linux-kernel - Re: [PATCH 2/2] x86/speculation: switch_to_cond

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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <alpine.DEB.2.21.1812071032270.3743@nanos.tec.linutronix.de>
Date:   Fri, 7 Dec 2018 10:33:00 +0100 (CET)
From:   Thomas Gleixner <tglx@...utronix.de>
To:     Peter Zijlstra <peterz@...radead.org>
cc:     Waiman Long <longman@...hat.com>, Ingo Molnar <mingo@...hat.com>,
        Borislav Petkov <bp@...en8.de>, x86@...nel.org,
        linux-kernel@...r.kernel.org,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Josh Poimboeuf <jpoimboe@...hat.com>
Subject: Re: [PATCH 2/2] x86/speculation: switch_to_cond_stibp on is the
 likely case

On Fri, 7 Dec 2018, Peter Zijlstra wrote:
> On Thu, Dec 06, 2018 at 10:38:00AM -0500, Waiman Long wrote:
> > On 12/06/2018 03:41 AM, Peter Zijlstra wrote:
> > > On Wed, Dec 05, 2018 at 02:49:28PM -0500, Waiman Long wrote:
> > >> Since conditional STIBP is the default, it should be treated as
> > >> the likely case. Changes the use of static_branch_unlikely() to
> > >> static_branch_likely() for switch_to_cond_stibp.
> > > So now you're making kernels on 'fixed' or unaffected hardware slower.
> > 
> > Good point.
> > 
> > The reason I sent out this patch is because of the inconsistency in the
> > use of likely/unlikely hints.
> > 
> > arch/x86/kernel/cpu/bugs.c:156:        if
> > (static_branch_unlikely(&switch_to_cond_stibp))
> > arch/x86/kernel/process.c:440:       
> > static_branch_unlikely(&switch_to_cond_stibp)) {
> > arch/x86/kernel/process.h:26:        if
> > (!static_branch_likely(&switch_to_cond_stibp)) {
> > 
> > So if we are aiming to optimize for "fixed" or unaffected hardware,
> > maybe we should modify the likely hint to unlikely then.
> 
> Right, I think that makes sense, Thomas?

Yeah, I probably got that wrong in some places. Let me look.

Thanks,

	Thomas