linux-kernel - Re: [PATCH 4/7] x86,tlb: make lazy TLB mode lazier

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>] [day] [month] [year] [list]

Message-ID: <CALCETrXhkcMyMo_-dmrQ3M+VJqLS_me5TKA688bdsQo5m1ddzg@mail.gmail.com>
Date:   Thu, 19 Jul 2018 10:18:58 -0700
From:   Andy Lutomirski <luto@...capital.net>
To:     Rik van Riel <riel@...riel.com>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        Andy Lutomirski <luto@...nel.org>,
        LKML <linux-kernel@...r.kernel.org>, X86 ML <x86@...nel.org>,
        Mike Galbraith <efault@....de>,
        kernel-team <kernel-team@...com>, Ingo Molnar <mingo@...nel.org>,
        Dave Hansen <dave.hansen@...el.com>
Subject: Re: [PATCH 4/7] x86,tlb: make lazy TLB mode lazier

On Thu, Jul 19, 2018 at 10:15 AM, Rik van Riel <riel@...riel.com> wrote:
>
>
> Given that CPUs in lazy TLB mode stay part of the mm_cpumask,
> that WARN_ON seems misplaced. You are right though, that the
> mm_cpumask alone should provide enough information for us to
> avoid a need for both tsk->active_mm and the refcounting.
>

If you do this extra shootdown after freeing pagetables, it would be
odd if mm_cpumask() wasn't empty.  But you're right, the warn is
probably silly.  And if you move it into arch_exit_mmap(), the warn is
definitely wrong.

>
> Does all that make sense?  Basically, as I understand it, the
> expensive atomic ops you're seeing are all pointless because they're
> enabling an optimization that hasn't actually worked for a long time,
> if ever.
>
>
> Our benchmark results suggest that lazy TLB mode works, and makes
> a measurable performance difference. Getting rid of the atomic ops
> should make it a little better, though :)
>

I'm not saying lazy mode is useless.  I'm saying that active_mm isn't
needed for x86's lazy mode :)