[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <0575AF4FD06DD142AD198903C74E1CC87A57231E@ORSMSX103.amr.corp.intel.com>
Date: Wed, 10 Jan 2018 13:42:48 +0000
From: "Van De Ven, Arjan" <arjan.van.de.ven@...el.com>
To: Andrea Arcangeli <aarcange@...hat.com>,
David Woodhouse <dwmw2@...radead.org>
CC: Peter Zijlstra <peterz@...radead.org>,
"Hansen, Dave" <dave.hansen@...el.com>,
Thomas Gleixner <tglx@...utronix.de>,
LKML <linux-kernel@...r.kernel.org>,
Linus Torvalds <torvalds@...uxfoundation.org>,
"x86@...nel.org" <x86@...nel.org>,
"Borislav Petkov" <bp@...en8.de>,
Tim Chen <tim.c.chen@...ux.intel.com>,
Andi Kleen <ak@...ux.intel.com>,
Greg KH <gregkh@...uxfoundation.org>,
Andy Lutomirski <luto@...nel.org>
Subject: RE: [patch RFC 5/5] x86/speculation: Add basic speculation control
code
> On Wed, Jan 10, 2018 at 12:12:53PM +0000, David Woodhouse wrote:
> > IBRS is like a barrier. You must write it between the 'problematic'
> > loading of the branch targets, and the kernel code which might be
> > affected.
> >
> > You cannot, on current hardware, merely set it once and forget about
> > it. That is not sufficient.
>
> I think you've got it all wrong...
Andrea: David is right. The specification draft that you have also makes this clear.
You can't just set IBRS once and call it good; you do need to write it on entering the kernel.
Powered by blists - more mailing lists