Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Florian Weimer <fweimer@redhat.com>
To:     Dave Hansen <dave.hansen@intel.com>
Cc:     libc-alpha@sourceware.org, linux-api@vger.kernel.org,
        x86@kernel.org, linux-arch@vger.kernel.org,
        "H.J. Lu" <hjl.tools@gmail.com>, linux-kernel@vger.kernel.org
Subject: Re: x86 CPU features detection for applications (and AMX)
References: <87tulo39ms.fsf@oldenburg.str.redhat.com>
        <e376bcb9-cd79-7665-5859-ae808dd286f1@intel.com>
        <878s2hz6g3.fsf@oldenburg.str.redhat.com>
        <b3b104cd-72d9-7f5c-116b-414c6ebf448d@intel.com>
Date:   Thu, 08 Jul 2021 16:31:28 +0200
In-Reply-To: <b3b104cd-72d9-7f5c-116b-414c6ebf448d@intel.com> (Dave Hansen's
        message of "Thu, 8 Jul 2021 07:19:21 -0700")
Message-ID: <87sg0oswqn.fsf@oldenburg.str.redhat.com>
User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/27.2 (gnu/linux)
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

* Dave Hansen:

> On 7/7/21 11:05 PM, Florian Weimer wrote:
>>> This looks basically like someone dumped a bunch of CPUID bit values and
>>> exposed them to applications without considering whether applications
>>> would ever need them.  For instance, why would an app ever care about:
>>>
>>> 	PKS =E2=80=93 Protection keys for supervisor-mode pages.
>>>
>>> And how could glibc ever give applications accurate information about
>>> whether PKS "is supported by the operating system"?  It just plain
>>> doesn't know, or at least only knows from a really weak ABI like
>>> /proc/cpuinfo.
>> glibc is expected to mask these bits for CPU_FEATURE_USABLE because they
>> have unknown semantics (to glibc).
>
> OK, so if I call CPU_FEATURE_USABLE(PKS) on a system *WITH* PKS
> supported in the operating system, I'll get false from an interface that
> claims to be:
>
>> This macro returns a nonzero value (true) if the processor has the
>> feature name and the feature is supported by the operating system.
>
> The interface just seems buggy by *design*.

Yes, but that is largely a documentation matter.  We should have said
something about =E2=80=9Cuserspace=E2=80=9D there, and that the bit needs t=
o be known to
glibc.  There is another exception: FSGSBASE, and that's a real bug we
need to fix (it has to go through AT_HWCAP2).

If we want to avoid that, we need to go down the road of a curated set
of CPUID bits, where a bit only exists if we have taught glibc its
semantics.  You still might get a false negative by running against an
older glibc than the application was built for.  (We are not going to
force applications that e.g. look for FSGSBASE only run with a glibc
that is at least of that version which implemented semantics for the
FSGSBASE bit.)

Thanks,
Florian