Re: [RFC] Retpoline: Binary mitigation for branch-target-injection (aka "Spectre") - Greg Kroah-Hartman

From: Greg Kroah-Hartman <gregkh@linux-foundation.org>
To: Paul Turner <pjt@google.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	"Woodhouse, David" <dwmw@amazon.co.uk>,
	Tim Chen <tim.c.chen@linux.intel.com>,
	Dave Hansen <dave.hansen@intel.com>,
	tglx@linuxtronix.de, Kees Cook <keescook@google.com>,
	Rik van Riel <riel@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Andy Lutomirski <luto@amacapital.net>,
	Jiri Kosina <jikos@kernel.org>,
	gnomes@lxorguk.ukuu.org.uk
Subject: Re: [RFC] Retpoline: Binary mitigation for branch-target-injection (aka "Spectre")
Date: Thu, 4 Jan 2018 10:48:36 +0100	[thread overview]
Message-ID: <20180104094836.GA31023@kroah.com> (raw)
In-Reply-To: <CAPM31RKp=tAz8TQ=tCGQRNHUKWvrC9B4LV3wG+hBUr+rG_FMsQ@mail.gmail.com>

On Thu, Jan 04, 2018 at 01:24:41AM -0800, Paul Turner wrote:
> On Thu, Jan 4, 2018 at 1:10 AM, Paul Turner <pjt@google.com> wrote:
> > Apologies for the discombobulation around today's disclosure.  Obviously the
> > original goal was to communicate this a little more coherently, but the
> > unscheduled advances in the disclosure disrupted the efforts to pull this
> > together more cleanly.
> >
> > I wanted to open discussion the "retpoline" approach and and define its
> > requirements so that we can separate the core
> > details from questions regarding any particular implementation thereof.
> >
> > As a starting point, a full write-up describing the approach is available at:
> >   https://support.google.com/faqs/answer/7625886
> >
> > The 30 second version is:
> > Returns are a special type of indirect branch.  As function returns are intended
> > to pair with function calls, processors often implement dedicated return stack
> > predictors.  The choice of this branch prediction allows us to generate an
> > indirect branch in which speculative execution is intentionally redirected into
> > a controlled location by a return stack target that we control.  Preventing
> > branch target injections (also known as "Spectre") against these binaries.
> >
> > On the targets (Intel Xeon) we have measured so far, cost is within cycles of a
> > "native" indirect branch for which branch prediction hardware has been disabled.
> > This is unfortunately measurable -- from 3 cycles on average to about 30.
> > However the cost is largely mitigated for many workloads since the kernel uses
> > comparatively few indirect branches (versus say, a C++ binary).  With some
> > effort we have the average overall overhead within the 0-1.5% range for our
> > internal workloads, including some particularly high packet processing engines.
> >
> > There are several components, the majority of which are independent of kernel
> > modifications:
> >
> > (1) A compiler supporting retpoline transformations.
> 
> An implementation for LLVM is available at:
>   https://reviews.llvm.org/D41723

Nice, thanks for the link and the write up.  There is also a patch for
gcc floating around somewhere, does anyone have the link for that?

thanks,

greg k-h