linux-kernel - Re: [RFC PATCH 00/16] x86/split_lock: Enable #AC exception for split locked accesses

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

Message-ID: <20180621200654.GE13636@worktop.programming.kicks-ass.net>
Date:   Thu, 21 Jun 2018 22:06:54 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Dave Hansen <dave.hansen@...el.com>
Cc:     Fenghua Yu <fenghua.yu@...el.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...e.hu>,
        "H. Peter Anvin" <hpa@...ux.intel.com>,
        Ashok Raj <ashok.raj@...el.com>,
        Rafael Wysocki <rafael.j.wysocki@...el.com>,
        Tony Luck <tony.luck@...el.com>,
        Alan Cox <alan@...ux.intel.com>,
        Ravi V Shankar <ravi.v.shankar@...el.com>,
        Arjan van de Ven <arjan@...radead.org>,
        linux-kernel <linux-kernel@...r.kernel.org>, x86 <x86@...nel.org>
Subject: Re: [RFC PATCH 00/16] x86/split_lock: Enable #AC exception for split
 locked accesses

On Tue, May 29, 2018 at 09:40:09AM -0700, Dave Hansen wrote:
> Split-lock-detection is a new hardware feature that generates
> alignment-check (#AC) faults to help detect when badly-aligned atomic
> instructions might impact whole-system performance.  These patches are
> primarily targeted at application-level issues, but we can also detect
> the same issues in the kernel.

Which is nice, Thomas and me spend quite a while searching for a perf
event that could tell us about unaligned LOCK insns a few months back
and could not find anything useful.

> There is a significant interaction
> between this feature and firmware because firmware may or may not be
> prepared for this feature to be enabled.

And allowing firmware to muddle through, instead of drawing a hard line
in the sand means we'll be stuck with crap firmware for at least another
decade :/

Just say no.