xgetbv nondeterminism

From	Andy Lutomirski <luto@kernel.org>
Newsgroups	linux.kernel
Subject	xgetbv nondeterminism
Date	2017-06-15 07:20 +0200
Message-ID	<tSvmh-6IX-1@gated-at.bofh.it> (permalink)
Organization	linux.* mail to news gateway

Show all headers | View raw

I saw your post about XGETBV
(http://robert.ocallahan.org/2017/06/another-case-of-obscure-cpu.html),
and it sounds like it could plausibly be a kernel bug.  What kernel
are you on?

I wonder if CPUs have an optimization in which, if a given register
set is in the init state but XINUSE=1, then they'll notice when
XRSTORS runs and clear XINUSE.  If so, that would be rather
unfortunate IMO.

Dave, why is XINUSE exposed at all to userspace?  IIRC it's visible
via XGETBV, XSAVEC, and maybe even XSAVE, and ISTM that making it
visible to userspace serves basically no performance purpose and just
encourages annoying corner cases.  I can see an argument that making
XSAVEC fast is nice for user threading libraries, but user threading
libraries that use XSAVEC are probably doing it wrong and should
instead rely on ABI guarantees to avoid saving and restoring extended
state at all.

To be fair, glibc uses this new XGETBV feature, but I suspect its
usage is rather dubious.  Shouldn't it just do XSAVEC directly rather
than rolling its own code?

Back to linux.kernel | Previous | Next — Next in thread | Find similar | Unroll thread

Thread

xgetbv nondeterminism Andy Lutomirski <luto@kernel.org> - 2017-06-15 07:20 +0200
  Re: xgetbv nondeterminism Dave Hansen <dave.hansen@intel.com> - 2017-06-15 16:40 +0200
    Re: xgetbv nondeterminism Andy Lutomirski <luto@kernel.org> - 2017-06-16 00:20 +0200
      Re: xgetbv nondeterminism "H.J. Lu" <hjl.tools@gmail.com> - 2017-06-16 00:50 +0200
        Re: xgetbv nondeterminism Andy Lutomirski <luto@kernel.org> - 2017-06-16 00:50 +0200
          Re: xgetbv nondeterminism "H.J. Lu" <hjl.tools@gmail.com> - 2017-06-16 01:20 +0200
            Re: xgetbv nondeterminism Andy Lutomirski <luto@kernel.org> - 2017-06-16 01:30 +0200
              Re: xgetbv nondeterminism "H.J. Lu" <hjl.tools@gmail.com> - 2017-06-16 04:20 +0200
                Re: xgetbv nondeterminism Andy Lutomirski <luto@kernel.org> - 2017-06-16 05:10 +0200
                Re: xgetbv nondeterminism "H.J. Lu" <hjl.tools@gmail.com> - 2017-06-16 06:40 +0200
                Re: xgetbv nondeterminism Andy Lutomirski <luto@kernel.org> - 2017-06-16 18:10 +0200
                Re: xgetbv nondeterminism "H.J. Lu" <hjl.tools@gmail.com> - 2017-06-16 18:20 +0200
                Re: xgetbv nondeterminism Andy Lutomirski <luto@kernel.org> - 2017-06-16 18:40 +0200
                Re: xgetbv nondeterminism "H.J. Lu" <hjl.tools@gmail.com> - 2017-06-16 19:50 +0200
                Re: xgetbv nondeterminism Andy Lutomirski <luto@kernel.org> - 2017-06-16 20:00 +0200
                Re: xgetbv nondeterminism "H.J. Lu" <hjl.tools@gmail.com> - 2017-06-16 20:10 +0200
                Re: xgetbv nondeterminism Andy Lutomirski <luto@kernel.org> - 2017-06-17 08:30 +0200
                Re: xgetbv nondeterminism "H.J. Lu" <hjl.tools@gmail.com> - 2017-06-17 15:00 +0200
                Re: xgetbv nondeterminism Andy Lutomirski <luto@kernel.org> - 2017-06-17 18:40 +0200
                Re: xgetbv nondeterminism "H.J. Lu" <hjl.tools@gmail.com> - 2017-06-17 21:50 +0200
      Re: xgetbv nondeterminism Dave Hansen <dave.hansen@intel.com> - 2017-06-16 01:40 +0200
        Re: xgetbv nondeterminism "H.J. Lu" <hjl.tools@gmail.com> - 2017-06-16 04:30 +0200

csiph-web