Re: glibc qsort() vulnerability

On Wed, Feb 07, 2024 at 04:42:07PM -0800, Andres Freund wrote:
> On 2024-02-07 16:21:24 -0600, Nathan Bossart wrote:
>> The assembly for that looks encouraging, but I still need to actually test
>> it...
> 
> Possible. For 16bit upcasting to 32bit is clearly the best way. For 32 bit
> that doesn't work, given the 32bit return, so we need something more.

For the same compASC() test, I see an ~8.4% improvement with your int64
code and a ~3.4% improvement with this:

    int
    compASC(const void *a, const void *b)
    {
        int         result;

        if (unlikely(pg_sub_s32_overflow(*(const int32 *) a,
                                         *(const int32 *) b,
                                         &result)))
        {
            if (*(const int32 *) a > *(const int32 *) b)
                return 1;
            if (*(const int32 *) a < *(const int32 *) b)
                return -1;
            return 0;
        }

        return result;
    }

-- 
Nathan Bossart
Amazon Web Services: https://aws.amazon.com