linux-kernel - Re: [PATCH] x86/cpufeatures: Add enumeration for serialize instruction

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20200407013625.GA5587@ranerica-svr.sc.intel.com>
Date:   Mon, 6 Apr 2020 18:36:25 -0700
From:   Ricardo Neri <ricardo.neri-calderon@...ux.intel.com>
To:     Borislav Petkov <bp@...en8.de>
Cc:     Ingo Molnar <mingo@...nel.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        linux-kernel@...r.kernel.org,
        Ricardo Neri <ricardo.neri@...el.com>, x86@...nel.org,
        "Ravi V. Shankar" <ravi.v.shankar@...el.com>
Subject: Re: [PATCH] x86/cpufeatures: Add enumeration for serialize
 instruction

On Sat, Apr 04, 2020 at 10:28:09AM +0200, Borislav Petkov wrote:
> On Fri, Apr 03, 2020 at 10:20:39PM -0700, Ricardo Neri wrote:
> > Do you mean code in the kernel using this instructions. Thus far, I
> > don't have any kernel use cases for this instruction.
> 
> I'm sure you can find at least a couple of places in the kernel
> which use CPUID to serialize and could switch to this new insn with
> alternatives, for example. Or all those memory barrier uses. Would it be
> better to switch to SERIALIZE there? Dunno, but would be good to know.
> And so on.

Yes, I lookede for uses of CPUID for serialization but I didn't find
any. I will look again. I will also look at the memory barrier cases.

Thanks and BR,
Ricardo

> 
> > My intention is to expose this instruction to user space via
> > /proc/cpuinfo. Is that not acceptable?
> 
> I know what your intention is. What good is the string "serialize" in
> /proc/cpuinfo if nothing uses it?

Wouldn't it be useful for userspace tools to see? Admittedly, the would
be looking at CPUID directly, I think.

Thanks and BR,
Ricardo