Date: Thu, 4 Jan 2018 01:31:43 +0100 (CET)
From: Thomas Gleixner <tglx@linutronix.de>
To: Alan Cox <gnomes@lxorguk.ukuu.org.uk>
cc: Andi Kleen <andi@firstfloor.org>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Greg Kroah-Hartman <gregkh@linux-foundation.org>,
        dwmw@amazon.co.uk, Tim Chen <tim.c.chen@linux.intel.com>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Dave Hansen <dave.hansen@intel.com>
Subject: Re: Avoid speculative indirect calls in kernel
In-Reply-To: <20180104002916.3ff66581@alans-desktop>
Message-ID: <alpine.DEB.2.20.1801040131050.1957@nanos>
References: <20180103230934.15788-1-andi@firstfloor.org> <CA+55aFzCocoK+4kxAUEhaxxba4RTv3ewBmhiZ8Osc9iDkBtCEQ@mail.gmail.com> <20180104000927.co5umvfzfwliqvqt@two.firstfloor.org> <alpine.DEB.2.20.1801040110440.1957@nanos> <20180104001501.3jof7zkrfkehnd3r@two.firstfloor.org>
 <20180104002916.3ff66581@alans-desktop>
User-Agent: Alpine 2.20 (DEB 67 2015-01-07)
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org

On Thu, 4 Jan 2018, Alan Cox wrote:
> On Wed, 3 Jan 2018 16:15:01 -0800
> Andi Kleen <andi@firstfloor.org> wrote:
> 
> > > It should be a CPU_BUG bit as we have for the other mess. And that can be
> > > used for patching.  
> > 
> > It has to be done at compile time because it requires a compiler option.
> > 
> > Most of the indirect calls are in C code.
> > 
> > So it cannot just patched in, only partially out.
> 
> You can replace the pushl ; jmp  with an alternatives section (although
> there might be a lot of them). Even if gcc isn't smart enough to do that
> perl is.

So you say, that we finally need a perl interpreter in the kernel to do
alternative patching?

Thanks,

	tglx