Re: [Qemu-trivial] [PATCH] cutils: Assert in-range base for string-to-integer conversions

[Laurent Vivier]

Le 06/12/2018 à 17:40, Laurent Vivier a écrit :
> Le 06/12/2018 à 16:18, Eric Blake a écrit :
>> POSIX states that the value of endptr is unspecified if strtol()
>> fails with EINVAL due to an invalid base argument.  Since none of
>> the callers to check_strtox_error() initialized endptr, we could
>> end up propagating uninitialized data back to a caller on error.
>> However, passing an out-of-range base is already a sign of poor
>> programming, so let's just assert that base is in range, at which
>> point check_strtox_error() can be tightened to assert that it is
>> receiving an initialized ep that points somewhere within the
>> caller's original string, regardless of whether strto*() succeeded
>> or failed with ERANGE.
>>
>> Reported-by: Vladimir Sementsov-Ogievskiy <address@hidden>
>> Signed-off-by: Eric Blake <address@hidden>
>> ---
>>
>> Also tested that this does not negatively impact David's pending
>> additions of qemu_strtod{,_finite}().  Thus:
>> Based-on: <address@hidden>
>>
>>  util/cutils.c | 8 ++++++++
>>  1 file changed, 8 insertions(+)
>>
>> diff --git a/util/cutils.c b/util/cutils.c
>> index 91930d1bbeb..e098debdc0c 100644
>> --- a/util/cutils.c
>> +++ b/util/cutils.c
>> @@ -278,6 +278,7 @@ int qemu_strtosz_metric(const char *nptr, const char 
>> **end, uint64_t *result)
>>  static int check_strtox_error(const char *nptr, char *ep,
>>                                const char **endptr, int libc_errno)
>>  {
>> +    assert(ep >= nptr);
>>      if (endptr) {
>>          *endptr = ep;
>>      }
>> @@ -325,6 +326,7 @@ int qemu_strtoi(const char *nptr, const char **endptr, 
>> int base,
>>      char *ep;
>>      long long lresult;
>>
>> +    assert((unsigned) base <= 36 && base != 1);
> 
> If you want to play with type, I think you can do:
> 
>    assert((unsigned)(base - 2) <= 34)

oops, no, '0' is a valid case. Forgive this...

Laurent