Re: [PATCH RFC] sscanf: Fix integer overflow with sscanf field width

2019-05-24 Thread Jan Beulich
>>> On 23.05.19 at 19:27,  wrote:
> This fixes 53809751ac23 ("sscanf: don't ignore field widths for numeric
> conversions"). sscanf overflows integers with simple strings such as dates.
> As an example, consider
> 
>   r = sscanf("20190523123456", "%4d%2d%2d%2d%2d%2d",
>   , , ,
>   , , );
> 
>   pr_info("%d %04d-%02d-%2d %02d:%02d:%02d\n",
>   r,
>   year, month, day,
>   hour, minute, second);
> 
> On a 32-bit machine this prints
> 
>   6 -05-23 12:34:56
> 
> where the year is zero, and not 2019 as expected. The reason is that sscanf
> attempts to read 20190523123456 as a whole integer and then divide it with
> 10^10 to obtain 2019, which obviously fails. Of course, 64-bit machines fail
> similarly on longer numerical strings.

Right, and that's also what that commit's description says remains as
non-conforming behavior.

> I'm offering a simple patch to correct this below. The idea is to have a
> variant of _parse_integer() called _parse_integer_end(), with the ability
> to stop consuming digits. The functions
> 
>   simple_{strtol,strtoll,strtoul,strtoull}()
> 
> now have the corresponding
> 
>   sscanf_{strtol,strtoll,strtoul,strtoull}()
> 
> taking a field width into account. There are some code duplication issues
> etc. so one might consider making more extensive changes than these.

I'm not the maintainer here, but to me it looks mostly okay.

> +static long sscanf_strtol(const char *cp, int field_width,
> + char **endp, unsigned int base)
> +{
> + if (*cp == '-')
> + return -sscanf_strtoul(cp + 1, field_width - 1, endp, base);

I'm afraid you may neither convert a field width of zero to -1 here,
nor convert a field width of 1 to zero (unlimited).

I'd also like to note that the 'u' and 'x' format characters also accept
a sign as per the standard, but that's an orthogonal issue which you
may or may not want to address at the same time.

Jan




Re: [PATCH RFC] sscanf: Fix integer overflow with sscanf field width

2019-05-23 Thread Alexey Dobriyan
> What are your thoughts?

Don't use sscanf(3), it is misdesigned.


[PATCH RFC] sscanf: Fix integer overflow with sscanf field width

2019-05-23 Thread Fredrik Noring
Hi,

This fixes 53809751ac23 ("sscanf: don't ignore field widths for numeric
conversions"). sscanf overflows integers with simple strings such as dates.
As an example, consider

r = sscanf("20190523123456", "%4d%2d%2d%2d%2d%2d",
, , ,
, , );

pr_info("%d %04d-%02d-%2d %02d:%02d:%02d\n",
r,
year, month, day,
hour, minute, second);

On a 32-bit machine this prints

6 -05-23 12:34:56

where the year is zero, and not 2019 as expected. The reason is that sscanf
attempts to read 20190523123456 as a whole integer and then divide it with
10^10 to obtain 2019, which obviously fails. Of course, 64-bit machines fail
similarly on longer numerical strings.

I'm offering a simple patch to correct this below. The idea is to have a
variant of _parse_integer() called _parse_integer_end(), with the ability
to stop consuming digits. The functions

simple_{strtol,strtoll,strtoul,strtoull}()

now have the corresponding

sscanf_{strtol,strtoll,strtoul,strtoull}()

taking a field width into account. There are some code duplication issues
etc. so one might consider making more extensive changes than these.

What are your thoughts?

Fredrik

diff --git a/lib/kstrtox.c b/lib/kstrtox.c
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -45,14 +45,15 @@ const char *_parse_integer_fixup_radix(const char *s, 
unsigned int *base)
  *
  * 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_end(const char *s, const char *e,
+   unsigned int base, unsigned long long *p)
 {
unsigned long long res;
unsigned int rv;
 
res = 0;
rv = 0;
-   while (1) {
+   while (!e || s < e) {
unsigned int c = *s;
unsigned int lc = c | 0x20; /* don't tolower() this line */
unsigned int val;
@@ -82,6 +83,11 @@ 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_end(s, NULL, base, p);
+}
+
 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
--- 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_end(const char *s, const char *e,
+   unsigned int base, unsigned long long *p);
 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
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -123,6 +123,48 @@ long long simple_strtoll(const char *cp, char **endp, 
unsigned int base)
 }
 EXPORT_SYMBOL(simple_strtoll);
 
+static unsigned long long sscanf_strtoull(const char *cp, int field_width,
+   char **endp, unsigned int base)
+{
+   const char *e = field_width > 0 ? [field_width] : NULL;
+   unsigned long long result;
+   unsigned int rv;
+
+   cp = _parse_integer_fixup_radix(cp, );
+   rv = _parse_integer_end(cp, e, base, );
+   /* FIXME */
+   cp += (rv & ~KSTRTOX_OVERFLOW);
+
+   if (endp)
+   *endp = (char *)cp;
+
+   return result;
+}
+
+static unsigned long sscanf_strtoul(const char *cp, int field_width,
+   char **endp, unsigned int base)
+{
+   return sscanf_strtoull(cp, field_width, endp, base);
+}
+
+static long sscanf_strtol(const char *cp, int field_width,
+   char **endp, unsigned int base)
+{
+   if (*cp == '-')
+   return -sscanf_strtoul(cp + 1, field_width - 1, endp, base);
+
+   return sscanf_strtoul(cp, field_width, endp, base);
+}
+
+static long long sscanf_strtoll(const char *cp, int field_width,
+   char **endp, unsigned int base)
+{
+   if (*cp == '-')
+   return -sscanf_strtoull(cp + 1, field_width - 1, endp, base);
+
+   return sscanf_strtoull(cp, field_width, endp, base);
+}
+
 static noinline_for_stack
 int skip_atoi(const char **s)
 {
@@ -3330,24 +3372,12 @@ int vsscanf(const char *buf, const char *fmt, va_list 
args)
 
if (is_sign)
val.s = qualifier != 'L' ?
-   simple_strtol(str, , base) :
-   simple_strtoll(str, , base);
+   sscanf_strtol(str, field_width, , base) :
+   sscanf_strtoll(str, field_width, , base);
else
val.u = qualifier != 'L' ?
-   simple_strtoul(str, , base) :
-   simple_strtoull(str, , base);
-
-   if (field_width > 0 && next - str > field_width) {