf, 3, "%1pE", "\123") would cause printf to write a \0 to buf[2] but leaving buf[0] and buf[1] with whatever they previously contained. This also fixes a bug in the escaped_string() helper function, which used to unconditionally pass a length of "end-buf" to string_escape_mem(); since the latter doesn't check osz for being insanely large, it would happily write to dst. For example, kasprintf(GFP_KERNEL, "something and then %pE", ...); is an easy way to trigger an oops. In test-string_helpers.c, the -ENOMEM test is replaced with testing for getting the expected return value even if the buffer is too small. We also ensure that nothing is written (by relying on a NULL pointer deref) if the output size is 0 by passing NULL - this has to work for kasprintf("%pE") to work. In net/sunrpc/cache.c, I think qword_add still has the same semantics. Someone should definitely double-check this. In fs/proc/array.c, I made the minimum possible change, but longer-term it should stop poking around in seq_file internals. [andriy.shevchenko@linux.intel.com: simplify qword_add] [andriy.shevchenko@linux.intel.com: add missed curly braces] Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Acked-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:17:28 +08:00
* 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.
*/
lib/string_helpers.c: change semantics of string_escape_mem The current semantics of string_escape_mem are inadequate for one of its current users, vsnprintf(). If that is to honour its contract, it must know how much space would be needed for the entire escaped buffer, and string_escape_mem provides no way of obtaining that (short of allocating a large enough buffer (~4 times input string) to let it play with, and that's definitely a big no-no inside vsnprintf). So change the semantics for string_escape_mem to be more snprintf-like: Return the size of the output that would be generated if the destination buffer was big enough, but of course still only write to the part of dst it is allowed to, and (contrary to snprintf) don't do '\0'-termination. It is then up to the caller to detect whether output was truncated and to append a '\0' if desired. Also, we must output partial escape sequences, otherwise a call such as snprintf(buf, 3, "%1pE", "\123") would cause printf to write a \0 to buf[2] but leaving buf[0] and buf[1] with whatever they previously contained. This also fixes a bug in the escaped_string() helper function, which used to unconditionally pass a length of "end-buf" to string_escape_mem(); since the latter doesn't check osz for being insanely large, it would happily write to dst. For example, kasprintf(GFP_KERNEL, "something and then %pE", ...); is an easy way to trigger an oops. In test-string_helpers.c, the -ENOMEM test is replaced with testing for getting the expected return value even if the buffer is too small. We also ensure that nothing is written (by relying on a NULL pointer deref) if the output size is 0 by passing NULL - this has to work for kasprintf("%pE") to work. In net/sunrpc/cache.c, I think qword_add still has the same semantics. Someone should definitely double-check this. In fs/proc/array.c, I made the minimum possible change, but longer-term it should stop poking around in seq_file internals. [andriy.shevchenko@linux.intel.com: simplify qword_add] [andriy.shevchenko@linux.intel.com: add missed curly braces] Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Acked-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:17:28 +08:00
int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz,
unsigned int flags, const char *only)
{
lib/string_helpers.c: change semantics of string_escape_mem The current semantics of string_escape_mem are inadequate for one of its current users, vsnprintf(). If that is to honour its contract, it must know how much space would be needed for the entire escaped buffer, and string_escape_mem provides no way of obtaining that (short of allocating a large enough buffer (~4 times input string) to let it play with, and that's definitely a big no-no inside vsnprintf). So change the semantics for string_escape_mem to be more snprintf-like: Return the size of the output that would be generated if the destination buffer was big enough, but of course still only write to the part of dst it is allowed to, and (contrary to snprintf) don't do '\0'-termination. It is then up to the caller to detect whether output was truncated and to append a '\0' if desired. Also, we must output partial escape sequences, otherwise a call such as snprintf(buf, 3, "%1pE", "\123") would cause printf to write a \0 to buf[2] but leaving buf[0] and buf[1] with whatever they previously contained. This also fixes a bug in the escaped_string() helper function, which used to unconditionally pass a length of "end-buf" to string_escape_mem(); since the latter doesn't check osz for being insanely large, it would happily write to dst. For example, kasprintf(GFP_KERNEL, "something and then %pE", ...); is an easy way to trigger an oops. In test-string_helpers.c, the -ENOMEM test is replaced with testing for getting the expected return value even if the buffer is too small. We also ensure that nothing is written (by relying on a NULL pointer deref) if the output size is 0 by passing NULL - this has to work for kasprintf("%pE") to work. In net/sunrpc/cache.c, I think qword_add still has the same semantics. Someone should definitely double-check this. In fs/proc/array.c, I made the minimum possible change, but longer-term it should stop poking around in seq_file internals. [andriy.shevchenko@linux.intel.com: simplify qword_add] [andriy.shevchenko@linux.intel.com: add missed curly braces] Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Acked-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:17:28 +08:00
char *p = dst;
char *end = p + osz;
bool is_dict = only && *only;
bool is_append = flags & ESCAPE_APPEND;
while (isz--) {
unsigned char c = *src++;
bool in_dict = is_dict && strchr(only, c);
/*
* Apply rules in the following sequence:
* - the @only string is supplied and does not contain a
* character under question
* - the character is printable and ASCII, when @flags has
* %ESCAPE_NAP bit set
* - the character is printable, when @flags has
* %ESCAPE_NP bit set
* - the character is ASCII, when @flags has
* %ESCAPE_NA bit set
* - 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.
