linux-kernel - Re: Avoid speculative indirect calls in kernel

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: <20180104000927.co5umvfzfwliqvqt@two.firstfloor.org>
Date:   Wed, 3 Jan 2018 16:09:27 -0800
From:   Andi Kleen <andi@...stfloor.org>
To:     Linus Torvalds <torvalds@...ux-foundation.org>
Cc:     Andi Kleen <andi@...stfloor.org>, tglx@...utronix.de,
        Greg Kroah-Hartman <gregkh@...ux-foundation.org>,
        dwmw@...zon.co.uk, Tim Chen <tim.c.chen@...ux.intel.com>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Dave Hansen <dave.hansen@...el.com>
Subject: Re: Avoid speculative indirect calls in kernel

Hi Linus,

On Wed, Jan 03, 2018 at 03:51:35PM -0800, Linus Torvalds wrote:
> On Wed, Jan 3, 2018 at 3:09 PM, Andi Kleen <andi@...stfloor.org> wrote:
> > This is a fix for Variant 2 in
> > https://googleprojectzero.blogspot.com/2018/01/reading-privileged-memory-with-side.html
> >
> > Any speculative indirect calls in the kernel can be tricked
> > to execute any kernel code, which may allow side channel
> > attacks that can leak arbitrary kernel data.
> 
> Why is this all done without any configuration options?

I was thinking of a config option, but I was struggling with a name.

CONFIG_INSECURE_KERNEL, CONFIG_LEAK_MEMORY? 

And should it be positive or negative?

So I opted to be secure uncontionally.

It would be simple to add however, all hooks are either in the Makefile
or in asm/jump-asm.h

>  - these workarounds should have a way to disable them.
> 

There will be soon patches to add other ways and they have a way
to patch out most of the retpoline overhead at runtime
(basically replace the trampoline with a pure ret)

We just wanted to get the retpoline code out first because
it's the most basic and widest applicable fix.

-Andi