diff mbox series

[v6,2/4] lib: vsprintf: Fix handling of number field widths in vsscanf

Message ID 20210209155604.6998-2-rf@opensource.cirrus.com (mailing list archive)
State New
Headers show
Series [v6,1/4] lib: vsprintf: scanf: Negative number must have field width > 1 | expand

Commit Message

Richard Fitzgerald Feb. 9, 2021, 3:56 p.m. UTC
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>
---
Changed since v5:
- Use INT_MAX to mean "unlimited length".
- Rework simple_strntoull() to avoid the goto
- Rewrite the comment in simple_strntoll()
- In vsscanf() change the calls to simple_strnto[u]ll() so that a field_width
  of 0 is not treated as unlimited.

Changed since v3:
- Use INT_MAX to mean "unlimited length".
- Use while-loop instead of for-loop in _parse_integer_limit().
- Keep the existing arguments for _parse_integer() on their original line.
  And the corresponding arguments to _parse_integer_limit() formatted/wrapped
  the same way as _parse_integer().
- Remove redundant check for (max_chars == 0) in simple_strntoull().
- Fixed "vsscanf" -> "vsscanf()" in commit message.
---
 lib/kstrtox.c  | 13 ++++++--
 lib/kstrtox.h  |  2 ++
 lib/vsprintf.c | 88 +++++++++++++++++++++++++++++---------------------
 3 files changed, 63 insertions(+), 40 deletions(-)

Comments

Petr Mladek Feb. 11, 2021, 1:48 p.m. UTC | #1
On Tue 2021-02-09 15:56:02, Richard Fitzgerald wrote:
> 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>

The patchset looks ready for upstream from my POV.

Best Regards,
Petr
diff mbox series

Patch

diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index a118b0b1e9b2..0b5fe8b41173 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -39,20 +39,22 @@  const char *_parse_integer_fixup_radix(const char *s, unsigned int *base)
 
 /*
  * Convert non-negative integer string representation in explicitly given radix
- * to an integer.
+ * 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(const char *s, unsigned int base, unsigned long long *p)
+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 (1) {
+	while (max_chars--) {
 		unsigned int c = *s;
 		unsigned int lc = c | 0x20; /* don't tolower() this line */
 		unsigned int val;
@@ -82,6 +84,11 @@  unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long
 	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;
diff --git a/lib/kstrtox.h b/lib/kstrtox.h
index 3b4637bcd254..158c400ca865 100644
--- a/lib/kstrtox.h
+++ b/lib/kstrtox.h
@@ -4,6 +4,8 @@ 
 
 #define KSTRTOX_OVERFLOW	(1U << 31)
 const char *_parse_integer_fixup_radix(const char *s, unsigned int *base);
+unsigned int _parse_integer_limit(const char *s, unsigned int base, unsigned long long *res,
+				  size_t max_chars);
 unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *res);
 
 #endif
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 28bb26cd1f67..794ecc373bf9 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -53,29 +53,43 @@ 
 #include <linux/string_helpers.h>
 #include "kstrtox.h"
 
-/**
- * simple_strtoull - convert a string to an unsigned long long
- * @cp: The start of the string
- * @endp: A pointer to the end of the parsed string will be placed here
- * @base: The number base to use
- *
- * This function has caveats. Please use kstrtoull instead.
- */
-unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base)
+static unsigned long long simple_strntoull(const char *startp, size_t max_chars,
+					   char **endp, unsigned int base)
 {
-	unsigned long long result;
+	const char *cp;
+	unsigned long long result = 0ULL;
+	size_t prefix_chars;
 	unsigned int rv;
 
-	cp = _parse_integer_fixup_radix(cp, &base);
-	rv = _parse_integer(cp, base, &result);
-	/* FIXME */
-	cp += (rv & ~KSTRTOX_OVERFLOW);
+	cp = _parse_integer_fixup_radix(startp, &base);
+	prefix_chars = cp - startp;
+	if (prefix_chars < max_chars) {
+		rv = _parse_integer_limit(cp, base, &result, max_chars - prefix_chars);
+		/* FIXME */
+		cp += (rv & ~KSTRTOX_OVERFLOW);
+	} else {
+		/* Field too short for prefix + digit, skip over without converting */
+		cp = startp + max_chars;
+	}
 
 	if (endp)
 		*endp = (char *)cp;
 
 	return result;
 }
+
+/**
+ * simple_strtoull - convert a string to an unsigned long long
+ * @cp: The start of the string
+ * @endp: A pointer to the end of the parsed string will be placed here
+ * @base: The number base to use
+ *
+ * This function has caveats. Please use kstrtoull instead.
+ */
+unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base)
+{
+	return simple_strntoull(cp, INT_MAX, endp, base);
+}
 EXPORT_SYMBOL(simple_strtoull);
 
 /**
@@ -88,7 +102,7 @@  EXPORT_SYMBOL(simple_strtoull);
  */
 unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base)
 {
-	return simple_strtoull(cp, endp, base);
+	return simple_strntoull(cp, INT_MAX, endp, base);
 }
 EXPORT_SYMBOL(simple_strtoul);
 
@@ -109,6 +123,21 @@  long simple_strtol(const char *cp, char **endp, unsigned int base)
 }
 EXPORT_SYMBOL(simple_strtol);
 
+static long long simple_strntoll(const char *cp, size_t max_chars, char **endp,
+				 unsigned int base)
+{
+	/*
+	 * simple_strntoull() safely handles receiving max_chars==0 in the
+	 * case cp[0] == '-' && max_chars == 1.
+	 * If max_chars == 0 we can drop through and pass it to simple_strntoull()
+	 * and the content of *cp is irrelevant.
+	 */
+	if (*cp == '-' && max_chars > 0)
+		return -simple_strntoull(cp + 1, max_chars - 1, endp, base);
+
+	return simple_strntoull(cp, max_chars, endp, base);
+}
+
 /**
  * simple_strtoll - convert a string to a signed long long
  * @cp: The start of the string
@@ -119,10 +148,7 @@  EXPORT_SYMBOL(simple_strtol);
  */
 long long simple_strtoll(const char *cp, char **endp, unsigned int base)
 {
-	if (*cp == '-')
-		return -simple_strtoull(cp + 1, endp, base);
-
-	return simple_strtoull(cp, endp, base);
+	return simple_strntoll(cp, INT_MAX, endp, base);
 }
 EXPORT_SYMBOL(simple_strtoll);
 
@@ -3449,25 +3475,13 @@  int vsscanf(const char *buf, const char *fmt, va_list args)
 			break;
 
 		if (is_sign)
-			val.s = qualifier != 'L' ?
-				simple_strtol(str, &next, base) :
-				simple_strtoll(str, &next, base);
+			val.s = simple_strntoll(str,
+						field_width >= 0 ? field_width : INT_MAX,
+						&next, base);
 		else
-			val.u = qualifier != 'L' ?
-				simple_strtoul(str, &next, base) :
-				simple_strtoull(str, &next, base);
-
-		if (field_width > 0 && next - str > field_width) {
-			if (base == 0)
-				_parse_integer_fixup_radix(str, &base);
-			while (next - str > field_width) {
-				if (is_sign)
-					val.s = div_s64(val.s, base);
-				else
-					val.u = div_u64(val.u, base);
-				--next;
-			}
-		}
+			val.u = simple_strntoull(str,
+						 field_width >= 0 ? field_width : INT_MAX,
+						 &next, base);
 
 		switch (qualifier) {
 		case 'H':	/* that's 'hh' in format */