*
* When %ESCAPE_APPEND is passed, the characters from @only
* have been excluded from the %ESCAPE_NAP, %ESCAPE_NP, and
* %ESCAPE_NA cases.
*/
if (!(is_append || in_dict) && is_dict &&
escape_passthrough(c, &p, end))
continue;
if (!(is_append && in_dict) && isascii(c) && isprint(c) &&
flags & ESCAPE_NAP && escape_passthrough(c, &p, end))
continue;
if (!(is_append && in_dict) && isprint(c) &&
flags & ESCAPE_NP && escape_passthrough(c, &p, end))
continue;
if (!(is_append && in_dict) && isascii(c) &&
flags & ESCAPE_NA && escape_passthrough(c, &p, end))
continue;
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;
/* ESCAPE_OCTAL and ESCAPE_HEX always go last */
if (flags & ESCAPE_OCTAL && escape_octal(c, &p, end))
continue;
if (flags & ESCAPE_HEX && escape_hex(c, &p, end))
continue;
escape_passthrough(c, &p, end);
}
lib/string_helpers.c: change semantics of string_escape_mem The current semantics of string_escape_mem are inadequate for one of its current users, vsnprintf(). If that is to honour its contract, it must know how much space would be needed for the entire escaped buffer, and string_escape_mem provides no way of obtaining that (short of allocating a large enough buffer (~4 times input string) to let it play with, and that's definitely a big no-no inside vsnprintf). So change the semantics for string_escape_mem to be more snprintf-like: Return the size of the output that would be generated if the destination buffer was big enough, but of course still only write to the part of dst it is allowed to, and (contrary to snprintf) don't do '\0'-termination. It is then up to the caller to detect whether output was truncated and to append a '\0' if desired. Also, we must output partial escape sequences, otherwise a call such as snprintf(buf, 3, "%1pE", "\123") would cause printf to write a \0 to buf[2] but leaving buf[0] and buf[1] with whatever they previously contained. This also fixes a bug in the escaped_string() helper function, which used to unconditionally pass a length of "end-buf" to string_escape_mem(); since the latter doesn't check osz for being insanely large, it would happily write to dst. For example, kasprintf(GFP_KERNEL, "something and then %pE", ...); is an easy way to trigger an oops. In test-string_helpers.c, the -ENOMEM test is replaced with testing for getting the expected return value even if the buffer is too small. We also ensure that nothing is written (by relying on a NULL pointer deref) if the output size is 0 by passing NULL - this has to work for kasprintf("%pE") to work. In net/sunrpc/cache.c, I think qword_add still has the same semantics. Someone should definitely double-check this. In fs/proc/array.c, I made the minimum possible change, but longer-term it should stop poking around in seq_file internals. [andriy.shevchenko@linux.intel.com: simplify qword_add] [andriy.shevchenko@linux.intel.com: add missed curly braces] Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Acked-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-04-16 07:17:28 +08:00
return p - dst;
}
EXPORT_SYMBOL(string_escape_mem);
/*
* 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);
/*
* 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;
mm: treewide: remove GFP_TEMPORARY allocation flag GFP_TEMPORARY was introduced by commit e12ba74d8ff3 ("Group short-lived and reclaimable kernel allocations") along with __GFP_RECLAIMABLE. It's primary motivation was to allow users to tell that an allocation is short lived and so the allocator can try to place such allocations close together and prevent long term fragmentation. As much as this sounds like a reasonable semantic it becomes much less clear when to use the highlevel GFP_TEMPORARY allocation flag. How long is temporary? Can the context holding that memory sleep? Can it take locks? It seems there is no good answer for those questions. The current implementation of GFP_TEMPORARY is basically GFP_KERNEL | __GFP_RECLAIMABLE which in itself is tricky because basically none of the existing caller provide a way to reclaim the allocated memory. So this is rather misleading and hard to evaluate for any benefits. I have checked some random users and none of them has added the flag with a specific justification. I suspect most of them just copied from other existing users and others just thought it might be a good idea to use without any measuring. This suggests that GFP_TEMPORARY just motivates for cargo cult usage without any reasoning. I believe that our gfp flags are quite complex already and especially those with highlevel semantic should be clearly defined to prevent from confusion and abuse. Therefore I propose dropping GFP_TEMPORARY and replace all existing users to simply use GFP_KERNEL. Please note that SLAB users with shrinkers will still get __GFP_RECLAIMABLE heuristic and so they will be placed properly for memory fragmentation prevention. I can see reasons we might want some gfp flag