Re: fstat(2) penalized by using newfstatat(6, "", buf, AT_EMPTY_PATH)

[Mateusz Guzik <mjguzik@gmail.com>]

On 9/5/23, Rich Felker <dalias@libc.org> wrote:
> On Tue, Sep 05, 2023 at 10:45:17AM -0700, Linus Torvalds wrote:
>> On Tue, 5 Sept 2023 at 10:28, Adhemerval Zanella Netto
>> <adhemerval.zanella@linaro.org> wrote:
>> >
>> > I think we can still make it in a generic way, stat family would use
>> > more
>> > syscall (which some filters might complain) but it should be ok:
>>
>> Ugh. That patch of yours certainly seems to avoid the kernel overhead
>> (where that "fetch a byte from user space just to check it is '\0'" is
>> much more expensive than it is in user space), but why does glibc do
>> that whole "turn fstat() into fstatat(), and then turn it back again"?
>>
>> It seems just stupid. If the user asked for 'fstat()', just give the
>> user 'fstat()'.
>
> We do it in musl, but we also do the "turn it back again" in
> userspace. musl's __fstatat_kstat checks if AT_EMPTY_PATH is set, and
> if so, calls SYS_fstat. I don't see why glibc couldn't do the same.
>
> However, we don't do this, and this does not seem to be possible, in
> the case where statx has to be used (32-bit archs). Is there an
> analogous issue for statx?
>

Yes and *currently* statx does not have a way out, but I'm going to
propose some patches to Linux about it in foreseeable future.

-- 
Mateusz Guzik <mjguzik gmail.com>