to reflect shorterm allocations but I propose starting from a clear semantic definition and only then add users with proper justification. This was been brought up before LSF this year by Matthew [1] and it turned out that GFP_TEMPORARY really doesn't have a clear semantic. It seems to be a heuristic without any measured advantage for most (if not all) its current users. The follow up discussion has revealed that opinions on what might be temporary allocation differ a lot between developers. So rather than trying to tweak existing users into a semantic which they haven't expected I propose to simply remove the flag and start from scratch if we really need a semantic for short term allocations. [1] http://lkml.kernel.org/r/20170118054945.GD18349@bombadil.infradead.org [akpm@linux-foundation.org: fix typo] [akpm@linux-foundation.org: coding-style fixes] [sfr@canb.auug.org.au: drm/i915: fix up] Link: http://lkml.kernel.org/r/20170816144703.378d4f4d@canb.auug.org.au Link: http://lkml.kernel.org/r/20170728091904.14627-1-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Neil Brown <neilb@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-14 07:28:29 +08:00
buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
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);
/*
* 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 */
mm: treewide: remove GFP_TEMPORARY allocation flag GFP_TEMPORARY was introduced by commit e12ba74d8ff3 ("Group short-lived and reclaimable kernel allocations") along with __GFP_RECLAIMABLE. It's primary motivation was to allow users to tell that an allocation is short lived and so the allocator can try to place such allocations close together and prevent long term fragmentation. As much as this sounds like a reasonable semantic it becomes much less clear when to use the highlevel GFP_TEMPORARY allocation flag. How long is temporary? Can the context holding that memory sleep? Can it take locks? It seems there is no good answer for those questions. The current implementation of GFP_TEMPORARY is basically GFP_KERNEL | __GFP_RECLAIMABLE which in itself is tricky because basically none of the existing caller provide a way to reclaim the allocated memory. So this is rather misleading and hard to evaluate for any benefits. I have checked some random users and none of them has added the flag with a specific justification. I suspect most of them just copied from other existing users and others just thought it might be a good idea to use without any measuring. This suggests that GFP_TEMPORARY just motivates for cargo cult usage without any reasoning. I believe that our gfp flags are quite complex already and especially those with highlevel semantic should be clearly defined to prevent from confusion and abuse. Therefore I propose dropping GFP_TEMPORARY and replace all existing users to simply use GFP_KERNEL. Please note that SLAB users with shrinkers will still get __GFP_RECLAIMABLE heuristic and so they will be placed properly for memory fragmentation prevention. I can see reasons we might want some gfp flag to reflect shorterm allocations but I propose starting from a clear semantic definition and only then add users with proper justification. This was been brought up before LSF this year by Matthew [1] and it turned out that GFP_TEMPORARY really doesn't have a clear semantic. It seems to be a heuristic without any measured advantage for most (if not all) its current users. The follow up discussion has revealed that opinions on what might be temporary allocation differ a lot between developers. So rather than trying to tweak existing users into a semantic which they haven't expected I propose to simply remove the flag and start from scratch if we really need a semantic for short term allocations. [1] http://lkml.kernel.org/r/20170118054945.GD18349@bombadil.infradead.org [akpm@linux-foundation.org: fix typo] [akpm@linux-foundation.org: coding-style fixes] [sfr@canb.auug.org.au: drm/i915: fix up] Link: http://lkml.kernel.org/r/20170816144703.378d4f4d@canb.auug.org.au Link: http://lkml.kernel.org/r/20170728091904.14627-1-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox <willy@infradead.org> Cc: Neil Brown <neilb@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-14 07:28:29 +08:00
temp = kmalloc(PATH_MAX + 11, GFP_KERNEL);
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);
/**
* kfree_strarray - free a number of dynamically allocated strings contained
* in an array and the array itself
*
* @array: Dynamically allocated array of strings to free.
* @n: Number of strings (starting from the beginning of the array) to free.
*
* Passing a non-NULL @array and @n == 0 as well as NULL @array are valid
* use-cases. If @array is NULL, the function does nothing.
*/
void kfree_strarray(char **array, size_t n)
{
unsigned int i;
if (!array)
return;
for (i = 0; i < n; i++)
kfree(array[i]);
kfree(array);
}
EXPORT_SYMBOL_GPL(kfree_strarray);